Crucial DDR5 Memory Benchmarks - AMD Ryzen

Crucial memory review benchmarks by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2302279-NE-RYZENDDR533
Jump To Table - Results

View

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

Limit displaying results to tests within:

AV1 2 Tests
Timed Code Compilation 7 Tests
C/C++ Compiler Tests 10 Tests
Compression Tests 2 Tests
CPU Massive 16 Tests
Creator Workloads 17 Tests
Encoding 7 Tests
Fortran Tests 2 Tests
Game Development 4 Tests
HPC - High Performance Computing 11 Tests
Imaging 2 Tests
Machine Learning 4 Tests
Memory Test Suite 2 Tests
Molecular Dynamics 4 Tests
MPI Benchmarks 3 Tests
Multi-Core 26 Tests
NVIDIA GPU Compute 2 Tests
Intel oneAPI 6 Tests
OpenMPI Tests 5 Tests
Programmer / Developer System Benchmarks 9 Tests
Python Tests 5 Tests
Renderers 2 Tests
Scientific Computing 4 Tests
Server CPU Tests 14 Tests
Video Encoding 7 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests 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
DDR5-4800 Crucial
February 22 2023
  6 Hours, 30 Minutes
DDR5-5200 Crucial
February 24 2023
  7 Hours
DDR5-5600 Crucial
February 23 2023
  6 Hours, 56 Minutes
DDR5-6000 GSKILL F5-6000J3038F16G
February 24 2023
  6 Hours, 17 Minutes
Invert Hiding All Results Option
  6 Hours, 41 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):

DDR5-4800 Crucial

Processor: AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: Gigabyte B650M DS3H (F4h BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: Gigabyte AMD Raphael 512MB (2200/2400MHz), Audio: AMD Rembrandt Radeon HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE

OS: Ubuntu 22.10, Kernel: 6.2.0-060200rc5daily20230129-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49), Vulkan: 1.3.235, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203
Graphics Notes: BAR1 / Visible vRAM Size: 512 MB - vBIOS Version: 102-RAPHAEL-008
Python Notes: Python 3.10.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

DDR5-5600 Crucial

Changed Graphics to Gigabyte AMD Raphael 512MB (2200/2800MHz).

DDR5-5200 Crucial

Changed Graphics to Gigabyte AMD Raphael 512MB (2200/2600MHz).

DDR5-6000 GSKILL F5-6000J3038F16G

Changed Graphics to Gigabyte AMD Raphael 512MB (2200/3000MHz).

Crucial DDR5 Memory Benchmarks - AMD RyzenOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads)Gigabyte B650M DS3H (F4h BIOS)AMD Device 14d832GB1000GB Sabrent Rocket 4.0 PlusGigabyte AMD Raphael 512MB (2200/2400MHz)Gigabyte AMD Raphael 512MB (2200/2800MHz)Gigabyte AMD Raphael 512MB (2200/2600MHz)Gigabyte AMD Raphael 512MB (2200/3000MHz)AMD Rembrandt Radeon HD AudioASUS VP28URealtek RTL8125 2.5GbEUbuntu 22.106.2.0-060200rc5daily20230129-generic (x86_64)GNOME Shell 43.0X Server 1.21.1.4 + Wayland4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49)1.3.235GCC 12.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionCrucial DDR5 Memory Benchmarks - AMD Ryzen PerformanceSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203- BAR1 / Visible vRAM Size: 512 MB - vBIOS Version: 102-RAPHAEL-008- Python 3.10.7- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

DDR5-4800 CrucialDDR5-5600 CrucialDDR5-5200 CrucialDDR5-6000 GSKILL F5-6000J3038F16GResult OverviewPhoronix Test Suite100%110%119%129%138%StreamXcompact3d Incompact3dRAMspeed SMPNAS Parallel BenchmarksnekRSDarktableONNX RuntimeOpenFOAMSVT-VP9GROMACSXonoticSVT-AV17-Zip Compressiondav1dOpenVKLRawTherapeeZstd CompressionEmbreeBlenderminiBUDETimed PHP CompilationVP9 libvpx EncodingTimed Mesa CompilationNAMDuvg266SVT-HEVConeDNNTimed Godot Game Engine CompilationBuild2Intel Open Image DenoiseOpenVINONeural Magic DeepSparseTimed FFmpeg CompilationTimed MPlayer CompilationVVenCsimdjsonTimed Linux Kernel CompilationOSPRay Studio

Crucial DDR5 Memory Benchmarks - AMD Ryzennpb: IS.Dnpb: SP.Cstream: Addstream: Triadnpb: SP.Bstream: Scaleramspeed: Copy - Integerincompact3d: input.i3d 129 Cells Per Directionramspeed: Scale - Integerramspeed: Copy - Floating Pointramspeed: Scale - Floating Pointstream: Copyramspeed: Average - Floating Pointramspeed: Average - Integerramspeed: Triad - Floating Pointramspeed: Add - Integerramspeed: Triad - Integerramspeed: Add - Floating Pointdarktable: Server Room - CPU-onlyopenfoam: drivaerFastback, Small Mesh Size - Execution Timenekrs: TurboPipe Periodicnpb: CG.Cnpb: FT.Cnpb: BT.Cdarktable: Masskrug - CPU-onlysvt-vp9: PSNR/SSIM Optimized - Bosphorus 4Knpb: LU.Conednn: IP Shapes 3D - bf16bf16bf16 - CPUcompress-7zip: Compression Ratingopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUsvt-av1: Preset 12 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Ksvt-hevc: 10 - Bosphorus 4Kdav1d: Summer Nature 4Kdarktable: Boat - CPU-onlysvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080pcompress-zstd: 19 - Compression Speedgromacs: MPI CPU - water_GMX50_baresvt-vp9: Visual Quality Optimized - Bosphorus 4Kdav1d: Chimera 1080p 10-bitsvt-av1: Preset 13 - Bosphorus 1080pembree: Pathtracer ISPC - Asian Dragonxonotic: 3840 x 2160 - Lowsvt-vp9: Visual Quality Optimized - Bosphorus 1080popenvkl: vklBenchmark ISPCcompress-zstd: 19, Long Mode - Compression Speedsvt-hevc: 10 - Bosphorus 1080pembree: Pathtracer - Asian Dragonopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdarktable: Server Rack - CPU-onlydeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamrawtherapee: Total Benchmark Timedeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamopenfoam: drivaerFastback, Small Mesh Size - Mesh Timevpxenc: Speed 5 - Bosphorus 4Kdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamsimdjson: Kostyasvt-hevc: 1 - Bosphorus 1080popenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUsvt-hevc: 1 - Bosphorus 4Kopenvino: Weld Porosity Detection FP16-INT8 - CPUblender: BMW27 - CPU-Onlyopenvkl: vklBenchmark Scalarminibude: OpenMP - BM1minibude: OpenMP - BM1openvino: Face Detection FP16-INT8 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUopenvino: Face Detection FP16-INT8 - CPUdav1d: Chimera 1080puvg266: Bosphorus 4K - Slowopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUsvt-hevc: 7 - Bosphorus 4Kopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUdav1d: Summer Nature 1080pbuild-php: Time To Compilebuild-mesa: Time To Compileonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamnamd: ATPase Simulation - 327,506 Atomsdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamuvg266: Bosphorus 4K - Super Fastsvt-av1: Preset 8 - Bosphorus 4Kuvg266: Bosphorus 1080p - Slowvpxenc: Speed 5 - Bosphorus 1080pcompress-7zip: Decompression Ratinguvg266: Bosphorus 1080p - Ultra Fastuvg266: Bosphorus 1080p - Super Fastbuild-godot: Time To Compileuvg266: Bosphorus 4K - Ultra Fastbuild2: Time To Compileoidn: RT.ldr_alb_nrm.3840x2160deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamvvenc: Bosphorus 1080p - Fasterdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamospray-studio: 1 - 1080p - 32 - Path Tracerospray-studio: 3 - 1080p - 32 - Path Tracervpxenc: Speed 0 - Bosphorus 4Kvvenc: Bosphorus 4K - Fastospray-studio: 3 - 1080p - 16 - Path Tracerbuild-ffmpeg: Time To Compilevvenc: Bosphorus 4K - Fasterdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamospray-studio: 1 - 1080p - 16 - Path Tracerbuild-mplayer: Time To Compilesvt-hevc: 7 - Bosphorus 1080pdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamembree: Pathtracer ISPC - Crownsimdjson: DistinctUserIDsimdjson: TopTweetembree: Pathtracer - Crowndeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamcompress-zstd: 19, Long Mode - Decompression Speedopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUsimdjson: PartialTweetsbuild-linux-kernel: defconfigcompress-zstd: 19 - Decompression Speedvvenc: Bosphorus 1080p - Fastonnx: GPT-2 - CPU - Standardonnx: GPT-2 - CPU - Standardsvt-vp9: VMAF Optimized - Bosphorus 1080psvt-vp9: VMAF Optimized - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 1080pDDR5-4800 CrucialDDR5-5600 CrucialDDR5-5200 CrucialDDR5-6000 GSKILL F5-6000J3038F16G1132.4710263.2536067.936119.716635.5432611.157672.1218.359361657863.5457636.0357705.0650254.054316.9154303.6950185.1150829.4150696.4751250.683.117214.18347541393666679459.4720676.3635720.433.63091.6738995.381.78174129906601.849.96163.064169.541122.74317.873.387328.2520.91.87479.02724.53642.93226.2354278.2181063278.4028111.8416.9622.979263.8493.9320.0522298.98350.246215.664727.817781.424638.44973.600628.33967821.3376.306378.60255.5416.2316905.916.394.091877.5575.68137930.32337.213324.391.1185318.46849.639.491191.685.0370.170.70840.1001261.9841.92129.6091647.125.071178.2247.01721.17886127.591332.4954.61044.9840.94123754157.25132.0371.32638.3271.4240.6364.559192.923931.029686.5236682.164644958537009.965.1072680629.36211.1678.72152240621.021219.598.771823.91749.639.3021.437429.6800202.05711877.11103.405.438.0962.9652020.312.6157.06313141.545313.9182.62606.0081234.0611236.7839357.639385.618332.5535521.563082.3116.683693663505.6962618.4963282.0954426.859071.1459431.9754896.9256146.5455484.3355117.962.938196.257175767386666710111.1222185.8837635.363.51097.1241426.361.66794135898635.919.43169.835176.374127.29332.413.295341.2921.21.97282.19732.68666.42926.9281283.6535071286.5028711.9428.8823.158461.6797.2319.8195302.46270.238209.559928.628083.787137.48971.529128.24621621.4174.762680.22595.6416.6317347.886.214.191929.6073.40139951.60638.064314.821.0867519.01820.139.681224.324.9072.330.69816.9171264.0141.06128.8871608.995.221141.5145.27191.14420132.481433.1256.34145.6141.36127567159.87134.5570.17239.0770.1140.6565.824091.139431.617672.8767672.3835438005234410.145.2192618928.69211.4218.86412192520.595224.138.871224.39739.819.4321.806629.1506205.72581908.41120.295.358.1562.2772044.012.7587.13655140.725325.0587.64620.7011189.6310678.4037460.937479.717428.0533827.159626.9417.552132359984.4259788.3060066.6751828.356333.2556191.8552228.8152635.9052568.1852756.422.969204.194135605436666710041.1121328.1436718.643.53494.3739990.711.71172134635623.469.62168.002174.459125.16314.513.331335.4421.31.91880.74733.20658.94326.6015284.0406829282.8128411.8422.8323.333462.8695.3919.8500302.02380.243212.227328.268282.847237.90872.355427.9603321.8575.587179.35105.5616.2417036.386.334.091895.4975.12138931.54337.262320.801.1100118.67847.809.471201.724.9970.750.7831.6191251.7541.16729.1531629.815.151160.4146.17511.17476129.896132.4255.41644.8041.62125579157.09132.0270.11538.3670.2290.6364.248293.343531.279681.5878682.3991443495292910.085.1182647229.05911.2308.77682215520.849219.768.771924.08029.739.4021.599929.3561204.28341903.11107.265.418.1362.0972037.312.6627.05429142.051320.1685.44591.8311649.0314295.2450039.750067.822999.9245060.979494.8813.383389279287.3578883.2978949.1968650.473941.5973776.8668037.8468724.8168139.7568527.112.359164.688987038946666712203.7926587.4945575.202.853110.7547062.831.47980156104717.898.35190.695195.544141.43361.862.954373.7723.72.12489.33815.29717.75229.1782308.9703437307.7731012.9455.1224.958059.00101.6318.6645321.20620.229200.990729.839187.038435.97568.866126.62513322.6472.116283.14495.8515.7616452.836.543.981833.2477.19144906.28036.251330.231.1396818.14859.069.251171.245.1273.240.72851.7251304.1940.26228.4511673.325.271134.1546.24421.18817129.673531.9156.65243.9742.46123051154.49130.0469.02737.8269.2100.6463.870993.900131.939691.4755690.1760447025315310.215.0972658829.15811.3968.67212234921.008220.538.691624.29009.709.2621.828229.3435204.37221909.51113.205.398.0362.3962029.812.6146.06455165.644360.18100.65650.380OpenBenchmarking.org

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial400800120016002000SE +/- 16.70, N = 3SE +/- 5.67, N = 3SE +/- 8.96, N = 3SE +/- 8.55, N = 31649.031189.631234.061132.471. (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 4.1.4

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial3K6K9K12K15KSE +/- 25.94, N = 3SE +/- 13.13, N = 3SE +/- 26.03, N = 3SE +/- 3.19, N = 314295.2410678.4011236.7810263.251. (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 4.1.4

Stream

This is a benchmark of Stream, the popular system memory (RAM) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: AddDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial11K22K33K44K55KSE +/- 27.60, N = 5SE +/- 26.33, N = 5SE +/- 47.43, N = 5SE +/- 87.68, N = 550039.737460.939357.636067.91. (CC) gcc options: -mcmodel=medium -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: TriadDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial11K22K33K44K55KSE +/- 19.20, N = 5SE +/- 40.56, N = 5SE +/- 38.04, N = 5SE +/- 91.75, N = 550067.837479.739385.636119.71. (CC) gcc options: -mcmodel=medium -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: SP.BDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial5K10K15K20K25KSE +/- 46.57, N = 3SE +/- 32.68, N = 3SE +/- 76.77, N = 3SE +/- 43.60, N = 322999.9217428.0518332.5516635.541. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.4

Stream

This is a benchmark of Stream, the popular system memory (RAM) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: ScaleDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial10K20K30K40K50KSE +/- 23.91, N = 5SE +/- 15.94, N = 5SE +/- 29.87, N = 5SE +/- 10.16, N = 545060.933827.135521.532611.11. (CC) gcc options: -mcmodel=medium -O3 -march=native -fopenmp

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: IntegerDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20K40K60K80K100KSE +/- 45.91, N = 3SE +/- 395.61, N = 3SE +/- 410.72, N = 3SE +/- 346.96, N = 379494.8859626.9463082.3157672.121. (CC) gcc options: -O3 -march=native

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 DirectionDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial510152025SE +/- 0.13, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 313.3817.5516.6818.361. (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

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: IntegerDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20K40K60K80K100KSE +/- 424.34, N = 3SE +/- 236.91, N = 3SE +/- 160.50, N = 3SE +/- 197.53, N = 379287.3559984.4263505.6957863.541. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating PointDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20K40K60K80K100KSE +/- 387.73, N = 3SE +/- 339.34, N = 3SE +/- 328.95, N = 3SE +/- 386.33, N = 378883.2959788.3062618.4957636.031. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Floating PointDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20K40K60K80K100KSE +/- 466.69, N = 3SE +/- 207.41, N = 3SE +/- 350.00, N = 3SE +/- 304.13, N = 378949.1960066.6763282.0957705.061. (CC) gcc options: -O3 -march=native

Stream

This is a benchmark of Stream, the popular system memory (RAM) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: CopyDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial15K30K45K60K75KSE +/- 76.39, N = 5SE +/- 25.98, N = 5SE +/- 37.52, N = 5SE +/- 25.41, N = 568650.451828.354426.850254.01. (CC) gcc options: -mcmodel=medium -O3 -march=native -fopenmp

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Floating PointDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial16K32K48K64K80KSE +/- 538.63, N = 3SE +/- 247.49, N = 3SE +/- 75.68, N = 3SE +/- 119.93, N = 373941.5956333.2559071.1454316.911. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: IntegerDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial16K32K48K64K80KSE +/- 246.81, N = 3SE +/- 352.40, N = 3SE +/- 209.97, N = 3SE +/- 135.76, N = 373776.8656191.8559431.9754303.691. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Floating PointDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial15K30K45K60K75KSE +/- 205.18, N = 3SE +/- 232.54, N = 3SE +/- 331.02, N = 3SE +/- 359.53, N = 368037.8452228.8154896.9250185.111. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: IntegerDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial15K30K45K60K75KSE +/- 248.69, N = 3SE +/- 532.23, N = 3SE +/- 383.49, N = 3SE +/- 472.49, N = 368724.8152635.9056146.5450829.411. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: IntegerDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial15K30K45K60K75KSE +/- 130.98, N = 3SE +/- 424.73, N = 3SE +/- 149.06, N = 3SE +/- 177.80, N = 368139.7552568.1855484.3350696.471. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Floating PointDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial15K30K45K60K75KSE +/- 364.18, N = 3SE +/- 417.65, N = 3SE +/- 102.99, N = 3SE +/- 236.30, N = 368527.1152756.4255117.9651250.681. (CC) gcc options: -O3 -march=native

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 4.0.0Test: Server Room - Acceleration: CPU-onlyDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial0.70131.40262.10392.80523.5065SE +/- 0.003, N = 3SE +/- 0.016, N = 3SE +/- 0.010, N = 3SE +/- 0.014, N = 32.3592.9692.9383.117

OpenFOAM

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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution TimeDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial50100150200250164.69204.19196.26214.181. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

nekRS

nekRS is an open-source Navier Stokes solver based on the spectral element method. NekRS supports both CPU and GPU/accelerator support though this test profile is currently configured for CPU execution. NekRS is part of Nek5000 of the Mathematics and Computer Science MCS at Argonne National Laboratory. This nekRS benchmark is primarily relevant to large core count HPC servers and otherwise may be very time consuming. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFLOP/s, More Is BetternekRS 22.0Input: TurboPipe PeriodicDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial15000M30000M45000M60000M75000MSE +/- 20525214.85, N = 3SE +/- 67017170.27, N = 3SE +/- 50616510.26, N = 3SE +/- 7097495.65, N = 3703894666675605436666757673866667541393666671. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -lmpi_cxx -lmpi

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.CDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial3K6K9K12K15KSE +/- 37.16, N = 3SE +/- 9.20, N = 3SE +/- 69.78, N = 3SE +/- 52.11, N = 312203.7910041.1110111.129459.471. (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 4.1.4

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial6K12K18K24K30KSE +/- 115.28, N = 3SE +/- 37.79, N = 3SE +/- 28.58, N = 3SE +/- 52.45, N = 326587.4921328.1422185.8820676.361. (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 4.1.4

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial10K20K30K40K50KSE +/- 153.54, N = 3SE +/- 126.24, N = 3SE +/- 134.18, N = 3SE +/- 126.80, N = 345575.2036718.6437635.3635720.431. (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 4.1.4

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 4.0.0Test: Masskrug - Acceleration: CPU-onlyDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial0.81681.63362.45043.26724.084SE +/- 0.010, N = 3SE +/- 0.024, N = 3SE +/- 0.020, N = 3SE +/- 0.032, N = 32.8533.5343.5103.630

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 4KDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20406080100SE +/- 0.23, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3110.7594.3797.1291.671. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial10K20K30K40K50KSE +/- 38.06, N = 3SE +/- 312.16, N = 3SE +/- 67.14, N = 3SE +/- 50.25, N = 347062.8339990.7141426.3638995.381. (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 4.1.4

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial0.40090.80181.20271.60362.0045SE +/- 0.00475, N = 3SE +/- 0.01014, N = 3SE +/- 0.00606, N = 3SE +/- 0.00200, N = 31.479801.711721.667941.78174MIN: 1.39MIN: 1.62MIN: 1.59MIN: 1.691. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

7-Zip Compression

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

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial30K60K90K120K150KSE +/- 235.04, N = 3SE +/- 132.99, N = 3SE +/- 97.51, N = 3SE +/- 223.88, N = 31561041346351358981299061. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial150300450600750SE +/- 2.88, N = 3SE +/- 2.99, N = 3SE +/- 2.47, N = 3SE +/- 1.53, N = 3717.89623.46635.91601.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial3691215SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 38.359.629.439.96MIN: 4.86 / MAX: 16.16MIN: 4.09 / MAX: 21.97MIN: 4.72 / MAX: 21.22MIN: 6.2 / MAX: 21.441. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

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 1.4Encoder Mode: Preset 12 - Input: Bosphorus 4KDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial4080120160200SE +/- 0.68, N = 3SE +/- 0.26, N = 3SE +/- 1.16, N = 3SE +/- 0.75, N = 3190.70168.00169.84163.061. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 13 - Input: Bosphorus 4KDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial4080120160200SE +/- 0.86, N = 3SE +/- 1.10, N = 3SE +/- 0.51, N = 3SE +/- 0.86, N = 3195.54174.46176.37169.541. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4KDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial306090120150SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.11, N = 3141.43125.16127.29122.741. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

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 1.1Video Input: Summer Nature 4KDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial80160240320400SE +/- 2.26, N = 3SE +/- 1.30, N = 3SE +/- 0.26, N = 3SE +/- 3.63, N = 3361.86314.51332.41317.871. (CC) gcc options: -pthread -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 4.0.0Test: Boat - Acceleration: CPU-onlyDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial0.76211.52422.28633.04843.8105SE +/- 0.007, N = 3SE +/- 0.014, N = 3SE +/- 0.004, N = 3SE +/- 0.021, N = 32.9543.3313.2953.387

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 1080pDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial80160240320400SE +/- 0.76, N = 3SE +/- 0.63, N = 3SE +/- 0.37, N = 3SE +/- 0.96, N = 3373.77335.44341.29328.251. (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 (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression SpeedDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial612182430SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 323.721.321.220.91. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

GROMACS

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

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial0.47790.95581.43371.91162.3895SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.000, N = 3SE +/- 0.002, N = 32.1241.9181.9721.8741. (CXX) g++ options: -O3

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 4KDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20406080100SE +/- 0.46, N = 3SE +/- 0.26, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 389.3380.7482.1979.021. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -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 1.1Video Input: Chimera 1080p 10-bitDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial2004006008001000SE +/- 2.44, N = 3SE +/- 4.88, N = 3SE +/- 0.79, N = 3SE +/- 2.04, N = 3815.29733.20732.68724.531. (CC) gcc options: -pthread -lm

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 13 - Input: Bosphorus 1080pDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial150300450600750SE +/- 5.69, N = 3SE +/- 5.26, N = 3SE +/- 7.13, N = 3SE +/- 2.37, N = 3717.75658.94666.43642.931. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer ISPC - Model: Asian DragonDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial714212835SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 329.1826.6026.9326.24MIN: 28.98 / MAX: 29.52MIN: 26.37 / MAX: 27.17MIN: 26.74 / MAX: 27.51MIN: 25.95 / MAX: 26.85

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.5Resolution: 3840 x 2160 - Effects Quality: LowDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial70140210280350SE +/- 0.83, N = 3SE +/- 0.46, N = 3SE +/- 1.03, N = 3SE +/- 0.52, N = 3308.97284.04283.65278.22MIN: 122 / MAX: 641MIN: 109 / MAX: 585MIN: 109 / MAX: 580MIN: 110 / MAX: 557

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 1080pDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial70140210280350SE +/- 0.34, N = 3SE +/- 0.35, N = 3SE +/- 0.14, N = 3SE +/- 0.40, N = 3307.77282.81286.50278.401. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.3.1Benchmark: vklBenchmark ISPCDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial70140210280350SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3310284287281MIN: 37 / MAX: 4615MIN: 38 / MAX: 3791MIN: 39 / MAX: 3765MIN: 38 / MAX: 3711

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression SpeedDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial3691215SE +/- 0.16, N = 4SE +/- 0.12, N = 15SE +/- 0.13, N = 15SE +/- 0.11, N = 1512.911.811.911.81. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial100200300400500SE +/- 0.76, N = 3SE +/- 4.52, N = 3SE +/- 0.81, N = 3SE +/- 0.93, N = 3455.12422.83428.88416.961. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer - Model: Asian DragonDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial612182430SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 324.9623.3323.1622.98MIN: 24.85 / MAX: 25.16MIN: 23.22 / MAX: 23.57MIN: 23.03 / MAX: 23.49MIN: 22.89 / MAX: 23.22

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1428425670SE +/- 0.12, N = 3SE +/- 0.14, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 359.0062.8661.6763.84MIN: 33.51 / MAX: 70.25MIN: 32.47 / MAX: 75.08MIN: 27.33 / MAX: 73.13MIN: 28.71 / MAX: 78.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20406080100SE +/- 0.21, N = 3SE +/- 0.21, N = 3SE +/- 0.23, N = 3SE +/- 0.17, N = 3101.6395.3997.2393.931. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial510152025SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 318.6619.8519.8220.05

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial70140210280350SE +/- 0.45, N = 3SE +/- 0.25, N = 3SE +/- 0.26, N = 3SE +/- 0.38, N = 3321.21302.02302.46298.98

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 4.0.0Test: Server Rack - Acceleration: CPU-onlyDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial0.05540.11080.16620.22160.277SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.002, N = 3SE +/- 0.000, N = 30.2290.2430.2380.246

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial50100150200250SE +/- 0.01, N = 3SE +/- 0.33, N = 3SE +/- 0.10, N = 3SE +/- 0.30, N = 3200.99212.23209.56215.66

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial714212835SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 329.8428.2728.6327.82

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20406080100SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.30, N = 3SE +/- 0.08, N = 387.0482.8583.7981.42

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 TimeDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial918273645SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 335.9837.9137.4938.451. RawTherapee, version 5.8, command line.

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1632486480SE +/- 0.03, N = 3SE +/- 0.16, N = 3SE +/- 0.26, N = 3SE +/- 0.08, N = 368.8772.3671.5373.60

OpenFOAM

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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh TimeDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial71421283526.6327.9628.2528.341. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

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 1.13Speed: Speed 5 - Input: Bosphorus 4KDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial510152025SE +/- 0.17, N = 3SE +/- 0.24, N = 5SE +/- 0.08, N = 3SE +/- 0.10, N = 322.6421.8521.4121.331. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20406080100SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.12, N = 3SE +/- 0.18, N = 372.1275.5974.7676.31

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20406080100SE +/- 0.05, N = 3SE +/- 0.19, N = 3SE +/- 0.13, N = 3SE +/- 0.18, N = 383.1479.3580.2378.60

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: KostyaDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1.31632.63263.94895.26526.5815SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 35.855.565.645.541. (CXX) g++ options: -O3

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial48121620SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 315.7616.2416.6316.231. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial4K8K12K16K20KSE +/- 15.11, N = 3SE +/- 4.87, N = 3SE +/- 18.16, N = 3SE +/- 8.58, N = 316452.8317036.3817347.8816905.911. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial246810SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 36.546.336.216.39MIN: 3.32 / MAX: 13.8MIN: 3.26 / MAX: 15.78MIN: 3.22 / MAX: 14.03MIN: 3.57 / MAX: 14.741. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 4KDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial0.94281.88562.82843.77124.714SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.984.094.194.091. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial400800120016002000SE +/- 1.40, N = 3SE +/- 1.07, N = 3SE +/- 0.36, N = 3SE +/- 0.45, N = 31833.241895.491929.601877.551. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: BMW27 - Compute: CPU-OnlyDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20406080100SE +/- 0.06, N = 3SE +/- 0.26, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 377.1975.1273.4075.68

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.3.1Benchmark: vklBenchmark ScalarDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial306090120150SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3144138139137MIN: 12 / MAX: 2882MIN: 13 / MAX: 2555MIN: 13 / MAX: 2552MIN: 13 / MAX: 2536

miniBUDE

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

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1DDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial2004006008001000SE +/- 0.40, N = 3SE +/- 0.47, N = 3SE +/- 0.53, N = 3SE +/- 0.92, N = 3906.28931.54951.61930.321. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1DDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial918273645SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 336.2537.2638.0637.211. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial70140210280350SE +/- 0.33, N = 3SE +/- 0.73, N = 3SE +/- 0.43, N = 3SE +/- 0.27, N = 3330.23320.80314.82324.39MIN: 294.04 / MAX: 356.94MIN: 251.8 / MAX: 345.27MIN: 286.85 / MAX: 334.42MIN: 292.86 / MAX: 346.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial0.25640.51280.76921.02561.282SE +/- 0.00178, N = 3SE +/- 0.00409, N = 3SE +/- 0.00235, N = 3SE +/- 0.00226, N = 31.139681.110011.086751.11853MIN: 1.02MIN: 1MIN: 1.01MIN: 1.021. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial510152025SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 318.1418.6719.0118.461. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

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 1.1Video Input: Chimera 1080pDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial2004006008001000SE +/- 6.09, N = 15SE +/- 3.47, N = 3SE +/- 8.96, N = 15SE +/- 1.12, N = 3859.06847.80820.13849.631. (CC) gcc options: -pthread -lm

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: SlowDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 39.259.479.689.49

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial30060090012001500SE +/- 0.53, N = 3SE +/- 1.27, N = 3SE +/- 0.53, N = 3SE +/- 2.26, N = 31171.241201.721224.321191.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1.1522.3043.4564.6085.76SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 35.124.994.905.03MIN: 3.24 / MAX: 13.03MIN: 2.99 / MAX: 13.44MIN: 3.02 / MAX: 13.29MIN: 3.05 / MAX: 14.521. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 4KDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1632486480SE +/- 0.08, N = 3SE +/- 0.17, N = 3SE +/- 0.15, N = 3SE +/- 0.20, N = 373.2470.7572.3370.171. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial0.1620.3240.4860.6480.81SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.720.700.690.70MIN: 0.39 / MAX: 7.49MIN: 0.36 / MAX: 7.92MIN: 0.38 / MAX: 8.15MIN: 0.39 / MAX: 9.571. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial2004006008001000SE +/- 0.89, N = 3SE +/- 1.10, N = 3SE +/- 1.60, N = 3SE +/- 1.36, N = 3851.73831.62816.92840.10MIN: 845.63MIN: 825.44MIN: 811.08MIN: 833.681. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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 1.1Video Input: Summer Nature 1080pDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial30060090012001500SE +/- 4.34, N = 3SE +/- 1.29, N = 3SE +/- 1.05, N = 3SE +/- 4.63, N = 31304.191251.751264.011261.981. (CC) gcc options: -pthread -lm

Timed PHP Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 8.1.9Time To CompileDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1020304050SE +/- 0.43, N = 3SE +/- 0.27, N = 3SE +/- 0.17, N = 3SE +/- 0.14, N = 340.2641.1741.0641.92

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 CompileDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial714212835SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 328.4529.1528.8929.61

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial400800120016002000SE +/- 2.77, N = 3SE +/- 1.11, N = 3SE +/- 0.27, N = 3SE +/- 1.81, N = 31673.321629.811608.991647.12MIN: 1664.25MIN: 1623.3MIN: 1604.05MIN: 1635.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1.18582.37163.55744.74325.929SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 35.275.155.225.071. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial30060090012001500SE +/- 2.32, N = 3SE +/- 4.21, N = 3SE +/- 4.13, N = 3SE +/- 4.77, N = 31134.151160.411141.511178.22MIN: 648.21 / MAX: 1251.21MIN: 726.59 / MAX: 1322.42MIN: 957.05 / MAX: 1331.52MIN: 669.64 / MAX: 1367.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1122334455SE +/- 0.04, N = 3SE +/- 0.27, N = 3SE +/- 0.16, N = 3SE +/- 0.39, N = 346.2446.1845.2747.02

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 AtomsDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial0.26730.53460.80191.06921.3365SE +/- 0.00066, N = 3SE +/- 0.00082, N = 3SE +/- 0.00278, N = 3SE +/- 0.00227, N = 31.188171.174761.144201.17886

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial306090120150SE +/- 0.10, N = 3SE +/- 0.76, N = 3SE +/- 0.48, N = 3SE +/- 1.07, N = 3129.67129.90132.48127.59

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial816243240SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 331.9132.4233.1232.49

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 1.4Encoder Mode: Preset 8 - Input: Bosphorus 4KDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1326395265SE +/- 0.77, N = 3SE +/- 0.76, N = 3SE +/- 0.65, N = 4SE +/- 0.66, N = 356.6555.4256.3454.611. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: SlowDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1020304050SE +/- 0.07, N = 3SE +/- 0.29, N = 3SE +/- 0.08, N = 3SE +/- 0.13, N = 343.9744.8045.6144.98

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 1.13Speed: Speed 5 - Input: Bosphorus 1080pDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1020304050SE +/- 0.29, N = 3SE +/- 0.30, N = 3SE +/- 0.53, N = 3SE +/- 0.36, N = 342.4641.6241.3640.941. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

7-Zip Compression

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

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial30K60K90K120K150KSE +/- 185.70, N = 3SE +/- 308.03, N = 3SE +/- 95.34, N = 3SE +/- 254.19, N = 31230511255791275671237541. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Ultra FastDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial4080120160200SE +/- 0.23, N = 3SE +/- 0.11, N = 3SE +/- 0.46, N = 3SE +/- 0.26, N = 3154.49157.09159.87157.25

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Super FastDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial306090120150SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.21, N = 3130.04132.02134.55132.03

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 CompileDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1632486480SE +/- 0.05, N = 3SE +/- 0.17, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 369.0370.1270.1771.33

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial918273645SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 337.8238.3639.0738.32

Build2

This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1632486480SE +/- 0.09, N = 3SE +/- 0.20, N = 3SE +/- 0.32, N = 3SE +/- 0.17, N = 369.2170.2370.1171.42

Intel Open Image Denoise

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

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x2160DDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial0.14630.29260.43890.58520.7315SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.640.630.650.63

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1530456075SE +/- 0.33, N = 3SE +/- 0.28, N = 3SE +/- 0.16, N = 3SE +/- 0.05, N = 363.8764.2565.8264.56

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20406080100SE +/- 0.49, N = 3SE +/- 0.40, N = 3SE +/- 0.22, N = 3SE +/- 0.08, N = 393.9093.3491.1492.92

VVenC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 1080p - Video Preset: FasterDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial714212835SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 331.9431.2831.6231.031. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial150300450600750SE +/- 0.33, N = 3SE +/- 0.38, N = 3SE +/- 1.02, N = 3SE +/- 0.67, N = 3691.48681.59672.88686.52

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial150300450600750SE +/- 1.07, N = 3SE +/- 0.44, N = 3SE +/- 0.72, N = 3SE +/- 1.62, N = 3690.18682.40672.38682.16

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 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial10K20K30K40K50KSE +/- 49.51, N = 3SE +/- 20.00, N = 3SE +/- 73.26, N = 3SE +/- 88.32, N = 3447024434943800449581. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial12K24K36K48K60KSE +/- 42.31, N = 3SE +/- 53.84, N = 3SE +/- 83.76, N = 3SE +/- 104.15, N = 3531535292952344537001. (CXX) g++ options: -O3 -lm -ldl

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 1.13Speed: Speed 0 - Input: Bosphorus 4KDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial3691215SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 310.2110.0810.149.961. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

VVenC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: FastDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1.17432.34863.52294.69725.8715SE +/- 0.027, N = 3SE +/- 0.028, N = 3SE +/- 0.021, N = 3SE +/- 0.024, N = 35.0975.1185.2195.1071. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

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 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial6K12K18K24K30KSE +/- 51.45, N = 3SE +/- 23.63, N = 3SE +/- 41.35, N = 3SE +/- 1.53, N = 3265882647226189268061. (CXX) g++ options: -O3 -lm -ldl

Timed FFmpeg Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.4Time To CompileDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial714212835SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 329.1629.0628.6929.36

VVenC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: FasterDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial3691215SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 311.4011.2311.4211.171. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial246810SE +/- 0.0044, N = 3SE +/- 0.0048, N = 3SE +/- 0.0265, N = 3SE +/- 0.0072, N = 38.67218.77688.86418.7215

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 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial5K10K15K20K25KSE +/- 19.65, N = 3SE +/- 35.80, N = 3SE +/- 3.84, N = 3SE +/- 34.96, N = 3223492215521925224061. (CXX) g++ options: -O3 -lm -ldl

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 CompileDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 321.0120.8520.6021.02

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial50100150200250SE +/- 0.40, N = 3SE +/- 0.42, N = 3SE +/- 0.22, N = 3SE +/- 0.23, N = 3220.53219.76224.13219.591. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial246810SE +/- 0.0140, N = 3SE +/- 0.0065, N = 3SE +/- 0.0190, N = 3SE +/- 0.0222, N = 38.69168.77198.87128.7718

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer ISPC - Model: CrownDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial612182430SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 324.2924.0824.4023.92MIN: 24.05 / MAX: 24.82MIN: 23.85 / MAX: 24.64MIN: 24.12 / MAX: 25.16MIN: 23.69 / MAX: 24.48

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserIDDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial3691215SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 39.709.739.819.631. (CXX) g++ options: -O3

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweetDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial3691215SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 39.269.409.439.301. (CXX) g++ options: -O3

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer - Model: CrownDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial510152025SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 321.8321.6021.8121.44MIN: 21.61 / MAX: 22.23MIN: 21.35 / MAX: 22.17MIN: 21.58 / MAX: 22.25MIN: 21.23 / MAX: 21.92

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial714212835SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 329.3429.3629.1529.68

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial50100150200250SE +/- 0.31, N = 3SE +/- 0.20, N = 3SE +/- 0.27, N = 3SE +/- 0.08, N = 3204.37204.28205.73202.06

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression SpeedDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial400800120016002000SE +/- 1.45, N = 4SE +/- 4.08, N = 15SE +/- 6.89, N = 15SE +/- 5.10, N = 151909.51903.11908.41877.11. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial2004006008001000SE +/- 2.28, N = 3SE +/- 0.63, N = 3SE +/- 3.89, N = 3SE +/- 1.12, N = 31113.201107.261120.291103.401. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1.22182.44363.66544.88726.109SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 35.395.415.355.43MIN: 4.06 / MAX: 11.72MIN: 3.94 / MAX: 13.39MIN: 3.9 / MAX: 13.26MIN: 3.94 / MAX: 10.361. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweetsDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial246810SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 38.038.138.158.091. (CXX) g++ options: -O3

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial1428425670SE +/- 0.29, N = 3SE +/- 0.32, N = 3SE +/- 0.22, N = 3SE +/- 0.31, N = 362.4062.1062.2862.97

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression SpeedDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial400800120016002000SE +/- 9.58, N = 3SE +/- 16.15, N = 3SE +/- 15.72, N = 3SE +/- 2.47, N = 32029.82037.32044.02020.31. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

VVenC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 1080p - Video Preset: FastDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial3691215SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 312.6112.6612.7612.621. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

ONNX Runtime

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

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: StandardDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial246810SE +/- 0.11277, N = 15SE +/- 0.09476, N = 15SE +/- 0.12994, N = 15SE +/- 0.02913, N = 36.064557.054297.136557.063131. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: StandardDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial4080120160200SE +/- 3.12, N = 15SE +/- 1.79, N = 15SE +/- 2.53, N = 15SE +/- 0.58, N = 3165.64142.05140.73141.551. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: StandardDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial246810SE +/- 0.11277, N = 15SE +/- 0.09476, N = 15SE +/- 0.12994, N = 15SE +/- 0.02913, N = 36.064557.054297.136557.063131. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial80160240320400SE +/- 7.90, N = 12SE +/- 5.59, N = 12SE +/- 6.00, N = 12SE +/- 5.37, N = 12360.18320.16325.05313.911. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 4KDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial20406080100SE +/- 3.06, N = 15SE +/- 2.08, N = 15SE +/- 2.24, N = 15SE +/- 2.02, N = 15100.6585.4487.6482.621. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 12 - Input: Bosphorus 1080pDDR5-6000 GSKILL F5-6000J3038F16GDDR5-5200 CrucialDDR5-5600 CrucialDDR5-4800 Crucial140280420560700SE +/- 29.03, N = 12SE +/- 23.86, N = 12SE +/- 4.26, N = 3SE +/- 4.49, N = 3650.38591.83620.70606.011. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

138 Results Shown

NAS Parallel Benchmarks:
  IS.D
  SP.C
Stream:
  Add
  Triad
NAS Parallel Benchmarks
Stream
RAMspeed SMP
Xcompact3d Incompact3d
RAMspeed SMP:
  Scale - Integer
  Copy - Floating Point
  Scale - Floating Point
Stream
RAMspeed SMP:
  Average - Floating Point
  Average - Integer
  Triad - Floating Point
  Add - Integer
  Triad - Integer
  Add - Floating Point
Darktable
OpenFOAM
nekRS
NAS Parallel Benchmarks:
  CG.C
  FT.C
  BT.C
Darktable
SVT-VP9
NAS Parallel Benchmarks
oneDNN
7-Zip Compression
OpenVINO:
  Vehicle Detection FP16 - CPU:
    FPS
    ms
SVT-AV1:
  Preset 12 - Bosphorus 4K
  Preset 13 - Bosphorus 4K
SVT-HEVC
dav1d
Darktable
SVT-VP9
Zstd Compression
GROMACS
SVT-VP9
dav1d
SVT-AV1
Embree
Xonotic
SVT-VP9
OpenVKL
Zstd Compression
SVT-HEVC
Embree
OpenVINO:
  Machine Translation EN To DE FP16 - CPU:
    ms
    FPS
Neural Magic DeepSparse:
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream:
    ms/batch
    items/sec
Darktable
Neural Magic DeepSparse:
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream:
    items/sec
RawTherapee
Neural Magic DeepSparse
OpenFOAM
VP9 libvpx Encoding
Neural Magic DeepSparse:
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
simdjson
SVT-HEVC
OpenVINO:
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
SVT-HEVC
OpenVINO
Blender
OpenVKL
miniBUDE:
  OpenMP - BM1:
    GFInst/s
    Billion Interactions/s
OpenVINO
oneDNN
OpenVINO
dav1d
uvg266
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU:
    FPS
    ms
SVT-HEVC
OpenVINO
oneDNN
dav1d
Timed PHP Compilation
Timed Mesa Compilation
oneDNN
OpenVINO:
  Person Detection FP16 - CPU:
    FPS
    ms
Neural Magic DeepSparse
NAMD
Neural Magic DeepSparse
uvg266
SVT-AV1
uvg266
VP9 libvpx Encoding
7-Zip Compression
uvg266:
  Bosphorus 1080p - Ultra Fast
  Bosphorus 1080p - Super Fast
Timed Godot Game Engine Compilation
uvg266
Build2
Intel Open Image Denoise
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
VVenC
Neural Magic DeepSparse:
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream
OSPRay Studio:
  1 - 1080p - 32 - Path Tracer
  3 - 1080p - 32 - Path Tracer
VP9 libvpx Encoding
VVenC
OSPRay Studio
Timed FFmpeg Compilation
VVenC
Neural Magic DeepSparse
OSPRay Studio
Timed MPlayer Compilation
SVT-HEVC
Neural Magic DeepSparse
Embree
simdjson:
  DistinctUserID
  TopTweet
Embree
Neural Magic DeepSparse:
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    ms/batch
    items/sec
Zstd Compression
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU:
    FPS
    ms
simdjson
Timed Linux Kernel Compilation
Zstd Compression
VVenC
ONNX Runtime:
  GPT-2 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
SVT-VP9:
  VMAF Optimized - Bosphorus 1080p
  VMAF Optimized - Bosphorus 4K
SVT-AV1

DDR5-4800 Crucial

Processor: AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: Gigabyte B650M DS3H (F4h BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: Gigabyte AMD Raphael 512MB (2200/2400MHz), Audio: AMD Rembrandt Radeon HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE

OS: Ubuntu 22.10, Kernel: 6.2.0-060200rc5daily20230129-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49), Vulkan: 1.3.235, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203
Graphics Notes: BAR1 / Visible vRAM Size: 512 MB - vBIOS Version: 102-RAPHAEL-008
Python Notes: Python 3.10.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 22 February 2023 13:27 by user phoronix.

DDR5-5600 Crucial

Processor: AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: Gigabyte B650M DS3H (F4h BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: Gigabyte AMD Raphael 512MB (2200/2800MHz), Audio: AMD Rembrandt Radeon HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE

OS: Ubuntu 22.10, Kernel: 6.2.0-060200rc5daily20230129-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49), Vulkan: 1.3.235, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203
Graphics Notes: BAR1 / Visible vRAM Size: 512 MB - vBIOS Version: 102-RAPHAEL-008
Python Notes: Python 3.10.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 February 2023 07:48 by user phoronix.

DDR5-5200 Crucial

Processor: AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: Gigabyte B650M DS3H (F4h BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: Gigabyte AMD Raphael 512MB (2200/2600MHz), Audio: AMD Rembrandt Radeon HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE

OS: Ubuntu 22.10, Kernel: 6.2.0-060200rc5daily20230129-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49), Vulkan: 1.3.235, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203
Graphics Notes: BAR1 / Visible vRAM Size: 512 MB - vBIOS Version: 102-RAPHAEL-008
Python Notes: Python 3.10.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 24 February 2023 06:37 by user phoronix.

DDR5-6000 GSKILL F5-6000J3038F16G

Processor: AMD Ryzen 9 7900 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: Gigabyte B650M DS3H (F4h BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: Gigabyte AMD Raphael 512MB (2200/3000MHz), Audio: AMD Rembrandt Radeon HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE

OS: Ubuntu 22.10, Kernel: 6.2.0-060200rc5daily20230129-generic (x86_64), Desktop: GNOME Shell 43.0, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.0.0-devel (git-e20564c 2022-12-12 kinetic-oibaf-ppa) (LLVM 15.0.5 DRM 3.49), Vulkan: 1.3.235, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203
Graphics Notes: BAR1 / Visible vRAM Size: 512 MB - vBIOS Version: 102-RAPHAEL-008
Python Notes: Python 3.10.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 24 February 2023 12:59 by user phoronix.