Arctic Freezer 4U-M Heatsink - AMD EPYC Siena Benchmarks

AMD EPYC 8534P 64-Core testing of various heatsinks/coolers by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2311220-NE-HSF03125600
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:

C++ Boost Tests 4 Tests
Timed Code Compilation 5 Tests
C/C++ Compiler Tests 3 Tests
Compression Tests 2 Tests
CPU Massive 9 Tests
Creator Workloads 8 Tests
Database Test Suite 3 Tests
Game Development 4 Tests
HPC - High Performance Computing 5 Tests
Java Tests 2 Tests
Common Kernel Benchmarks 2 Tests
Machine Learning 2 Tests
Molecular Dynamics 2 Tests
Multi-Core 16 Tests
Intel oneAPI 6 Tests
OpenMPI Tests 3 Tests
Programmer / Developer System Benchmarks 6 Tests
Python Tests 6 Tests
Renderers 2 Tests
Scientific Computing 3 Tests
Server 4 Tests
Server CPU Tests 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
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Dynatron A54
November 11 2023
  14 Hours, 27 Minutes
NH-D9 TR5-SP6 4U
November 13 2023
  15 Hours, 3 Minutes
Noctua NH-U14S TR5-SP6
November 14 2023
  14 Hours, 8 Minutes
Arctic Freezer 4U-M
November 21 2023
  14 Hours, 10 Minutes
Invert Hiding All Results Option
  14 Hours, 27 Minutes

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


Arctic Freezer 4U-M Heatsink - AMD EPYC Siena BenchmarksOpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads)AMD Cinnabar (RCB1009C BIOS)AMD Device 14a4192GB800GB Micron_7450_MTFDKBA800TFSASPEED2 x Broadcom NetXtreme BCM5720 PCIeUbuntu 23.106.5.0-5-generic (x86_64)GNOME Shell 45.0X Server 1.21.1.7GCC 13.2.0ext4640x480ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionArctic Freezer 4U-M Heatsink - AMD EPYC Siena Benchmarks PerformanceSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212- OpenJDK Runtime Environment (build 11.0.20+8-post-Ubuntu-1ubuntu1)- Python 3.11.5- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Dynatron A54NH-D9 TR5-SP6 4UNoctua NH-U14S TR5-SP6Arctic Freezer 4U-MResult OverviewPhoronix Test Suite100%102%103%105%107%C-BloscPostgreSQLTimed Linux Kernel CompilationOpenFOAMTiDB Community ServerApache IoTDBTimed Gem5 CompilationOpenVINOBlenderRocksDBTimed Godot Game Engine CompilationCoremarkQMCPACKCloverLeafeasyWaveoneDNNTimed LLVM CompilationTimed Node.js CompilationQuantLib7-Zip CompressionDuckDBOpenVKLEmbreeCpuminer-OptDaCapo BenchmarkOSPRay StudioIntel Open Image Denoise

Arctic Freezer 4U-M Heatsink - AMD EPYC Siena Benchmarksopenfoam: drivaerFastback, Small Mesh Size - Mesh Timepgbench: 100 - 1000 - Read Write - Average Latencypgbench: 100 - 1000 - Read Writeopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timeblosc: blosclz shuffle - 64MBblosc: blosclz shuffle - 128MBblosc: blosclz shuffle - 32MBblosc: blosclz shuffle - 8MBblosc: blosclz shuffle - 256MBblosc: blosclz shuffle - 16MBtidb: oltp_update_index - 128blosc: blosclz bitshuffle - 256MBtidb: oltp_update_non_index - 128blosc: blosclz noshuffle - 128MBblosc: blosclz bitshuffle - 64MBblosc: blosclz bitshuffle - 128MBblosc: blosclz noshuffle - 256MBblosc: blosclz noshuffle - 16MBblosc: blosclz noshuffle - 32MBblosc: blosclz noshuffle - 64MBblosc: blosclz bitshuffle - 8MBblosc: blosclz bitshuffle - 32MBbuild-linux-kernel: allmodconfigblosc: blosclz noshuffle - 8MBblosc: blosclz bitshuffle - 16MBapache-iotdb: 800 - 100 - 800 - 400apache-iotdb: 800 - 100 - 800 - 400openvino: Handwritten English Recognition FP16-INT8 - CPUdacapobench: Apache Lucene Search Engineopenvino: Handwritten English Recognition FP16-INT8 - CPUdacapobench: Tradebeansbuild-linux-kernel: defconfigdacapobench: FOP Print Formatteropenfoam: drivaerFastback, Small Mesh Size - Execution Timeapache-iotdb: 800 - 100 - 500 - 400rocksdb: Read Rand Write Randdacapobench: H2 Database Enginerocksdb: Read While Writingqmcpack: LiH_ae_MSDblender: Fishy Cat - CPU-Onlyopenvino: Handwritten English Recognition FP16 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUopenvino: Handwritten English Recognition FP16 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUapache-iotdb: 800 - 100 - 500 - 400openvino: Vehicle Detection FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUdacapobench: GraphChionednn: Convolution Batch Shapes Auto - u8s8f32 - CPUbuild-gem5: Time To Compileonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Person Detection FP32 - CPUdacapobench: Apache Kafkaopenvino: Person Detection FP32 - CPUdacapobench: BioJava Biological Data Frameworkopenvino: Face Detection Retail FP16 - CPUdacapobench: Apache Lucene Search Indexopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUcloverleaf: clover_bmblender: Pabellon Barcelona - CPU-Onlyopenvino: Weld Porosity Detection FP16 - CPUospray-studio: 2 - 4K - 16 - Path Tracer - CPUquantlib: Multi-Threadedopenvino: Weld Porosity Detection FP16 - CPUdacapobench: Tradesoapopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Face Detection FP16 - CPUcpuminer-opt: scryptdacapobench: Zxing 1D/2D Barcode Image Processingdacapobench: Jythonopenvino: Road Segmentation ADAS FP16-INT8 - CPUdacapobench: Spring Bootopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Face Detection FP16 - CPUembree: Pathtracer - Crowndacapobench: Apache Xalan XSLTopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUospray-studio: 1 - 4K - 32 - Path Tracer - CPUrocksdb: Update Randcpuminer-opt: Quad SHA-256, Pyriteqmcpack: O_ae_pyscf_UHFopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUdacapobench: Batik SVG Toolkiteasywave: e2Asean Grid + BengkuluSept2007 Source - 1200openvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUospray-studio: 1 - 4K - 16 - Path Tracer - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUbuild-llvm: Ninjaeasywave: e2Asean Grid + BengkuluSept2007 Source - 240dacapobench: Eclipsepgbench: 100 - 1000 - Read Only - Average Latencybuild-godot: Time To Compileopenfoam: drivaerFastback, Medium Mesh Size - Execution Timeopenvino: Person Vehicle Bike Detection FP16 - CPUblender: Classroom - CPU-Onlyospray-studio: 1 - 4K - 1 - Path Tracer - CPUblender: BMW27 - CPU-Onlyonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: IP Shapes 3D - f32 - CPUospray-studio: 1 - 1080p - 16 - Path Tracer - CPUembree: Pathtracer ISPC - Asian Dragon Objopenvino: Person Vehicle Bike Detection FP16 - CPUospray-studio: 1 - 1080p - 32 - Path Tracer - CPUpgbench: 100 - 1000 - Read Onlyonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUcoremark: CoreMark Size 666 - Iterations Per Seconddacapobench: Apache Tomcatonednn: Recurrent Neural Network Training - u8s8f32 - CPUquantlib: Single-Threadedqmcpack: simple-H2Oospray-studio: 1 - 1080p - 1 - Path Tracer - CPUospray-studio: 3 - 4K - 32 - Path Tracer - CPUduckdb: TPC-H Parquetqmcpack: FeCO6_b3lyp_gmscpuminer-opt: Deepcoinospray-studio: 3 - 1080p - 16 - Path Tracer - CPUbuild-llvm: Unix Makefilesopenvino: Vehicle Detection FP16 - CPUdacapobench: Avrora AVR Simulation Frameworkospray-studio: 2 - 4K - 32 - Path Tracer - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUopenvino: Vehicle Detection FP16 - CPUcompress-7zip: Compression Ratingospray-studio: 3 - 4K - 1 - Path Tracer - CPUospray-studio: 2 - 1080p - 32 - Path Tracer - CPUospray-studio: 3 - 1080p - 1 - Path Tracer - CPUeasywave: e2Asean Grid + BengkuluSept2007 Source - 2400onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUembree: Pathtracer - Asian Dragoncpuminer-opt: Myriad-Groestlcpuminer-opt: Skeincoincpuminer-opt: Garlicoindacapobench: Apache Cassandraqmcpack: Li2_STO_aeospray-studio: 3 - 1080p - 32 - Path Tracer - CPUbuild-nodejs: Time To Compileopenvino: Face Detection FP16-INT8 - CPUospray-studio: 2 - 1080p - 16 - Path Tracer - CPUospray-studio: 2 - 1080p - 1 - Path Tracer - CPUcpuminer-opt: Ringcoinonednn: Deconvolution Batch shapes_1d - f32 - CPUopenvino: Face Detection FP16-INT8 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUembree: Pathtracer ISPC - Crownduckdb: IMDBcloverleaf: clover_bm16ospray-studio: 2 - 4K - 1 - Path Tracer - CPUcompress-7zip: Decompression Ratingonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUopenvkl: vklBenchmarkCPU ISPCcloverleaf: clover_bm64_shortonednn: Recurrent Neural Network Training - f32 - CPUtidb: oltp_point_select - 128onednn: Deconvolution Batch shapes_3d - f32 - CPUcpuminer-opt: LBC, LBRY Creditsrocksdb: Rand Readospray-studio: 3 - 4K - 16 - Path Tracer - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUblender: Barbershop - CPU-Onlyembree: Pathtracer - Asian Dragon Objopenvkl: vklBenchmarkCPU Scalarembree: Pathtracer ISPC - Asian Dragoncpuminer-opt: Triple SHA-256, Onecoincpuminer-opt: Magidacapobench: jMonkeyEnginecpuminer-opt: Blake-2 Soidn: RTLightmap.hdr.4096x4096 - CPU-Onlyoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyoidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlytidb: oltp_read_write - 128qmcpack: H4_aeonednn: IP Shapes 3D - bf16bf16bf16 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 1D - f32 - CPUdacapobench: H2O In-Memory Platform For Machine Learningdacapobench: PMD Source Code AnalyzerDynatron A54NH-D9 TR5-SP6 4UNoctua NH-U14S TR5-SP6Arctic Freezer 4U-M29.8334517.24158014157.3305412050.18925.614333.314908.16001.514860.5317695919.9575608347.211878.59041.55691.213207.212666.510874.015572.014307.0285.69013413.615140.7256.8011589986944.0015751456.81903440.38673953.722761179.2527321942619790673781.51028.441693.900.3642651.3480137.750.5356261031757669.730.493279.5134330.900905214.831557.8685.47153.605200208.1576793.96448611656.718043.8812.8767.8718.3033410215906.73492.7156680.6634.27802.5940565011165.38238727.41928.8471.453695657.65554.4459596484131153597202.70368.0186.83170139.46474181.75153.43208.363311194089.01167.8231.878122210.322130.798679.554399.8854.16165821.78551.3851.73846669974.04953231.741341731037530.7720382609983.9416161595807.5032626.430.47641969819175.405117.39214137979260.32924.416877603301.139791307.77361530197213580498111.275808.77879.55443001388680125305789113.9815960157.77967.0567934257956.528.60454475.520.34678273.8429123.373496.4016794294050.461978141757.36807.9211318341.3237341463364693916380949.30551.6836870.14203.0270.941759086.81942692731607.5469103640531.012.132.129265112.941.1563027.667133.898142.509294001182528.73843716.85959315142.2159913190.09737.515492.016126.06481.615912.8317566352.9585858865.112587.39624.46041.513911.113354.511486.916452.115024.5282.20813984.915886.2254.4911615655142.5116231504.57876240.38073353.825841179.1727147812596801704879.94327.821727.360.3731241.3491037.020.5240591031360729.530.483347.2834430.913218211.135548.0215.38150.815202211.9877813.90446411851.028169.0012.7767.0018.0532891218763.03539.2856250.6534.68813.3541165051179.51241227.09916.8072.282095556.97561.0859620480021154743202.11372.3085.84168239.03574980.37152.49209.643281794607.98166.1931.869122710.321129.864673.27739.8353.67165021.59552.1911.73842665573.90423247.591332231140150.7657332615136.6720681595812.2372606.830.42541669325176.494116.57213707941259.80024.376903601831.146321309.72363699196013543496110.934811.00879.70002998789180125135790113.3815896156.99267.0067644237949.678.62775475.510.34654174.1535123.236494.9216734299210.461672142057.18805.3981317351.3231541383365383171380819.29550.5326879.03202.6470.820859186.83432689701609.0969063640771.012.132.128810613.381.1201356.708844.152792.380053998181725.50636718.47754139157.6975513202.19755.015555.116080.96490.815989.6304496294.2559408907.912663.69638.06055.714003.813397.111496.216458.315080.9285.96314075.715881.8265.5711183102042.8116231493.83886440.56173754.261054179.6726818672550796199381.99327.741731.900.3684871.3264536.920.5238781017539149.590.483326.9533790.914553212.963547.6175.39151.705108210.7278193.90449711830.608174.4412.6566.7218.0333124219225.43545.1056950.6534.75808.8440565961182.29239927.03916.1472.450296856.88561.8859530485837155453202.36372.2285.85169839.04174918.38151.87210.503309494926.19167.4581.869123020.322130.967677.587919.7953.75164321.62550.8061.72350664873.42143258.821330631035850.7676552594063.0099161583807.1912610.030.54341669499176.645116.96214437924258.53724.456881603141.139051305.34363359196013498495111.278807.34380.01162989388910125135820113.9615910156.99567.0667604237933.768.62102475.350.34527674.1070123.318495.4316734309360.462504142257.16807.3981321321.3232041350365498944380089.29550.9416874.04202.9370.918259186.69362692801607.9469053641901.012.132.129259813.551.1324696.984664.552772.484574448182428.93891316.64560077146.0185212879.39538.915194.315745.36363.515734.5326916262.5599218753.212435.09485.65969.113832.313205.811363.316231.714887.8297.14513966.715713.4259.7411448216342.6616301499.22878041.56371852.735207184.3327564272603811456180.85427.841735.130.3675941.3586236.860.5272991010065119.550.483341.4734470.919030215.202548.9155.37152.145201210.1076783.89454411864.038186.8312.7666.9118.0133396219299.23547.4957120.6534.78801.4440965561168.48237827.34916.0672.044095757.15559.2458835482768153803204.53372.0285.90169039.19574882.42152.16210.083278095022.03167.4451.860123390.324131.077674.335869.8653.93164921.63555.6351.73218664273.71023237.651332330883410.7703182605687.4777611588806.1692607.030.31741669537175.900116.64215207941260.00924.296922599421.140131313.65363789196613515496110.619806.36079.79782984389143124605817113.5315876157.10067.3367634237970.538.64364473.370.34610374.0068123.732496.7416754302530.460872142057.19805.1271321611.3272241380365597754380709.31550.9256866.03202.8770.872759086.79022692901607.5169063641201.012.132.129292613.221.1165746.855264.502512.4889242831916OpenBenchmarking.org

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 TimeNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M71421283525.5128.7429.8328.941. (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

PostgreSQL

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average LatencyNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M510152025SE +/- 0.23, N = 3SE +/- 0.05, N = 3SE +/- 0.18, N = 3SE +/- 0.02, N = 318.4816.8617.2416.651. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read WriteNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M13K26K39K52K65KSE +/- 673.20, N = 3SE +/- 173.21, N = 3SE +/- 627.52, N = 3SE +/- 77.76, N = 3541395931558014600771. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenFOAM

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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh TimeNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M306090120150157.70142.22157.33146.021. (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

C-Blosc

C-Blosc (c-blosc2) simple, compressed, fast and persistent data store library for C that focuses on compression of binary data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz shuffle - Buffer Size: 64MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 16.58, N = 3SE +/- 7.60, N = 3SE +/- 19.22, N = 3SE +/- 13.42, N = 313202.113190.012050.112879.31. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz shuffle - Buffer Size: 128MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2K4K6K8K10KSE +/- 12.99, N = 3SE +/- 0.67, N = 3SE +/- 12.34, N = 3SE +/- 7.64, N = 39755.09737.58925.69538.91. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz shuffle - Buffer Size: 32MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 3.37, N = 3SE +/- 18.39, N = 3SE +/- 5.28, N = 3SE +/- 16.97, N = 315555.115492.014333.315194.31. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz shuffle - Buffer Size: 8MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 29.31, N = 3SE +/- 7.57, N = 3SE +/- 12.43, N = 3SE +/- 2.60, N = 316080.916126.014908.115745.31. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz shuffle - Buffer Size: 256MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M14002800420056007000SE +/- 2.27, N = 3SE +/- 2.55, N = 3SE +/- 29.07, N = 3SE +/- 10.74, N = 36490.86481.66001.56363.51. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz shuffle - Buffer Size: 16MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 6.00, N = 3SE +/- 16.90, N = 3SE +/- 5.40, N = 3SE +/- 3.44, N = 315989.615912.814860.515734.51. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

TiDB Community Server

This is a PingCAP TiDB Community Server benchmark facilitated using the sysbench OLTP database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterTiDB Community Server 7.3Test: oltp_update_index - Threads: 128Noctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M7K14K21K28K35KSE +/- 105.69, N = 3SE +/- 227.17, N = 3SE +/- 163.31, N = 3SE +/- 263.61, N = 330449317563176932691

C-Blosc

C-Blosc (c-blosc2) simple, compressed, fast and persistent data store library for C that focuses on compression of binary data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz bitshuffle - Buffer Size: 256MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M14002800420056007000SE +/- 14.42, N = 3SE +/- 22.27, N = 3SE +/- 22.32, N = 3SE +/- 11.51, N = 36294.26352.95919.96262.51. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

TiDB Community Server

This is a PingCAP TiDB Community Server benchmark facilitated using the sysbench OLTP database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterTiDB Community Server 7.3Test: oltp_update_non_index - Threads: 128Noctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M13K26K39K52K65KSE +/- 8.69, N = 2SE +/- 143.55, N = 3SE +/- 40.44, N = 3SE +/- 205.41, N = 355940585855756059921

C-Blosc

C-Blosc (c-blosc2) simple, compressed, fast and persistent data store library for C that focuses on compression of binary data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz noshuffle - Buffer Size: 128MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2K4K6K8K10KSE +/- 11.56, N = 3SE +/- 7.45, N = 3SE +/- 4.99, N = 3SE +/- 16.84, N = 38907.98865.18347.28753.21. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz bitshuffle - Buffer Size: 64MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 10.69, N = 3SE +/- 5.89, N = 3SE +/- 2.42, N = 3SE +/- 15.76, N = 312663.612587.311878.512435.01. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz bitshuffle - Buffer Size: 128MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2K4K6K8K10KSE +/- 12.64, N = 3SE +/- 11.45, N = 3SE +/- 8.06, N = 3SE +/- 6.55, N = 39638.09624.49041.59485.61. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz noshuffle - Buffer Size: 256MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M13002600390052006500SE +/- 2.72, N = 3SE +/- 3.64, N = 3SE +/- 2.90, N = 3SE +/- 8.27, N = 36055.76041.55691.25969.11. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz noshuffle - Buffer Size: 16MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 53.87, N = 3SE +/- 32.67, N = 3SE +/- 12.29, N = 3SE +/- 94.44, N = 314003.813911.113207.213832.31. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz noshuffle - Buffer Size: 32MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 28.63, N = 3SE +/- 15.17, N = 3SE +/- 36.10, N = 3SE +/- 46.74, N = 313397.113354.512666.513205.81. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz noshuffle - Buffer Size: 64MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2K4K6K8K10KSE +/- 19.66, N = 3SE +/- 27.62, N = 3SE +/- 22.73, N = 3SE +/- 14.16, N = 311496.211486.910874.011363.31. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz bitshuffle - Buffer Size: 8MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M4K8K12K16K20KSE +/- 16.10, N = 3SE +/- 16.14, N = 3SE +/- 12.66, N = 3SE +/- 30.15, N = 316458.316452.115572.016231.71. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz bitshuffle - Buffer Size: 32MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 11.58, N = 3SE +/- 27.46, N = 3SE +/- 11.14, N = 3SE +/- 21.86, N = 315080.915024.514307.014887.81. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

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: allmodconfigNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M60120180240300SE +/- 0.58, N = 3SE +/- 0.65, N = 3SE +/- 0.53, N = 3SE +/- 0.80, N = 3285.96282.21285.69297.15

C-Blosc

C-Blosc (c-blosc2) simple, compressed, fast and persistent data store library for C that focuses on compression of binary data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz noshuffle - Buffer Size: 8MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 16.71, N = 3SE +/- 26.20, N = 3SE +/- 16.66, N = 3SE +/- 53.64, N = 314075.713984.913413.613966.71. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz bitshuffle - Buffer Size: 16MBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 23.64, N = 3SE +/- 28.42, N = 3SE +/- 26.60, N = 3SE +/- 15.60, N = 315881.815886.215140.715713.41. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm

Apache IoTDB

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

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Noctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M60120180240300SE +/- 3.10, N = 3SE +/- 3.41, N = 3SE +/- 2.90, N = 3SE +/- 0.84, N = 3265.57254.49256.80259.74MAX: 27237.61MAX: 26906.76MAX: 26991.92MAX: 30064.62

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Noctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M20M40M60M80M100MSE +/- 1061890.13, N = 3SE +/- 896265.80, N = 3SE +/- 839333.42, N = 3SE +/- 525506.11, N = 3111831020116156551115899869114482163

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 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1020304050SE +/- 0.21, N = 3SE +/- 0.21, N = 3SE +/- 0.68, N = 12SE +/- 0.15, N = 342.8142.5144.0042.66MIN: 27.82 / MAX: 63.4MIN: 27.83 / MAX: 54.18MIN: 27.32 / MAX: 75.7MIN: 28.04 / MAX: 57.141. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search EngineNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M400800120016002000SE +/- 5.52, N = 5SE +/- 5.97, N = 5SE +/- 5.70, N = 5SE +/- 4.29, N = 51623162315751630

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 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M30060090012001500SE +/- 7.09, N = 3SE +/- 7.46, N = 3SE +/- 19.56, N = 12SE +/- 5.33, N = 31493.831504.571456.811499.221. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: TradebeansNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2K4K6K8K10KSE +/- 103.48, N = 3SE +/- 102.15, N = 4SE +/- 96.66, N = 15SE +/- 60.98, N = 38864876290348780

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: defconfigNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M918273645SE +/- 0.49, N = 4SE +/- 0.41, N = 5SE +/- 0.42, N = 5SE +/- 0.47, N = 440.5640.3840.3941.56

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: FOP Print FormatterNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M160320480640800SE +/- 2.62, N = 8SE +/- 1.77, N = 8SE +/- 3.59, N = 8SE +/- 10.01, N = 15737733739718

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 TimeNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M122436486054.2653.8353.7252.741. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

Apache IoTDB

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

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Noctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M4080120160200SE +/- 1.25, N = 3SE +/- 3.27, N = 3SE +/- 1.60, N = 3SE +/- 2.05, N = 3179.67179.17179.25184.33MAX: 26880.71MAX: 27068.91MAX: 27281.2MAX: 26905.03

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Read Random Write RandomNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M600K1200K1800K2400K3000KSE +/- 21486.01, N = 15SE +/- 29433.81, N = 5SE +/- 23452.89, N = 3SE +/- 5125.15, N = 326818672714781273219427564271. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: H2 Database EngineNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M6001200180024003000SE +/- 19.86, N = 3SE +/- 16.56, N = 3SE +/- 8.25, N = 3SE +/- 19.23, N = 32550259626192603

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Read While WritingNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2M4M6M8M10MSE +/- 49439.53, N = 3SE +/- 23377.20, N = 3SE +/- 49692.28, N = 3SE +/- 53569.19, N = 379619938017048790673781145611. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

QMCPACK

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

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.17.1Input: LiH_ae_MSDNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M20406080100SE +/- 1.09, N = 3SE +/- 0.13, N = 3SE +/- 0.44, N = 3SE +/- 0.37, N = 381.9979.9481.5180.851. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Fishy Cat - Compute: CPU-OnlyNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M714212835SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.16, N = 3SE +/- 0.13, N = 327.7427.8228.4427.84

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 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M400800120016002000SE +/- 5.31, N = 3SE +/- 2.37, N = 3SE +/- 2.25, N = 3SE +/- 3.21, N = 31731.901727.361693.901735.131. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.0840.1680.2520.3360.42SE +/- 0.005219, N = 3SE +/- 0.002099, N = 3SE +/- 0.002898, N = 3SE +/- 0.002241, N = 30.3684870.3731240.3642650.367594MIN: 0.33MIN: 0.33MIN: 0.33MIN: 0.331. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.30570.61140.91711.22281.5285SE +/- 0.00909, N = 3SE +/- 0.00892, N = 3SE +/- 0.00861, N = 3SE +/- 0.00982, N = 151.326451.349101.348011.35862MIN: 1.24MIN: 1.25MIN: 1.25MIN: 1.251. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M918273645SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 336.9237.0237.7536.86MIN: 22.21 / MAX: 59.67MIN: 22.21 / MAX: 59.58MIN: 24.92 / MAX: 64.27MIN: 22.22 / MAX: 63.041. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.12050.2410.36150.4820.6025SE +/- 0.000722, N = 5SE +/- 0.001085, N = 5SE +/- 0.002350, N = 5SE +/- 0.000504, N = 50.5238780.5240590.5356260.527299MIN: 0.46MIN: 0.46MIN: 0.47MIN: 0.471. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Apache IoTDB

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

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Noctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M20M40M60M80M100MSE +/- 600215.19, N = 3SE +/- 936061.82, N = 3SE +/- 673354.88, N = 3SE +/- 459029.65, N = 3101753914103136072103175766101006511

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 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3691215SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 39.599.539.739.55MIN: 4.52 / MAX: 27.12MIN: 4.8 / MAX: 33.9MIN: 4.59 / MAX: 26.79MIN: 4.45 / MAX: 32.581. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.11030.22060.33090.44120.5515SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.480.480.490.48MIN: 0.26 / MAX: 19.92MIN: 0.26 / MAX: 32.61MIN: 0.26 / MAX: 25.77MIN: 0.26 / MAX: 19.921. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M7001400210028003500SE +/- 24.03, N = 3SE +/- 1.55, N = 3SE +/- 12.47, N = 3SE +/- 7.97, N = 33326.953347.283279.513341.471. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: GraphChiNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M7001400210028003500SE +/- 24.53, N = 15SE +/- 15.95, N = 3SE +/- 28.51, N = 15SE +/- 30.87, N = 73379344334333447

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 3.3Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.20680.41360.62040.82721.034SE +/- 0.001480, N = 7SE +/- 0.001721, N = 7SE +/- 0.002277, N = 6SE +/- 0.005549, N = 70.9145530.9132180.9009050.919030MIN: 0.84MIN: 0.84MIN: 0.84MIN: 0.841. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Timed Gem5 Compilation

This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To CompileNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M50100150200250SE +/- 2.46, N = 3SE +/- 2.32, N = 5SE +/- 0.72, N = 3SE +/- 2.64, N = 3212.96211.14214.83215.20

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 3.3Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M120240360480600SE +/- 2.44, N = 3SE +/- 1.42, N = 3SE +/- 3.29, N = 3SE +/- 2.13, N = 3547.62548.02557.87548.92MIN: 538.81MIN: 539.44MIN: 545.56MIN: 537.81. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1.23082.46163.69244.92326.154SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 35.395.385.475.37MIN: 3.19 / MAX: 19.08MIN: 3.18 / MAX: 16.36MIN: 3.23 / MAX: 28.68MIN: 3.21 / MAX: 18.591. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M306090120150SE +/- 0.58, N = 3SE +/- 0.94, N = 3SE +/- 0.33, N = 3SE +/- 0.32, N = 3151.70150.81153.60152.14MIN: 55.39 / MAX: 212.78MIN: 53.46 / MAX: 212.6MIN: 63.54 / MAX: 214MIN: 56.72 / MAX: 212.081. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache KafkaNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M11002200330044005500SE +/- 1.33, N = 3SE +/- 2.00, N = 3SE +/- 4.63, N = 3SE +/- 1.00, N = 35108520252005201

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 2023.2.devModel: Person Detection FP32 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M50100150200250SE +/- 0.79, N = 3SE +/- 1.36, N = 3SE +/- 0.42, N = 3SE +/- 0.45, N = 3210.72211.98208.15210.101. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: BioJava Biological Data FrameworkNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2K4K6K8K10KSE +/- 80.64, N = 3SE +/- 81.45, N = 3SE +/- 10.82, N = 3SE +/- 44.09, N = 37819778176797678

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 2023.2.devModel: Face Detection Retail FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.8911.7822.6733.5644.455SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 33.903.903.963.89MIN: 2.2 / MAX: 22.15MIN: 2.2 / MAX: 29.97MIN: 2.22 / MAX: 28.64MIN: 2.26 / MAX: 22.381. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search IndexNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M10002000300040005000SE +/- 9.96, N = 3SE +/- 9.82, N = 3SE +/- 3.51, N = 3SE +/- 55.19, N = 44497446444864544

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 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 9.54, N = 3SE +/- 13.35, N = 3SE +/- 11.83, N = 3SE +/- 24.14, N = 311830.6011851.0211656.7111864.031. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2K4K6K8K10KSE +/- 10.57, N = 3SE +/- 12.62, N = 3SE +/- 9.37, N = 3SE +/- 3.94, N = 38174.448169.008043.888186.831. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

CloverLeaf

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

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bmNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3691215SE +/- 0.07, N = 4SE +/- 0.08, N = 4SE +/- 0.12, N = 4SE +/- 0.02, N = 412.6512.7712.8712.761. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Pabellon Barcelona - Compute: CPU-OnlyNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1530456075SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 366.7267.0067.8766.91

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 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 318.0318.0518.3018.01MIN: 9.7 / MAX: 29.11MIN: 9.42 / MAX: 37.14MIN: 9.51 / MAX: 69.8MIN: 9.44 / MAX: 29.651. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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 0.13Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M7K14K21K28K35KSE +/- 289.97, N = 3SE +/- 287.98, N = 3SE +/- 146.71, N = 3SE +/- 77.54, N = 333124328913341033396

QuantLib

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

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M50K100K150K200K250KSE +/- 188.26, N = 3SE +/- 116.53, N = 3SE +/- 472.20, N = 3SE +/- 203.49, N = 3219225.4218763.0215906.7219299.21. (CXX) g++ options: -O3 -march=native -fPIE -pie

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 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M8001600240032004000SE +/- 1.00, N = 3SE +/- 1.77, N = 3SE +/- 1.78, N = 3SE +/- 0.38, N = 33545.103539.283492.713547.491. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: TradesoapNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M12002400360048006000SE +/- 41.30, N = 11SE +/- 43.72, N = 15SE +/- 53.41, N = 3SE +/- 37.03, N = 145695562556685712

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 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.14850.2970.44550.5940.7425SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.650.650.660.65MIN: 0.34 / MAX: 20.93MIN: 0.34 / MAX: 20.26MIN: 0.34 / MAX: 23.67MIN: 0.34 / MAX: 20.081. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M816243240SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 334.7534.6834.2734.781. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Cpuminer-Opt

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

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: scryptNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2004006008001000SE +/- 3.96, N = 3SE +/- 0.27, N = 3SE +/- 0.83, N = 3SE +/- 0.50, N = 3808.84813.35802.59801.441. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Zxing 1D/2D Barcode Image ProcessingNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M90180270360450SE +/- 5.23, N = 15SE +/- 5.03, N = 15SE +/- 4.30, N = 15SE +/- 4.66, N = 15405411405409

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: JythonNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M14002800420056007000SE +/- 17.03, N = 3SE +/- 14.26, N = 3SE +/- 82.91, N = 3SE +/- 26.56, N = 36596650565016556

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 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M30060090012001500SE +/- 3.64, N = 3SE +/- 6.52, N = 3SE +/- 3.32, N = 3SE +/- 2.59, N = 31182.291179.511165.381168.481. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Spring BootNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M5001000150020002500SE +/- 15.68, N = 15SE +/- 11.80, N = 4SE +/- 13.69, N = 4SE +/- 21.16, N = 72399241223872378

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 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M612182430SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 327.0327.0927.4127.34MIN: 13.91 / MAX: 47.64MIN: 18.57 / MAX: 45.49MIN: 13.94 / MAX: 51.14MIN: 13.93 / MAX: 47.981. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2004006008001000SE +/- 1.04, N = 3SE +/- 0.28, N = 3SE +/- 0.57, N = 3SE +/- 0.33, N = 3916.14916.80928.84916.06MIN: 880.57 / MAX: 968.04MIN: 865.44 / MAX: 971.95MIN: 885.23 / MAX: 978.93MIN: 467.88 / MAX: 975.681. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer - Model: CrownNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1632486480SE +/- 0.13, N = 5SE +/- 0.10, N = 5SE +/- 0.11, N = 5SE +/- 0.05, N = 572.4572.2871.4572.04MIN: 71.25 / MAX: 74.25MIN: 71.09 / MAX: 74.2MIN: 70.33 / MAX: 73.11MIN: 70.98 / MAX: 74.08

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Xalan XSLTNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2004006008001000SE +/- 6.26, N = 8SE +/- 5.03, N = 8SE +/- 6.67, N = 8SE +/- 7.37, N = 8968955956957

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 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1326395265SE +/- 0.33, N = 3SE +/- 0.53, N = 3SE +/- 0.61, N = 3SE +/- 0.37, N = 356.8856.9757.6557.15MIN: 17.04 / MAX: 77.08MIN: 18.25 / MAX: 87.32MIN: 17.43 / MAX: 102.46MIN: 15.94 / MAX: 83.031. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M120240360480600SE +/- 3.31, N = 3SE +/- 5.22, N = 3SE +/- 5.87, N = 3SE +/- 3.69, N = 3561.88561.08554.44559.241. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M13K26K39K52K65KSE +/- 75.76, N = 3SE +/- 118.55, N = 3SE +/- 63.86, N = 3SE +/- 58.07, N = 359530596205959658835

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Update RandomNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M100K200K300K400K500KSE +/- 375.32, N = 3SE +/- 102.40, N = 3SE +/- 462.43, N = 3SE +/- 611.10, N = 34858374800214841314827681. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Cpuminer-Opt

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

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: Quad SHA-256, PyriteNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M30K60K90K120K150KSE +/- 1883.77, N = 3SE +/- 1498.36, N = 3SE +/- 55.48, N = 3SE +/- 188.36, N = 31554531547431535971538031. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

QMCPACK

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

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.17.1Input: O_ae_pyscf_UHFNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M4080120160200SE +/- 0.74, N = 3SE +/- 1.04, N = 3SE +/- 0.22, N = 3SE +/- 1.06, N = 3202.36202.11202.70204.531. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M80160240320400SE +/- 0.78, N = 3SE +/- 0.49, N = 3SE +/- 0.50, N = 3SE +/- 0.24, N = 3372.22372.30368.01372.021. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M20406080100SE +/- 0.18, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 385.8585.8486.8385.90MIN: 41.81 / MAX: 127.31MIN: 42.72 / MAX: 128.74MIN: 46.22 / MAX: 127.41MIN: 43.82 / MAX: 127.731. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Batik SVG ToolkitNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M400800120016002000SE +/- 13.40, N = 6SE +/- 3.87, N = 6SE +/- 12.32, N = 6SE +/- 8.49, N = 61698168217011690

easyWave

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

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200Noctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M918273645SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 339.0439.0439.4639.201. (CXX) g++ options: -O3 -fopenmp

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M16K32K48K64K80KSE +/- 97.06, N = 3SE +/- 95.58, N = 3SE +/- 106.60, N = 3SE +/- 153.60, N = 374918.3874980.3774181.7574882.421. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M306090120150SE +/- 0.20, N = 3SE +/- 0.57, N = 3SE +/- 0.23, N = 3SE +/- 0.26, N = 3151.87152.49153.43152.16MIN: 71.37 / MAX: 219.37MIN: 56.06 / MAX: 213.04MIN: 54.07 / MAX: 216.13MIN: 57.94 / MAX: 212.811. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M50100150200250SE +/- 0.27, N = 3SE +/- 0.78, N = 3SE +/- 0.33, N = 3SE +/- 0.38, N = 3210.50209.64208.36210.081. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M7K14K21K28K35KSE +/- 50.53, N = 3SE +/- 249.34, N = 3SE +/- 85.70, N = 3SE +/- 137.99, N = 333094328173311132780

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 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M20K40K60K80K100KSE +/- 82.69, N = 3SE +/- 253.03, N = 3SE +/- 123.77, N = 3SE +/- 106.13, N = 394926.1994607.9894089.0195022.031. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M4080120160200SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3167.46166.19167.82167.45

easyWave

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

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240Noctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.42260.84521.26781.69042.113SE +/- 0.005, N = 9SE +/- 0.003, N = 9SE +/- 0.011, N = 9SE +/- 0.003, N = 91.8691.8691.8781.8601. (CXX) g++ options: -O3 -fopenmp

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: EclipseNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 123.96, N = 3SE +/- 75.24, N = 3SE +/- 134.12, N = 3SE +/- 43.09, N = 312302122711222112339

PostgreSQL

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencyNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.07290.14580.21870.29160.3645SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 30.3220.3210.3220.3241. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Timed Godot Game Engine Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To CompileNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M306090120150SE +/- 0.26, N = 3SE +/- 0.51, N = 3SE +/- 0.14, N = 3SE +/- 0.35, N = 3130.97129.86130.80131.08

OpenFOAM

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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution TimeNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M150300450600750677.59673.28679.55674.341. (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

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 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3691215SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 39.799.839.889.86MIN: 5.6 / MAX: 23.25MIN: 5.83 / MAX: 27.83MIN: 5.9 / MAX: 36.14MIN: 5.77 / MAX: 23.721. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Classroom - Compute: CPU-OnlyNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1224364860SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.11, N = 353.7553.6754.1653.93

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 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M400800120016002000SE +/- 1.73, N = 3SE +/- 2.19, N = 3SE +/- 2.73, N = 3SE +/- 2.40, N = 31643165016581649

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: BMW27 - Compute: CPU-OnlyNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 321.6221.5921.7821.63

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 3.3Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M120240360480600SE +/- 1.16, N = 3SE +/- 3.84, N = 3SE +/- 0.86, N = 3SE +/- 3.44, N = 3550.81552.19551.39555.64MIN: 543.57MIN: 541.87MIN: 543.64MIN: 546.051. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.39120.78241.17361.56481.956SE +/- 0.00654, N = 5SE +/- 0.00436, N = 5SE +/- 0.00533, N = 5SE +/- 0.00309, N = 51.723501.738421.738461.73218MIN: 1.57MIN: 1.59MIN: 1.58MIN: 1.581. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OSPRay Studio

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

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M14002800420056007000SE +/- 10.90, N = 3SE +/- 0.58, N = 3SE +/- 6.66, N = 3SE +/- 14.68, N = 36648665566996642

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon ObjNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1632486480SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.20, N = 373.4273.9074.0573.71MIN: 72.69 / MAX: 74.45MIN: 73.22 / MAX: 74.9MIN: 73.28 / MAX: 75.58MIN: 72.66 / MAX: 75.18

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M7001400210028003500SE +/- 16.81, N = 3SE +/- 3.44, N = 3SE +/- 3.50, N = 3SE +/- 1.07, N = 33258.823247.593231.743237.651. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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 0.13Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 15.06, N = 3SE +/- 16.33, N = 3SE +/- 10.69, N = 3SE +/- 16.34, N = 313306133221341713323

PostgreSQL

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlyNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M700K1400K2100K2800K3500KSE +/- 22492.45, N = 3SE +/- 20993.48, N = 3SE +/- 21879.14, N = 3SE +/- 9542.00, N = 331035853114015310375330883411. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

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 3.3Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.17370.34740.52110.69480.8685SE +/- 0.001168, N = 9SE +/- 0.000942, N = 9SE +/- 0.001650, N = 9SE +/- 0.002094, N = 90.7676550.7657330.7720380.770318MIN: 0.76MIN: 0.76MIN: 0.76MIN: 0.761. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Coremark

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

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M600K1200K1800K2400K3000KSE +/- 26379.27, N = 5SE +/- 1080.25, N = 3SE +/- 7834.55, N = 3SE +/- 16956.27, N = 32594063.012615136.672609983.942605687.481. (CC) gcc options: -O2 -lrt" -lrt

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache TomcatNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M30060090012001500SE +/- 12.23, N = 5SE +/- 5.49, N = 5SE +/- 10.85, N = 5SE +/- 12.86, N = 51583159515951588

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 3.3Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2004006008001000SE +/- 2.64, N = 3SE +/- 0.59, N = 3SE +/- 2.26, N = 3SE +/- 0.59, N = 3807.19812.24807.50806.17MIN: 797.49MIN: 804.37MIN: 797.78MIN: 799.731. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

QuantLib

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

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Single-ThreadedNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M6001200180024003000SE +/- 13.41, N = 3SE +/- 15.21, N = 3SE +/- 1.50, N = 3SE +/- 15.38, N = 32610.02606.82626.42607.01. (CXX) g++ options: -O3 -march=native -fPIE -pie

QMCPACK

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

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.17.1Input: simple-H2ONoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M714212835SE +/- 0.12, N = 3SE +/- 0.14, N = 3SE +/- 0.18, N = 3SE +/- 0.12, N = 330.5430.4330.4830.321. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl

OSPRay Studio

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

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M90180270360450SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.58, N = 3416416419416

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M15K30K45K60K75KSE +/- 9.24, N = 3SE +/- 84.69, N = 3SE +/- 74.81, N = 3SE +/- 92.61, N = 369499693256981969537

DuckDB

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

OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: TPC-H ParquetNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M4080120160200SE +/- 0.23, N = 3SE +/- 0.38, N = 3SE +/- 0.24, N = 3SE +/- 0.11, N = 3176.65176.49175.41175.901. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl

QMCPACK

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

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.17.1Input: FeCO6_b3lyp_gmsNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M306090120150SE +/- 0.27, N = 3SE +/- 0.32, N = 3SE +/- 0.49, N = 3SE +/- 0.30, N = 3116.96116.57117.39116.641. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl

Cpuminer-Opt

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

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: DeepcoinNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M5K10K15K20K25KSE +/- 48.42, N = 3SE +/- 5.77, N = 3SE +/- 35.28, N = 3SE +/- 81.85, N = 3214432137021413215201. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

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 0.13Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2K4K6K8K10KSE +/- 12.99, N = 3SE +/- 8.39, N = 3SE +/- 10.20, N = 3SE +/- 12.49, N = 37924794179797941

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix MakefilesNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M60120180240300SE +/- 1.07, N = 3SE +/- 0.42, N = 3SE +/- 0.10, N = 3SE +/- 0.90, N = 3258.54259.80260.33260.01

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 2023.2.devModel: Vehicle Detection FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M612182430SE +/- 0.07, N = 3SE +/- 0.19, N = 3SE +/- 0.28, N = 3SE +/- 0.05, N = 324.4524.3724.4124.29MIN: 8.96 / MAX: 51.37MIN: 9.52 / MAX: 57.66MIN: 9.88 / MAX: 54.94MIN: 8.85 / MAX: 49.531. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Avrora AVR Simulation FrameworkNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M15003000450060007500SE +/- 10.41, N = 3SE +/- 10.15, N = 3SE +/- 9.85, N = 3SE +/- 11.26, N = 36881690368776922

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 0.13Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M13K26K39K52K65KSE +/- 105.01, N = 3SE +/- 63.01, N = 3SE +/- 196.68, N = 3SE +/- 243.95, N = 360314601836033059942

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 3.3Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.25790.51580.77371.03161.2895SE +/- 0.00083, N = 7SE +/- 0.00376, N = 7SE +/- 0.00377, N = 6SE +/- 0.00256, N = 71.139051.146321.139791.14013MIN: 1.06MIN: 1.06MIN: 1.06MIN: 1.061. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M30060090012001500SE +/- 3.73, N = 3SE +/- 10.16, N = 3SE +/- 15.06, N = 3SE +/- 2.82, N = 31305.341309.721307.771313.651. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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 RatingNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M80K160K240K320K400KSE +/- 157.10, N = 3SE +/- 120.89, N = 3SE +/- 224.34, N = 3SE +/- 474.93, N = 33633593636993615303637891. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

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 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M400800120016002000SE +/- 0.58, N = 3SE +/- 1.76, N = 3SE +/- 2.08, N = 3SE +/- 0.88, N = 31960196019721966

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 7.84, N = 3SE +/- 10.59, N = 3SE +/- 1.76, N = 3SE +/- 21.61, N = 313498135431358013515

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M110220330440550SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3495496498496

easyWave

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

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400Noctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M20406080100SE +/- 0.07, N = 3SE +/- 0.22, N = 3SE +/- 0.24, N = 3SE +/- 0.36, N = 3111.28110.93111.28110.621. (CXX) g++ options: -O3 -fopenmp

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 3.3Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2004006008001000SE +/- 2.76, N = 3SE +/- 2.70, N = 3SE +/- 0.30, N = 3SE +/- 2.10, N = 3807.34811.01808.78806.36MIN: 795.77MIN: 800.64MIN: 800.97MIN: 7981. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer - Model: Asian DragonNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M20406080100SE +/- 0.04, N = 5SE +/- 0.03, N = 5SE +/- 0.10, N = 5SE +/- 0.08, N = 580.0179.7079.5579.80MIN: 79.34 / MAX: 80.87MIN: 79.03 / MAX: 80.61MIN: 78.61 / MAX: 80.51MIN: 79.08 / MAX: 80.84

Cpuminer-Opt

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

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: Myriad-GroestlNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M6K12K18K24K30KSE +/- 14.53, N = 3SE +/- 76.67, N = 3SE +/- 58.97, N = 3SE +/- 13.33, N = 3298932998730013298431. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: SkeincoinNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M20K40K60K80K100KSE +/- 151.00, N = 3SE +/- 370.72, N = 3SE +/- 20.82, N = 3SE +/- 396.75, N = 3889108918088680891431. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: GarlicoinNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 27.28, N = 3SE +/- 31.80, N = 3SE +/- 20.82, N = 3SE +/- 20.82, N = 3125131251312530124601. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache CassandraNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M12002400360048006000SE +/- 32.51, N = 3SE +/- 34.53, N = 3SE +/- 3.48, N = 3SE +/- 17.46, N = 35820579057895817

QMCPACK

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

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.17.1Input: Li2_STO_aeNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M306090120150SE +/- 0.27, N = 3SE +/- 0.18, N = 3SE +/- 0.61, N = 3SE +/- 0.14, N = 3113.96113.38113.98113.531. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl

OSPRay Studio

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

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3K6K9K12K15KSE +/- 29.82, N = 3SE +/- 29.28, N = 3SE +/- 18.50, N = 3SE +/- 14.24, N = 315910158961596015876

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 19.8.1Time To CompileNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M306090120150SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3157.00156.99157.78157.10

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 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1530456075SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.09, N = 367.0667.0067.0567.331. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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 0.13Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M15003000450060007500SE +/- 9.07, N = 3SE +/- 8.37, N = 3SE +/- 3.06, N = 3SE +/- 4.10, N = 36760676467936763

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M90180270360450SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3423423425423

Cpuminer-Opt

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

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: RingcoinNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2K4K6K8K10KSE +/- 58.30, N = 11SE +/- 1.86, N = 3SE +/- 1.70, N = 3SE +/- 10.81, N = 37933.767949.677956.527970.531. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

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 3.3Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M246810SE +/- 0.00704, N = 3SE +/- 0.03103, N = 3SE +/- 0.01034, N = 3SE +/- 0.01368, N = 38.621028.627758.604548.64364MIN: 8.01MIN: 8MIN: 7.95MIN: 7.951. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M100200300400500SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.70, N = 3SE +/- 0.53, N = 3475.35475.51475.52473.37MIN: 436.16 / MAX: 492.52MIN: 246.55 / MAX: 497.4MIN: 425.59 / MAX: 494.41MIN: 246.52 / MAX: 493.871. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.0780.1560.2340.3120.39SE +/- 0.000642, N = 9SE +/- 0.000430, N = 9SE +/- 0.000899, N = 9SE +/- 0.000682, N = 90.3452760.3465410.3467820.346103MIN: 0.34MIN: 0.34MIN: 0.34MIN: 0.341. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: CrownNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1632486480SE +/- 0.16, N = 5SE +/- 0.14, N = 5SE +/- 0.07, N = 5SE +/- 0.13, N = 574.1174.1573.8474.01MIN: 72.48 / MAX: 76.13MIN: 72.69 / MAX: 75.98MIN: 72.65 / MAX: 75.71MIN: 72.46 / MAX: 75.98

DuckDB

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

OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: IMDBNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M306090120150SE +/- 0.16, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.23, N = 3123.32123.24123.37123.731. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl

CloverLeaf

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

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bm16Noctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M110220330440550SE +/- 0.87, N = 3SE +/- 0.38, N = 3SE +/- 0.63, N = 3SE +/- 0.78, N = 3495.43494.92496.40496.741. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

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 0.13Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M400800120016002000SE +/- 0.88, N = 3SE +/- 1.86, N = 3SE +/- 3.06, N = 3SE +/- 2.08, N = 31673167316791675

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 RatingNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M90K180K270K360K450KSE +/- 126.01, N = 3SE +/- 352.41, N = 3SE +/- 497.61, N = 3SE +/- 418.61, N = 34309364299214294054302531. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

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 3.3Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.10410.20820.31230.41640.5205SE +/- 0.000671, N = 7SE +/- 0.001085, N = 7SE +/- 0.001306, N = 7SE +/- 0.001388, N = 70.4625040.4616720.4619780.460872MIN: 0.44MIN: 0.44MIN: 0.44MIN: 0.441. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVKL

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

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 2.0.0Benchmark: vklBenchmarkCPU ISPCNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M30060090012001500SE +/- 0.67, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 31422142014171420MIN: 114 / MAX: 17494MIN: 113 / MAX: 17461MIN: 114 / MAX: 17373MIN: 114 / MAX: 17475

CloverLeaf

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

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bm64_shortNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1326395265SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 357.1657.1857.3657.191. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

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 3.3Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M2004006008001000SE +/- 1.70, N = 3SE +/- 2.78, N = 3SE +/- 1.62, N = 3SE +/- 0.70, N = 3807.40805.40807.92805.13MIN: 799.36MIN: 796.45MIN: 798.54MIN: 797.921. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

TiDB Community Server

This is a PingCAP TiDB Community Server benchmark facilitated using the sysbench OLTP database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterTiDB Community Server 7.3Test: oltp_point_select - Threads: 128Noctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M30K60K90K120K150KSE +/- 388.36, N = 3SE +/- 46.36, N = 2SE +/- 187.31, N = 3SE +/- 144.76, N = 3132132131735131834132161

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 3.3Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.29860.59720.89581.19441.493SE +/- 0.00098, N = 9SE +/- 0.00099, N = 9SE +/- 0.00125, N = 9SE +/- 0.00086, N = 91.323201.323151.323731.32722MIN: 1.31MIN: 1.31MIN: 1.31MIN: 1.321. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Cpuminer-Opt

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

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: LBC, LBRY CreditsNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M9K18K27K36K45KSE +/- 5.77, N = 3SE +/- 17.64, N = 3SE +/- 6.67, N = 3SE +/- 20.00, N = 3413504138341463413801. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Random ReadNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M80M160M240M320M400MSE +/- 78230.55, N = 3SE +/- 286715.49, N = 3SE +/- 805455.00, N = 3SE +/- 389026.77, N = 33654989443653831713646939163655977541. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M8K16K24K32K40KSE +/- 84.89, N = 3SE +/- 23.25, N = 3SE +/- 68.64, N = 3SE +/- 103.71, N = 338008380813809438070

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 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3691215SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 39.299.299.309.31MIN: 5.01 / MAX: 25.36MIN: 4.97 / MAX: 20.13MIN: 4.94 / MAX: 41.53MIN: 4.93 / MAX: 26.591. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M120240360480600SE +/- 3.04, N = 3SE +/- 3.03, N = 3SE +/- 2.21, N = 3SE +/- 2.01, N = 3550.94550.53551.68550.93MIN: 540.62MIN: 539.43MIN: 542.54MIN: 539.781. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M15003000450060007500SE +/- 12.85, N = 3SE +/- 12.82, N = 3SE +/- 2.08, N = 3SE +/- 2.06, N = 36874.046879.036870.146866.031. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Barbershop - Compute: CPU-OnlyNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M4080120160200SE +/- 0.24, N = 3SE +/- 0.16, N = 3SE +/- 0.15, N = 3SE +/- 0.27, N = 3202.93202.64203.02202.87

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer - Model: Asian Dragon ObjNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1632486480SE +/- 0.41, N = 3SE +/- 0.20, N = 3SE +/- 0.07, N = 3SE +/- 0.13, N = 370.9270.8270.9470.87MIN: 69.53 / MAX: 72.34MIN: 70.01 / MAX: 71.92MIN: 70.26 / MAX: 71.81MIN: 70.11 / MAX: 71.95

OpenVKL

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

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 2.0.0Benchmark: vklBenchmarkCPU ScalarNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M130260390520650SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3591591590590MIN: 42 / MAX: 10115MIN: 42 / MAX: 10116MIN: 42 / MAX: 10106MIN: 42 / MAX: 10108

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian DragonNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M20406080100SE +/- 0.13, N = 5SE +/- 0.05, N = 5SE +/- 0.11, N = 5SE +/- 0.10, N = 586.6986.8386.8286.79MIN: 85.69 / MAX: 88.22MIN: 86.04 / MAX: 88.04MIN: 85.87 / MAX: 88.44MIN: 85.99 / MAX: 88.21

Cpuminer-Opt

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

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: Triple SHA-256, OnecoinNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M60K120K180K240K300KSE +/- 126.62, N = 3SE +/- 90.74, N = 3SE +/- 239.75, N = 3SE +/- 181.48, N = 32692802689702692732692901. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: MagiNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M30060090012001500SE +/- 1.67, N = 3SE +/- 3.52, N = 3SE +/- 0.71, N = 3SE +/- 1.08, N = 31607.941609.091607.541607.511. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: jMonkeyEngineNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M15003000450060007500SE +/- 1.76, N = 3SE +/- 3.00, N = 3SE +/- 1.67, N = 3SE +/- 1.20, N = 36905690669106906

Cpuminer-Opt

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

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: Blake-2 SNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M80K160K240K320K400KSE +/- 140.00, N = 3SE +/- 3.33, N = 3SE +/- 23.33, N = 3SE +/- 5.77, N = 33641903640773640533641201. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RTLightmap.hdr.4096x4096 - Device: CPU-OnlyNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.22730.45460.68190.90921.1365SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.011.011.011.01

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.47930.95861.43791.91722.3965SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 42.132.132.132.13

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-OnlyNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.4770.9541.4311.9082.385SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 42.122.122.122.12

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M20406080100Min: 25.5 / Avg: 41.58 / Max: 63.13Min: 25 / Avg: 42.69 / Max: 64.75Min: 30 / Avg: 63.81 / Max: 87.88Min: 25.75 / Avg: 42.06 / Max: 60.38

TiDB Community Server

OpenBenchmarking.orgCelsius, Fewer Is BetterTiDB Community Server 7.3CPU Temperature MonitorNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1530456075Min: 30.38 / Avg: 35.79 / Max: 45.13Min: 31.88 / Avg: 37.68 / Max: 48.75Min: 43.88 / Avg: 58.81 / Max: 79.63Min: 34.38 / Avg: 39.37 / Max: 48.63

OpenBenchmarking.orgQueries Per Second, More Is BetterTiDB Community Server 7.3Test: oltp_read_write - Threads: 128Noctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M20K40K60K80K100KSE +/- 80.07, N = 3SE +/- 4551.87, N = 9SE +/- 88.74, N = 3SE +/- 78.76, N = 392598881069265192926

QMCPACK

MinAvgMaxNoctua NH-U14S TR5-SP637.147.250.4NH-D9 TR5-SP6 4U39.950.453.3Dynatron A5461.174.380.9Arctic Freezer 4U-M39.448.350.3OpenBenchmarking.orgCelsius, Fewer Is BetterQMCPACK 3.17.1CPU Temperature Monitor20406080100

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.17.1Input: H4_aeNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M3691215SE +/- 0.15, N = 4SE +/- 0.25, N = 12SE +/- 0.14, N = 4SE +/- 0.14, N = 1513.5513.3812.9413.221. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl

oneDNN

MinAvgMaxNoctua NH-U14S TR5-SP628.633.536.1NH-D9 TR5-SP6 4U29.434.436.9Dynatron A5441.947.351.1Arctic Freezer 4U-M31.135.137.5OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 3.3CPU Temperature Monitor1530456075

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.26020.52040.78061.04081.301SE +/- 0.022930, N = 15SE +/- 0.026240, N = 15SE +/- 0.020821, N = 12SE +/- 0.022445, N = 151.1324691.1201351.1563021.116574MIN: 0.93MIN: 0.92MIN: 0.92MIN: 0.921. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

MinAvgMaxNoctua NH-U14S TR5-SP628.431.633.0NH-D9 TR5-SP6 4U29.032.333.8Dynatron A5443.145.947.9Arctic Freezer 4U-M31.033.734.8OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 3.3CPU Temperature Monitor1428425670

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M246810SE +/- 0.50620, N = 15SE +/- 0.56116, N = 15SE +/- 0.51948, N = 15SE +/- 0.54894, N = 156.984666.708847.667136.85526MIN: 2.06MIN: 2.2MIN: 1.99MIN: 2.11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

MinAvgMaxNoctua NH-U14S TR5-SP629.531.933.9NH-D9 TR5-SP6 4U30.632.834.6Dynatron A5445.947.551.3Arctic Freezer 4U-M32.033.834.8OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 3.3CPU Temperature Monitor1530456075

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M1.02442.04883.07324.09765.122SE +/- 0.21282, N = 15SE +/- 0.29938, N = 15SE +/- 0.31635, N = 12SE +/- 0.18064, N = 154.552774.152793.898144.50251MIN: 1.47MIN: 1.31MIN: 1.18MIN: 1.731. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

MinAvgMaxNoctua NH-U14S TR5-SP630.636.240.8NH-D9 TR5-SP6 4U31.337.542.3Dynatron A5445.653.359.5Arctic Freezer 4U-M33.137.942.6OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 3.3CPU Temperature Monitor1632486480

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M0.56461.12921.69382.25842.823SE +/- 0.06453, N = 12SE +/- 0.07713, N = 15SE +/- 0.05467, N = 15SE +/- 0.06889, N = 152.484572.380052.509292.48892MIN: 1.58MIN: 1.56MIN: 1.61MIN: 1.691. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

DaCapo Benchmark

MinAvgMaxNoctua NH-U14S TR5-SP627.030.631.8NH-D9 TR5-SP6 4U27.530.632.0Dynatron A5435.839.141.3Arctic Freezer 4U-M29.432.533.4OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor1122334455

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: H2O In-Memory Platform For Machine LearningNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M10002000300040005000SE +/- 266.33, N = 15SE +/- 37.26, N = 3SE +/- 28.54, N = 3SE +/- 200.53, N = 124448399840014283

MinAvgMaxNoctua NH-U14S TR5-SP626.531.933.6NH-D9 TR5-SP6 4U27.933.034.8Dynatron A5434.441.945.8Arctic Freezer 4U-M28.633.234.8OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor1224364860

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: PMD Source Code AnalyzerNoctua NH-U14S TR5-SP6NH-D9 TR5-SP6 4UDynatron A54Arctic Freezer 4U-M400800120016002000SE +/- 28.43, N = 15SE +/- 25.71, N = 12SE +/- 29.96, N = 15SE +/- 32.79, N = 151824181718251916

196 Results Shown

OpenFOAM
PostgreSQL:
  100 - 1000 - Read Write - Average Latency
  100 - 1000 - Read Write
OpenFOAM
C-Blosc:
  blosclz shuffle - 64MB
  blosclz shuffle - 128MB
  blosclz shuffle - 32MB
  blosclz shuffle - 8MB
  blosclz shuffle - 256MB
  blosclz shuffle - 16MB
TiDB Community Server
C-Blosc
TiDB Community Server
C-Blosc:
  blosclz noshuffle - 128MB
  blosclz bitshuffle - 64MB
  blosclz bitshuffle - 128MB
  blosclz noshuffle - 256MB
  blosclz noshuffle - 16MB
  blosclz noshuffle - 32MB
  blosclz noshuffle - 64MB
  blosclz bitshuffle - 8MB
  blosclz bitshuffle - 32MB
Timed Linux Kernel Compilation
C-Blosc:
  blosclz noshuffle - 8MB
  blosclz bitshuffle - 16MB
Apache IoTDB:
  800 - 100 - 800 - 400:
    Average Latency
    point/sec
OpenVINO
DaCapo Benchmark
OpenVINO
DaCapo Benchmark
Timed Linux Kernel Compilation
DaCapo Benchmark
OpenFOAM
Apache IoTDB
RocksDB
DaCapo Benchmark
RocksDB
QMCPACK
Blender
OpenVINO
oneDNN:
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU
OpenVINO
oneDNN
Apache IoTDB
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
  Vehicle Detection FP16-INT8 - CPU
DaCapo Benchmark
oneDNN
Timed Gem5 Compilation
oneDNN
OpenVINO:
  Face Detection Retail FP16-INT8 - CPU
  Person Detection FP32 - CPU
DaCapo Benchmark
OpenVINO
DaCapo Benchmark
OpenVINO
DaCapo Benchmark
OpenVINO:
  Face Detection Retail FP16-INT8 - CPU
  Face Detection Retail FP16 - CPU
CloverLeaf
Blender
OpenVINO
OSPRay Studio
QuantLib
OpenVINO
DaCapo Benchmark
OpenVINO:
  Age Gender Recognition Retail 0013 FP16 - CPU
  Face Detection FP16 - CPU
Cpuminer-Opt
DaCapo Benchmark:
  Zxing 1D/2D Barcode Image Processing
  Jython
OpenVINO
DaCapo Benchmark
OpenVINO:
  Road Segmentation ADAS FP16-INT8 - CPU
  Face Detection FP16 - CPU
Embree
DaCapo Benchmark
OpenVINO:
  Road Segmentation ADAS FP16 - CPU:
    ms
    FPS
OSPRay Studio
RocksDB
Cpuminer-Opt
QMCPACK
OpenVINO:
  Machine Translation EN To DE FP16 - CPU:
    FPS
    ms
DaCapo Benchmark
easyWave
OpenVINO:
  Age Gender Recognition Retail 0013 FP16 - CPU
  Person Detection FP16 - CPU
  Person Detection FP16 - CPU
OSPRay Studio
OpenVINO
Timed LLVM Compilation
easyWave
DaCapo Benchmark
PostgreSQL
Timed Godot Game Engine Compilation
OpenFOAM
OpenVINO
Blender
OSPRay Studio
Blender
oneDNN:
  Recurrent Neural Network Inference - u8s8f32 - CPU
  IP Shapes 3D - f32 - CPU
OSPRay Studio
Embree
OpenVINO
OSPRay Studio
PostgreSQL
oneDNN
Coremark
DaCapo Benchmark
oneDNN
QuantLib
QMCPACK
OSPRay Studio:
  1 - 1080p - 1 - Path Tracer - CPU
  3 - 4K - 32 - Path Tracer - CPU
DuckDB
QMCPACK
Cpuminer-Opt
OSPRay Studio
Timed LLVM Compilation
OpenVINO
DaCapo Benchmark
OSPRay Studio
oneDNN
OpenVINO
7-Zip Compression
OSPRay Studio:
  3 - 4K - 1 - Path Tracer - CPU
  2 - 1080p - 32 - Path Tracer - CPU
  3 - 1080p - 1 - Path Tracer - CPU
easyWave
oneDNN
Embree
Cpuminer-Opt:
  Myriad-Groestl
  Skeincoin
  Garlicoin
DaCapo Benchmark
QMCPACK
OSPRay Studio
Timed Node.js Compilation
OpenVINO
OSPRay Studio:
  2 - 1080p - 16 - Path Tracer - CPU
  2 - 1080p - 1 - Path Tracer - CPU
Cpuminer-Opt
oneDNN
OpenVINO
oneDNN
Embree
DuckDB
CloverLeaf
OSPRay Studio
7-Zip Compression
oneDNN
OpenVKL
CloverLeaf
oneDNN
TiDB Community Server
oneDNN
Cpuminer-Opt
RocksDB
OSPRay Studio
OpenVINO
oneDNN
OpenVINO
Blender
Embree
OpenVKL
Embree
Cpuminer-Opt:
  Triple SHA-256, Onecoin
  Magi
DaCapo Benchmark
Cpuminer-Opt
Intel Open Image Denoise:
  RTLightmap.hdr.4096x4096 - CPU-Only
  RT.ldr_alb_nrm.3840x2160 - CPU-Only
  RT.hdr_alb_nrm.3840x2160 - CPU-Only
CPU Temperature Monitor:
  Phoronix Test Suite System Monitoring
  CPU Temp Monitor
TiDB Community Server
QMCPACK
QMCPACK
oneDNN
oneDNN
oneDNN
oneDNN
oneDNN
oneDNN
oneDNN
oneDNN
DaCapo Benchmark
DaCapo Benchmark
DaCapo Benchmark
DaCapo Benchmark