Intel Optimized Power Mode Xeon Platinum Benchmarks

2 x INTEL XEON PLATINUM 8592 testing by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2312153-NE-XEONEMRPO30
Jump To Table - Results

View

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

Limit displaying results to tests within:

C++ Boost Tests 3 Tests
Timed Code Compilation 3 Tests
C/C++ Compiler Tests 9 Tests
Compression Tests 2 Tests
CPU Massive 12 Tests
Creator Workloads 9 Tests
Database Test Suite 4 Tests
Encoding 6 Tests
Game Development 2 Tests
HPC - High Performance Computing 6 Tests
Java Tests 2 Tests
Common Kernel Benchmarks 2 Tests
Machine Learning 3 Tests
Multi-Core 15 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 3 Tests
Programmer / Developer System Benchmarks 4 Tests
Python Tests 7 Tests
Scientific Computing 2 Tests
Server 8 Tests
Server CPU Tests 9 Tests
Single-Threaded 2 Tests
Video Encoding 6 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
Default
December 14 2023
  16 Hours, 25 Minutes
Optimized Power Mode
December 15 2023
  1 Day, 52 Minutes
Invert Hiding All Results Option
  20 Hours, 38 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

Default

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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
Processor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x21000161
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

Optimized Power Mode

Processor: 2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Intel X710 for 10GBASE-T

OS: Ubuntu 23.10, Kernel: 6.5.0-13-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080

Intel Optimized Power Mode Xeon Platinum BenchmarksOpenBenchmarking.orgPhoronix Test Suite2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads)Quanta Cloud S6Q-MB-MPS (3B05.TEL4P1 BIOS)Intel Device 1bce1008GB3201GB Micron_7450_MTFDKCB3T2TFSASPEED2 x Intel X710 for 10GBASE-TUbuntu 23.106.5.0-13-generic (x86_64)GCC 13.2.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionIntel Optimized Power Mode Xeon Platinum 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: intel_pstate performance (EPP: performance) - CPU Microcode: 0x21000161- OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)- Python 3.11.6- 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: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

Default vs. Optimized Power Mode ComparisonPhoronix Test SuiteBaseline+13.5%+13.5%+27%+27%+40.5%+40.5%+54%+54%15%10.7%8.4%4.6%4.2%3.7%2.7%2.5%1:1054.1%CPU - 256 - ResNet-5041.2%CPU - 256 - ResNet-15239.3%CPU - 64 - ResNet-15238.5%50035.1%CPU - 64 - ResNet-5033.7%motorBike - Execution Time33.3%100031.7%GET - 5024.5%12 - Compression Speed22.6%CPU - 64 - Efficientnet_v2_l20.2%GhostRider - 1M19.4%Bosphorus 4K - Faster19.1%Bosphorus 4K - Ultra Fast18.3%CPU - 256 - Efficientnet_v2_l18.3%19 - Compression Speed17.9%10 - G.M.O.A.Q16.9%e.G.B.S - 120016.5%19, Long Mode - Compression Speed15.7%Barbershop - CPU-OnlyPreset 12 - Bosphorus 1080p14.4%e.G.B.S - 240014.4%IMDB14.2%Bosphorus 4K - Super Fast14.2%Bosphorus 4K - Very Fast14.2%Create - 100 - 10000014%50012.4%19 - D.S12.3%Preset 8 - Bosphorus 1080p12.3%Preset 8 - Bosphorus 4K12.2%libx265 - Live11.5%Bosphorus 1080p - Faster10.9%12 - D.S10.9%1B32 - 256 - 5710.5%Bosphorus 1080p - Fast10.3%VMAF Optimized - Bosphorus 1080p10.1%64 - 256 - 579.9%Preset 12 - Bosphorus 4K9.9%Preset 4 - Bosphorus 4K9.8%Preset 13 - Bosphorus 4K9.6%Preset 13 - Bosphorus 1080p9.4%R.O.R.S.I9.4%Bosphorus 4K - Ultra Fast9.4%Bosphorus 1080p - Very Fast9.2%Bosphorus 4K - Fast9.2%Bosphorus 1080p - Ultra Fast8.7%Bosphorus 1080p - Super Fast8.6%d.S.M.S - Mesh Time19, Long Mode - D.S8.2%P.S.O - Bosphorus 1080p8%Time To Compile7.5%100 - 1000 - Read Write - Average Latency7.2%100 - 1000 - Read Write7.1%V.Q.O - Bosphorus 1080p6.9%Bosphorus 1080p - Ultra Fast6.9%Bosphorus 4K - Very Fast6.8%Preset 4 - Bosphorus 1080p6.5%10005.9%Unix Makefiles5.9%TPC-H Parquet5.8%Bosphorus 4K - Super Fast5.7%Compression Rating5.4%libx265 - Platform5.2%1:1005.1%Bosphorus 1080p - Super Fast5%128 - 256 - 575%Bosphorus 1080p - Very Fast4.8%SET - 5004.8%R.5.S.I - A.M.S4.7%R.5.S.I - A.M.S4.7%Classroom - CPU-Onlylibx265 - Video On Demand4.2%RT.ldr_alb_nrm.3840x2160 - CPU-Onlylibx265 - Upload3.8%128 - 256 - 32A.G.R.R.0.F.I - CPU3.6%32 - 256 - 5123.4%256 - 256 - 573.2%defconfig3%GET - 5002.8%128 - 256 - 512A.G.R.R.0.F.I - CPU2.5%Bumper BeamNinja2.5%10 - Q2210.5%10 - Q2117.7%10 - Q2019.6%10 - Q1912.6%10 - Q1810.1%10 - Q173.4%10 - Q1613.8%10 - Q158.7%10 - Q1413.3%10 - Q1315.8%10 - Q1226.8%10 - Q1133.9%10 - Q1018.4%10 - Q0923.3%10 - Q0830.5%10 - Q0722.5%10 - Q0626.8%10 - Q0539.4%10 - Q0413.7%10 - Q0319.3%10 - Q0240.2%10 - Q0119%MemcachedPyTorchPyTorchPyTorchnginxPyTorchOpenFOAMnginxRedisZstd CompressionPyTorchXmrigVVenCuvg266PyTorchZstd CompressionApache Spark TPC-HeasyWaveZstd CompressionBlenderSVT-AV1easyWaveDuckDBuvg266uvg266Apache HadoopApache HTTP ServerZstd CompressionSVT-AV1SVT-AV1FFmpegVVenCZstd CompressionY-CruncherLiquid-DSPVVenCSVT-VP9Liquid-DSPSVT-AV1SVT-AV1SVT-AV1SVT-AV1OpenRadiossKvazaaruvg266VVenCuvg266uvg266OpenFOAMZstd CompressionSVT-VP9Timed GCC CompilationPostgreSQLPostgreSQLSVT-VP9KvazaarKvazaarSVT-AV1Apache HTTP ServerTimed LLVM CompilationDuckDBKvazaar7-Zip CompressionFFmpegMemcachedKvazaarLiquid-DSPKvazaarRedisNeural Magic DeepSparseNeural Magic DeepSparseBlenderFFmpegIntel Open Image DenoiseFFmpegLiquid-DSPOpenVINOLiquid-DSPLiquid-DSPTimed Linux Kernel CompilationRedisLiquid-DSPOpenVINOOpenRadiossTimed LLVM CompilationApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HDefaultOptimized Power Mode

Intel Optimized Power Mode Xeon Platinum Benchmarkspytorch: CPU - 64 - Efficientnet_v2_lpytorch: CPU - 256 - Efficientnet_v2_lbuild-gcc: Time To Compilepgbench: 100 - 1000 - Read Only - Average Latencypgbench: 100 - 1000 - Read Onlyspark-tpch: 10 - Q22spark-tpch: 10 - Q21spark-tpch: 10 - Q20spark-tpch: 10 - Q19spark-tpch: 10 - Q18spark-tpch: 10 - Q17spark-tpch: 10 - Q16spark-tpch: 10 - Q15spark-tpch: 10 - Q14spark-tpch: 10 - Q13spark-tpch: 10 - Q12spark-tpch: 10 - Q11spark-tpch: 10 - Q10spark-tpch: 10 - Q09spark-tpch: 10 - Q08spark-tpch: 10 - Q07spark-tpch: 10 - Q06spark-tpch: 10 - Q05spark-tpch: 10 - Q04spark-tpch: 10 - Q03spark-tpch: 10 - Q02spark-tpch: 10 - Q01spark-tpch: 10 - Geometric Mean Of All Queriespytorch: CPU - 64 - ResNet-152memcached: 1:10pytorch: CPU - 256 - ResNet-152blender: Barbershop - CPU-Onlyeasywave: e2Asean Grid + BengkuluSept2007 Source - 2400duckdb: TPC-H Parquetduckdb: IMDBbuild-llvm: Unix Makefilesffmpeg: libx265 - Uploadffmpeg: libx265 - Video On Demandffmpeg: libx265 - Platformbuild-linux-kernel: allmodconfigpgbench: 100 - 1000 - Read Write - Average Latencypgbench: 100 - 1000 - Read Writeqmcpack: Li2_STO_aeeasywave: e2Asean Grid + BengkuluSept2007 Source - 1200openradioss: Chrysler Neon 1Mopenradioss: Bird Strike on Windshieldopenradioss: INIVOL and Fluid Structure Interaction Drop Containerbuild-llvm: Ninjavvenc: Bosphorus 4K - Fastnginx: 500apache: 500openradioss: Rubber O-Ring Seal Installationliquid-dsp: 64 - 256 - 57openradioss: Bumper Beamcompress-zstd: 12 - Decompression Speedcompress-zstd: 12 - Compression Speedredis: SET - 500deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamcompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedbuild-linux-kernel: defconfignginx: 1000compress-zstd: 19 - Decompression Speedcompress-zstd: 19 - Compression Speedxmrig: GhostRider - 1Mpytorch: CPU - 64 - ResNet-50pytorch: CPU - 256 - ResNet-50openvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUmemcached: 1:100vvenc: Bosphorus 4K - Fasteropenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUquantlib: Multi-Threadedopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUffmpeg: libx265 - Livehadoop: Create - 100 - 100000deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamliquid-dsp: 32 - 256 - 512liquid-dsp: 256 - 256 - 32compress-7zip: Decompression Ratingcompress-7zip: Compression Ratingdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamuvg266: Bosphorus 4K - Very Fastdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamvvenc: Bosphorus 1080p - Fastopenradioss: Cell Phone Drop Testblender: Classroom - CPU-Onlyliquid-dsp: 256 - 256 - 512apache: 1000liquid-dsp: 128 - 256 - 512liquid-dsp: 64 - 256 - 512liquid-dsp: 256 - 256 - 57liquid-dsp: 128 - 256 - 57liquid-dsp: 128 - 256 - 32liquid-dsp: 64 - 256 - 32liquid-dsp: 32 - 256 - 32liquid-dsp: 32 - 256 - 57vvenc: Bosphorus 1080p - Fastersvt-av1: Preset 4 - Bosphorus 4Kredis: SET - 50uvg266: Bosphorus 4K - Slowredis: GET - 500quantlib: Single-Threadedxmrig: Wownero - 1Mredis: GET - 50openfoam: drivaerFastback, Small Mesh Size - Execution Timeopenfoam: drivaerFastback, Small Mesh Size - Mesh Timesvt-av1: Preset 13 - Bosphorus 4Kuvg266: Bosphorus 4K - Mediumuvg266: Bosphorus 1080p - Super Fastxmrig: CryptoNight-Femto UPX2 - 1Mkvazaar: Bosphorus 4K - Slowxmrig: KawPow - 1Mxmrig: Monero - 1Mxmrig: CryptoNight-Heavy - 1Mkvazaar: Bosphorus 4K - Mediumblender: BMW27 - CPU-Onlysvt-av1: Preset 4 - Bosphorus 1080puvg266: Bosphorus 4K - Super Fastuvg266: Bosphorus 4K - Ultra Fastkvazaar: Bosphorus 4K - Ultra Fastsvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Kuvg266: Bosphorus 1080p - Ultra Fastuvg266: Bosphorus 1080p - Slowkvazaar: Bosphorus 4K - Very Fastsvt-vp9: VMAF Optimized - Bosphorus 1080pkvazaar: Bosphorus 4K - Super Fastoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyy-cruncher: 1Bsvt-av1: Preset 8 - Bosphorus 1080puvg266: Bosphorus 1080p - Mediumkvazaar: Bosphorus 1080p - Slowuvg266: Bosphorus 1080p - Very Fastsvt-av1: Preset 12 - Bosphorus 1080pkvazaar: Bosphorus 1080p - Mediumsvt-vp9: Visual Quality Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080psvt-av1: Preset 13 - Bosphorus 1080pkvazaar: Bosphorus 1080p - Super Fastkvazaar: Bosphorus 1080p - Ultra Fastkvazaar: Bosphorus 1080p - Very Fastopenfoam: motorBike - Execution Timesvt-vp9: Visual Quality Optimized - Bosphorus 4KDefaultOptimized Power Mode2.622.59706.2591.1248930894.4956595126.481879558.561719895.0945846212.8941656812.600738214.972441044.245615805.778444925.644020567.933933265.9976617511.8791221017.5612882012.0530392311.474618282.5661711712.944283498.1769722312.590769777.698114088.841855698.3591968317.673360511.1217.85149.4989.984148.55121.967177.43127.0053.6353.98149.79215.6346396294.38436.54685.82111.2397.8796.5186.921273684.7190823.0681.69281016666784.781422.7333.62503177.67397.7731160.40641183.89.9023.756243384.191173.519.116522.543.9144.58236.70539.693441439.7110.83612.5110205.6153.512390.2542.72748.1014.328930.0028.851106.325.1524795.17388447.238.413330.190.40121577.552.4548795.97131.81549013.94514580.631833.63851899.2223463.0854137.3439462.9932137.35405082450006185600000637311689516350.9008182.159151.70331235.406356.065.673211244.794135.93141778.594576.5445834.176735.66951791.273774.0722862.138219.91525.7434.94214456666780826.711473900000101233666758355000004329866667361186666724760333331211766667142910000032.0917.2973060186.4227.203240001.583650.575002.34744838.923.46982230.04223218.76329.79158.2369677.841.4570383.270469.870573.041.9912.8920.95257.8759.5977.5369.466218.452166.4780.3069.36542.9871.054.535.199142.26588.46127.25160.63502.707131.14463.27542.17628.755263.88282.05268.494.132882.182.19759.2161.1418784684.9695701631.1611911210.242673195.7373820014.1998758313.028431495.656485284.614900046.548335146.5348194710.057694168.0304369914.0628064021.6599576115.7232208214.057704933.2531764218.041547789.2947692915.0188730810.7942171110.525319649.7730412712.762180648.2112.81129.94102.928157.101139.326187.83726.0251.4551.31151.27616.7525969592.67242.55986.30111.7398.4998.9056.340202507.4280817.7389.37255657333382.731282.7272.22389636.67392.4515162.58951094.28.5624.476184861.991044.616.213832.432.8331.58237.36538.203274425.329.09612.5510168.0653.452392.3842.59750.4314.308943.8828.991100.765.1324922.40391468.438.793297.810.41117369.552.4249494.06118.24481413.90954590.337533.90321883.6573461.1469138.0114460.6851138.14974914266676301483333638136654459346.7411183.710451.61761237.025749.105.938510738.135236.12861768.910876.5042834.270635.95611776.525273.9896863.347418.05325.3733.40214100000076315.65151346666799966333356566000004125000000374523333324608666671204500000129333333328.9266.6453050498.0026.713152359.753641.475701.73811819.5023.34883327.70873199.54929.62145.7569847.941.1369196.770298.870338.641.6912.6719.66950.6850.3670.8761.914198.742153.1778.9364.97493.2667.214.724.697126.69786.78125.18147.08439.477130.64433.53502.05574.599251.33263.96256.195.50897OpenBenchmarking.org

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_lOptimized Power ModeDefault0.58951.1791.76852.3582.9475SE +/- 0.02, N = 3SE +/- 0.02, N = 32.182.62MIN: 0.98 / MAX: 3.41MIN: 1.32 / MAX: 3.9
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_lOptimized Power ModeDefault0.00160.00320.00480.00640.0080.0070.007
OpenBenchmarking.orgMegahertz, More Is BetterPyTorch 2.1CPU Peak Freq (Highest CPU Core Frequency) MonitorOptimized Power ModeDefault9001800270036004500Min: 800 / Avg: 3770.85 / Max: 5154Min: 800 / Avg: 3771.05 / Max: 4127
OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.1CPU Power Consumption MonitorOptimized Power ModeDefault80160240320400Min: 151.88 / Avg: 323.77 / Max: 364.19Min: 191.62 / Avg: 400.65 / Max: 444.681. Optimized Power Mode: Approximate power consumption of 699024 Joules per run.2. Default: Approximate power consumption of 793148 Joules per run.
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_lOptimized Power ModeDefault246810Min: 2.15 / Avg: 2.18 / Max: 2.22Min: 2.59 / Avg: 2.62 / Max: 2.67

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_lOptimized Power ModeDefault0.58281.16561.74842.33122.914SE +/- 0.02, N = 3SE +/- 0.00, N = 32.192.59MIN: 0.98 / MAX: 3.3MIN: 1.19 / MAX: 4
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_lOptimized Power ModeDefault0.00160.00320.00480.00640.0080.0070.006
OpenBenchmarking.orgMegahertz, More Is BetterPyTorch 2.1CPU Peak Freq (Highest CPU Core Frequency) MonitorOptimized Power ModeDefault8001600240032004000Min: 800 / Avg: 3772.48 / Max: 4480Min: 800 / Avg: 3773.77 / Max: 3934
OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.1CPU Power Consumption MonitorOptimized Power ModeDefault80160240320400Min: 150.79 / Avg: 323.75 / Max: 378.29Min: 188.24 / Avg: 400.23 / Max: 457.621. Optimized Power Mode: Approximate power consumption of 699740 Joules per run.2. Default: Approximate power consumption of 776446 Joules per run.
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_lOptimized Power ModeDefault246810Min: 2.15 / Avg: 2.19 / Max: 2.23Min: 2.58 / Avg: 2.59 / Max: 2.59

Timed GCC Compilation

This test times how long it takes to build the GNU Compiler Collection (GCC) open-source compiler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 13.2Time To CompileOptimized Power ModeDefault160320480640800SE +/- 4.73, N = 3SE +/- 2.37, N = 3759.22706.26
OpenBenchmarking.orgMegahertz, More Is BetterTimed GCC Compilation 13.2CPU Peak Freq (Highest CPU Core Frequency) MonitorOptimized Power ModeDefault7001400210028003500Min: 800 / Avg: 3848.62 / Max: 3914Min: 800 / Avg: 3844.27 / Max: 3932
OpenBenchmarking.orgWatts, Fewer Is BetterTimed GCC Compilation 13.2CPU Power Consumption MonitorOptimized Power ModeDefault130260390520650Min: 90.55 / Avg: 227.95 / Max: 760.59Min: 115.2 / Avg: 332.29 / Max: 762.281. Optimized Power Mode: Approximate power consumption of 174682 Joules per run.2. Default: Approximate power consumption of 236811 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 13.2Time To CompileOptimized Power ModeDefault130260390520650Min: 754.14 / Avg: 759.22 / Max: 768.67Min: 701.9 / Avg: 706.26 / Max: 710.04

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 LatencyOptimized Power ModeDefault0.25670.51340.77011.02681.2835SE +/- 0.016, N = 12SE +/- 0.022, N = 101.1411.1241. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgMegahertz, More Is BetterPostgreSQL 16CPU Peak Freq (Highest CPU Core Frequency) MonitorOptimized Power ModeDefault7001400210028003500Min: 800 / Avg: 2988.27 / Max: 3921Min: 800 / Avg: 3000.4 / Max: 3925
OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16CPU Power Consumption MonitorOptimized Power ModeDefault130260390520650Min: 94.15 / Avg: 458.57 / Max: 678.78Min: 199.24 / Avg: 508.51 / Max: 759.361. Optimized Power Mode: Approximate power consumption of 63054 Joules per run.2. Default: Approximate power consumption of 68242 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencyOptimized Power ModeDefault246810Min: 1.07 / Avg: 1.14 / Max: 1.29Min: 1.01 / Avg: 1.12 / Max: 1.241. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlyOptimized Power ModeDefault200K400K600K800K1000KSE +/- 11877.48, N = 12SE +/- 17460.42, N = 108784688930891. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlyOptimized Power ModeDefault150K300K450K600K750KMin: 775483.19 / Avg: 878468.08 / Max: 938747.21Min: 808478.15 / Avg: 893089.02 / Max: 992473.841. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Apache Spark TPC-H

This is a benchmark of Apache Spark using TPC-H data-set. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmarks the Apache Spark in a single-system configuration using spark-submit. The test makes use of https://github.com/ssavvides/tpch-spark/ for facilitating the TPC-H benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q22Optimized Power ModeDefault1.11822.23643.35464.47285.591SE +/- 0.13159559, N = 7SE +/- 0.16829529, N = 34.969570164.49565951
OpenBenchmarking.orgMegahertz, More Is BetterApache Spark TPC-H 3.5CPU Peak Freq (Highest CPU Core Frequency) MonitorOptimized Power ModeDefault10002000300040005000Min: 800 / Avg: 3833.92 / Max: 4663Min: 800 / Avg: 3836.91 / Max: 5474
OpenBenchmarking.orgWatts, Fewer Is BetterApache Spark TPC-H 3.5CPU Power Consumption MonitorOptimized Power ModeDefault110220330440550Min: 92.82 / Avg: 308.18 / Max: 608.02Min: 145.89 / Avg: 378.9 / Max: 600.021. Optimized Power Mode: Approximate power consumption of 87523 Joules per run.2. Default: Approximate power consumption of 99525 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q22Optimized Power ModeDefault246810Min: 4.57 / Avg: 4.97 / Max: 5.53Min: 4.17 / Avg: 4.5 / Max: 4.74

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q21Optimized Power ModeDefault714212835SE +/- 0.34, N = 7SE +/- 0.40, N = 331.1626.48
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q21Optimized Power ModeDefault714212835Min: 30.28 / Avg: 31.16 / Max: 32.81Min: 26.01 / Avg: 26.48 / Max: 27.27

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q20Optimized Power ModeDefault3691215SE +/- 0.14303850, N = 7SE +/- 0.45558852, N = 310.242673198.56171989
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q20Optimized Power ModeDefault3691215Min: 9.81 / Avg: 10.24 / Max: 10.91Min: 8.01 / Avg: 8.56 / Max: 9.47

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q19Optimized Power ModeDefault1.29092.58183.87275.16366.4545SE +/- 0.14465657, N = 7SE +/- 0.17083033, N = 35.737382005.09458462
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q19Optimized Power ModeDefault246810Min: 5.27 / Avg: 5.74 / Max: 6.26Min: 4.82 / Avg: 5.09 / Max: 5.41

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q18Optimized Power ModeDefault48121620SE +/- 0.53, N = 7SE +/- 0.44, N = 314.2012.89
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q18Optimized Power ModeDefault48121620Min: 12.93 / Avg: 14.2 / Max: 16.72Min: 12.21 / Avg: 12.89 / Max: 13.71

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q17Optimized Power ModeDefault3691215SE +/- 0.26, N = 7SE +/- 0.23, N = 313.0312.60
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q17Optimized Power ModeDefault48121620Min: 12.3 / Avg: 13.03 / Max: 14.17Min: 12.35 / Avg: 12.6 / Max: 13.06

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q16Optimized Power ModeDefault1.27272.54543.81815.09086.3635SE +/- 0.10743013, N = 7SE +/- 0.28343850, N = 35.656485284.97244104
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q16Optimized Power ModeDefault246810Min: 5.34 / Avg: 5.66 / Max: 6.18Min: 4.59 / Avg: 4.97 / Max: 5.53

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q15Optimized Power ModeDefault1.03842.07683.11524.15365.192SE +/- 0.07270001, N = 7SE +/- 0.05108329, N = 34.614900044.24561580
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q15Optimized Power ModeDefault246810Min: 4.46 / Avg: 4.61 / Max: 4.99Min: 4.15 / Avg: 4.25 / Max: 4.33

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q14Optimized Power ModeDefault246810SE +/- 0.14967485, N = 7SE +/- 0.09561638, N = 36.548335145.77844492
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q14Optimized Power ModeDefault3691215Min: 6.22 / Avg: 6.55 / Max: 7.24Min: 5.62 / Avg: 5.78 / Max: 5.95

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q13Optimized Power ModeDefault246810SE +/- 0.30330721, N = 7SE +/- 0.08149193, N = 36.534819475.64402056
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q13Optimized Power ModeDefault3691215Min: 5.7 / Avg: 6.53 / Max: 7.77Min: 5.53 / Avg: 5.64 / Max: 5.8

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q12Optimized Power ModeDefault3691215SE +/- 0.34240704, N = 7SE +/- 0.47598391, N = 310.057694167.93393326
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q12Optimized Power ModeDefault3691215Min: 9.01 / Avg: 10.06 / Max: 11.29Min: 7.43 / Avg: 7.93 / Max: 8.89

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q11Optimized Power ModeDefault246810SE +/- 0.21479648, N = 7SE +/- 0.21358847, N = 38.030436995.99766175
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q11Optimized Power ModeDefault3691215Min: 7.44 / Avg: 8.03 / Max: 9.07Min: 5.75 / Avg: 6 / Max: 6.42

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q10Optimized Power ModeDefault48121620SE +/- 0.34, N = 7SE +/- 0.36, N = 314.0611.88
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q10Optimized Power ModeDefault48121620Min: 12.51 / Avg: 14.06 / Max: 15.08Min: 11.16 / Avg: 11.88 / Max: 12.28

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q09Optimized Power ModeDefault510152025SE +/- 0.36, N = 7SE +/- 1.37, N = 321.6617.56
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q09Optimized Power ModeDefault510152025Min: 20.42 / Avg: 21.66 / Max: 23.22Min: 15.25 / Avg: 17.56 / Max: 20

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q08Optimized Power ModeDefault48121620SE +/- 0.45, N = 7SE +/- 0.29, N = 315.7212.05
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q08Optimized Power ModeDefault48121620Min: 14.5 / Avg: 15.72 / Max: 17.85Min: 11.67 / Avg: 12.05 / Max: 12.62

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q07Optimized Power ModeDefault48121620SE +/- 0.30, N = 7SE +/- 0.65, N = 314.0611.47
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q07Optimized Power ModeDefault48121620Min: 13.14 / Avg: 14.06 / Max: 15.35Min: 10.58 / Avg: 11.47 / Max: 12.73

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q06Optimized Power ModeDefault0.7321.4642.1962.9283.66SE +/- 0.19375001, N = 7SE +/- 0.19354811, N = 33.253176422.56617117
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q06Optimized Power ModeDefault246810Min: 2.45 / Avg: 3.25 / Max: 3.82Min: 2.22 / Avg: 2.57 / Max: 2.89

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q05Optimized Power ModeDefault48121620SE +/- 0.84, N = 7SE +/- 0.17, N = 318.0412.94
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q05Optimized Power ModeDefault510152025Min: 15.45 / Avg: 18.04 / Max: 21.29Min: 12.64 / Avg: 12.94 / Max: 13.24

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q04Optimized Power ModeDefault3691215SE +/- 0.18685247, N = 7SE +/- 0.27780883, N = 39.294769298.17697223
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q04Optimized Power ModeDefault3691215Min: 8.66 / Avg: 9.29 / Max: 9.89Min: 7.82 / Avg: 8.18 / Max: 8.72

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q03Optimized Power ModeDefault48121620SE +/- 0.30, N = 7SE +/- 0.05, N = 315.0212.59
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q03Optimized Power ModeDefault48121620Min: 13.8 / Avg: 15.02 / Max: 16.03Min: 12.52 / Avg: 12.59 / Max: 12.68

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q02Optimized Power ModeDefault3691215SE +/- 0.18560870, N = 7SE +/- 0.14674980, N = 310.794217117.69811408
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q02Optimized Power ModeDefault3691215Min: 10.12 / Avg: 10.79 / Max: 11.41Min: 7.47 / Avg: 7.7 / Max: 7.97

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q01Optimized Power ModeDefault3691215SE +/- 0.34672923, N = 7SE +/- 0.23680200, N = 310.525319648.84185569
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q01Optimized Power ModeDefault3691215Min: 9.25 / Avg: 10.53 / Max: 11.61Min: 8.55 / Avg: 8.84 / Max: 9.31

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Geometric Mean Of All QueriesOptimized Power ModeDefault3691215SE +/- 0.09145601, N = 7SE +/- 0.07178690, N = 39.773041278.35919683MIN: 4.46 / MAX: 32.81MIN: 4.15 / MAX: 27.27
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q01Optimized Power ModeDefault3691215SE +/- 0.34672923, N = 7SE +/- 0.23680200, N = 310.525319648.84185569
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q02Optimized Power ModeDefault3691215SE +/- 0.18560870, N = 7SE +/- 0.14674980, N = 310.794217117.69811408
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q03Optimized Power ModeDefault48121620SE +/- 0.30, N = 7SE +/- 0.05, N = 315.0212.59
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q04Optimized Power ModeDefault3691215SE +/- 0.18685247, N = 7SE +/- 0.27780883, N = 39.294769298.17697223
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q05Optimized Power ModeDefault48121620SE +/- 0.84, N = 7SE +/- 0.17, N = 318.0412.94
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q06Optimized Power ModeDefault0.7321.4642.1962.9283.66SE +/- 0.19375001, N = 7SE +/- 0.19354811, N = 33.253176422.56617117
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q07Optimized Power ModeDefault48121620SE +/- 0.30, N = 7SE +/- 0.65, N = 314.0611.47
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q08Optimized Power ModeDefault48121620SE +/- 0.45, N = 7SE +/- 0.29, N = 315.7212.05
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q09Optimized Power ModeDefault510152025SE +/- 0.36, N = 7SE +/- 1.37, N = 321.6617.56
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q10Optimized Power ModeDefault48121620SE +/- 0.34, N = 7SE +/- 0.36, N = 314.0611.88
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q11Optimized Power ModeDefault246810SE +/- 0.21479648, N = 7SE +/- 0.21358847, N = 38.030436995.99766175
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q12Optimized Power ModeDefault3691215SE +/- 0.34240704, N = 7SE +/- 0.47598391, N = 310.057694167.93393326
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q13Optimized Power ModeDefault246810SE +/- 0.30330721, N = 7SE +/- 0.08149193, N = 36.534819475.64402056
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q14Optimized Power ModeDefault246810SE +/- 0.14967485, N = 7SE +/- 0.09561638, N = 36.548335145.77844492
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q15Optimized Power ModeDefault1.03842.07683.11524.15365.192SE +/- 0.07270001, N = 7SE +/- 0.05108329, N = 34.614900044.24561580
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q16Optimized Power ModeDefault1.27272.54543.81815.09086.3635SE +/- 0.10743013, N = 7SE +/- 0.28343850, N = 35.656485284.97244104
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q17Optimized Power ModeDefault3691215SE +/- 0.26, N = 7SE +/- 0.23, N = 313.0312.60
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q18Optimized Power ModeDefault48121620SE +/- 0.53, N = 7SE +/- 0.44, N = 314.2012.89
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q19Optimized Power ModeDefault1.29092.58183.87275.16366.4545SE +/- 0.14465657, N = 7SE +/- 0.17083033, N = 35.737382005.09458462
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q20Optimized Power ModeDefault3691215SE +/- 0.14303850, N = 7SE +/- 0.45558852, N = 310.242673198.56171989
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q21Optimized Power ModeDefault714212835SE +/- 0.34, N = 7SE +/- 0.40, N = 331.1626.48
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Q22Optimized Power ModeDefault1.11822.23643.35464.47285.591SE +/- 0.13159559, N = 7SE +/- 0.16829529, N = 34.969570164.49565951
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Geometric Mean Of All QueriesOptimized Power ModeDefault3691215Min: 9.57 / Avg: 9.77 / Max: 10.19Min: 8.28 / Avg: 8.36 / Max: 8.5

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-152Optimized Power ModeDefault48121620SE +/- 0.12, N = 12SE +/- 0.23, N = 312.7617.67MIN: 5.75 / MAX: 15.71MIN: 10.89 / MAX: 18.38
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-152Optimized Power ModeDefault0.00720.01440.02160.02880.0360.0300.032
OpenBenchmarking.orgMegahertz, More Is BetterPyTorch 2.1CPU Peak Freq (Highest CPU Core Frequency) MonitorOptimized Power ModeDefault7001400210028003500Min: 800 / Avg: 2922.73 / Max: 3908Min: 800 / Avg: 2912.64 / Max: 3907
OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.1CPU Power Consumption MonitorOptimized Power ModeDefault100200300400500Min: 181.02 / Avg: 419.77 / Max: 482.16Min: 206.94 / Avg: 550.2 / Max: 586.611. Optimized Power Mode: Approximate power consumption of 72165 Joules per run.2. Default: Approximate power consumption of 69509 Joules per run.
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-152Optimized Power ModeDefault48121620Min: 12.18 / Avg: 12.76 / Max: 13.37Min: 17.29 / Avg: 17.67 / Max: 18.08

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10Optimized Power ModeDefault700K1400K2100K2800K3500KSE +/- 43551.88, N = 15SE +/- 29533.59, N = 152180648.213360511.121. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10Optimized Power ModeDefault130026003900520065005158.076290.44
MinAvgMaxOptimized Power Mode80029253905Default80029083906OpenBenchmarking.orgMegahertz, More Is BetterMemcached 1.6.19CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode94.3422.8504.5Default199.2534.2599.5OpenBenchmarking.orgWatts, Fewer Is BetterMemcached 1.6.19CPU Power Consumption Monitor1603204806408001. Optimized Power Mode: Approximate power consumption of 29509 Joules per run.2. Default: Approximate power consumption of 37289 Joules per run.
OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10Optimized Power ModeDefault600K1200K1800K2400K3000KMin: 1997443.47 / Avg: 2180648.21 / Max: 2512967.14Min: 3079708.96 / Avg: 3360511.12 / Max: 3515921.441. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-152Optimized Power ModeDefault48121620SE +/- 0.17, N = 3SE +/- 0.13, N = 1112.8117.85MIN: 6.6 / MAX: 13.9MIN: 7.02 / MAX: 19.19
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-152Optimized Power ModeDefault0.00720.01440.02160.02880.0360.0300.032
MinAvgMaxOptimized Power Mode80029363905Default80029383906OpenBenchmarking.orgMegahertz, More Is BetterPyTorch 2.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode181.0425.6481.4Default206.8549.6589.4OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.1CPU Power Consumption Monitor1603204806408001. Optimized Power Mode: Approximate power consumption of 73200 Joules per run.2. Default: Approximate power consumption of 69045 Joules per run.
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-152Optimized Power ModeDefault510152025Min: 12.62 / Avg: 12.81 / Max: 13.16Min: 17.48 / Avg: 17.85 / Max: 18.9

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Barbershop - Compute: CPU-OnlyOptimized Power ModeDefault306090120150SE +/- 0.11, N = 3SE +/- 6.68, N = 9129.94149.49
MinAvgMaxOptimized Power Mode80027703909Default50026593908OpenBenchmarking.orgMegahertz, More Is BetterBlender 4.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode179654760Default207601760OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 89349 Joules per run.2. Default: Approximate power consumption of 93071 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Barbershop - Compute: CPU-OnlyOptimized Power ModeDefault306090120150Min: 129.76 / Avg: 129.94 / Max: 130.14Min: 129.51 / Avg: 149.49 / Max: 183.04

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: 2400Optimized Power ModeDefault20406080100SE +/- 1.07, N = 3SE +/- 1.41, N = 15102.9389.981. (CXX) g++ options: -O3 -fopenmp
MinAvgMaxOptimized Power Mode80034863906Default80034363906OpenBenchmarking.orgMegahertz, More Is BettereasyWave r34CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode160.9328.1496.2Default198.3407.9539.4OpenBenchmarking.orgWatts, Fewer Is BettereasyWave r34CPU Power Consumption Monitor1402804205607001. Optimized Power Mode: Approximate power consumption of 35760 Joules per run.2. Default: Approximate power consumption of 38994 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400Optimized Power ModeDefault20406080100Min: 100.89 / Avg: 102.93 / Max: 104.49Min: 83.82 / Avg: 89.98 / Max: 101.441. (CXX) g++ options: -O3 -fopenmp

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 ParquetOptimized Power ModeDefault306090120150SE +/- 0.38, N = 3SE +/- 0.31, N = 3157.10148.551. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl
MinAvgMaxOptimized Power Mode80038813918Default80038773921OpenBenchmarking.orgMegahertz, More Is BetterDuckDB 0.9.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode90.3192.7281.6Default137.7288.3394.2OpenBenchmarking.orgWatts, Fewer Is BetterDuckDB 0.9.1CPU Power Consumption Monitor1102203304405501. Optimized Power Mode: Approximate power consumption of 41243 Joules per run.2. Default: Approximate power consumption of 59783 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: TPC-H ParquetOptimized Power ModeDefault306090120150Min: 156.47 / Avg: 157.1 / Max: 157.78Min: 147.97 / Avg: 148.55 / Max: 149.011. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: IMDBOptimized Power ModeDefault306090120150SE +/- 0.43, N = 3SE +/- 0.49, N = 3139.33121.971. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl
MinAvgMaxOptimized Power Mode80038633920Default80038733927OpenBenchmarking.orgMegahertz, More Is BetterDuckDB 0.9.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode101.6224.7314.2Default160.7312.8391.9OpenBenchmarking.orgWatts, Fewer Is BetterDuckDB 0.9.1CPU Power Consumption Monitor1102203304405501. Optimized Power Mode: Approximate power consumption of 42916 Joules per run.2. Default: Approximate power consumption of 61207 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: IMDBOptimized Power ModeDefault306090120150Min: 138.69 / Avg: 139.33 / Max: 140.15Min: 121.06 / Avg: 121.97 / Max: 122.761. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl

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 MakefilesOptimized Power ModeDefault4080120160200SE +/- 0.58, N = 3SE +/- 0.30, N = 3187.84177.43
MinAvgMaxOptimized Power Mode80037093912Default80037013918OpenBenchmarking.orgMegahertz, More Is BetterTimed LLVM Compilation 16.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode94367758Default200469762OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 75506 Joules per run.2. Default: Approximate power consumption of 91316 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix MakefilesOptimized Power ModeDefault306090120150Min: 186.86 / Avg: 187.84 / Max: 188.87Min: 176.85 / Avg: 177.43 / Max: 177.83

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: UploadOptimized Power ModeDefault612182430SE +/- 0.06, N = 3SE +/- 0.06, N = 326.0227.001. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: UploadOptimized Power ModeDefault0.02810.05620.08430.11240.14050.1250.090
MinAvgMaxOptimized Power Mode80038763907Default80038763907OpenBenchmarking.orgMegahertz, More Is BetterFFmpeg 6.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode89.7207.8317.2Default138.2299.2415.2OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor1102203304405501. Optimized Power Mode: Approximate power consumption of 35814 Joules per run.2. Default: Approximate power consumption of 50564 Joules per run.
OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: UploadOptimized Power ModeDefault612182430Min: 25.93 / Avg: 26.02 / Max: 26.12Min: 26.89 / Avg: 27 / Max: 27.091. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On DemandOptimized Power ModeDefault1224364860SE +/- 0.10, N = 3SE +/- 0.04, N = 351.4553.631. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On DemandOptimized Power ModeDefault0.05310.10620.15930.21240.26550.2360.169
MinAvgMaxOptimized Power Mode80038953912Default80038883914OpenBenchmarking.orgMegahertz, More Is BetterFFmpeg 6.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode109.2218.0280.6Default162.7318.2364.5OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor1002003004005001. Optimized Power Mode: Approximate power consumption of 37354 Joules per run.2. Default: Approximate power consumption of 52403 Joules per run.
OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On DemandOptimized Power ModeDefault1122334455Min: 51.26 / Avg: 51.45 / Max: 51.61Min: 53.56 / Avg: 53.63 / Max: 53.681. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: PlatformOptimized Power ModeDefault1224364860SE +/- 0.14, N = 3SE +/- 0.11, N = 351.3153.981. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: PlatformOptimized Power ModeDefault0.05330.10660.15990.21320.26650.2370.169
MinAvgMaxOptimized Power Mode80038833909Default80038683913OpenBenchmarking.orgMegahertz, More Is BetterFFmpeg 6.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode100.3216.9272.9Default103.6319.0374.1OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor1002003004005001. Optimized Power Mode: Approximate power consumption of 37236 Joules per run.2. Default: Approximate power consumption of 52107 Joules per run.
OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: PlatformOptimized Power ModeDefault1122334455Min: 51.04 / Avg: 51.31 / Max: 51.51Min: 53.83 / Avg: 53.98 / Max: 54.191. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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: allmodconfigOptimized Power ModeDefault306090120150SE +/- 0.48, N = 3SE +/- 0.51, N = 3151.28149.79
MinAvgMaxOptimized Power Mode80030663911Default80030663911OpenBenchmarking.orgMegahertz, More Is BetterTimed Linux Kernel Compilation 6.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode174553761Default186584759OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.1CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 90265 Joules per run.2. Default: Approximate power consumption of 94487 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfigOptimized Power ModeDefault306090120150Min: 150.49 / Avg: 151.28 / Max: 152.15Min: 149.28 / Avg: 149.79 / Max: 150.81

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 LatencyOptimized Power ModeDefault48121620SE +/- 0.06, N = 3SE +/- 0.02, N = 316.7515.631. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MinAvgMaxOptimized Power Mode80029963906Default80029813910OpenBenchmarking.orgMegahertz, More Is BetterPostgreSQL 16CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode144.0378.6455.4Default206.2446.2510.9OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 53759 Joules per run.2. Default: Approximate power consumption of 63206 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average LatencyOptimized Power ModeDefault48121620Min: 16.68 / Avg: 16.75 / Max: 16.87Min: 15.61 / Avg: 15.63 / Max: 15.671. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read WriteOptimized Power ModeDefault14K28K42K56K70KSE +/- 214.64, N = 3SE +/- 70.87, N = 359695639621. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read WriteOptimized Power ModeDefault11K22K33K44K55KMin: 59271.88 / Avg: 59695.27 / Max: 59968.38Min: 63821.38 / Avg: 63962.31 / Max: 64045.981. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

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_aeOptimized Power ModeDefault20406080100SE +/- 1.02, N = 5SE +/- 0.40, N = 392.6794.381. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
MinAvgMaxOptimized Power Mode80027393907Default80027603909OpenBenchmarking.orgMegahertz, More Is BetterQMCPACK 3.17.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode175663758Default193667756OpenBenchmarking.orgWatts, Fewer Is BetterQMCPACK 3.17.1CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 66661 Joules per run.2. Default: Approximate power consumption of 68485 Joules per run.
OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.17.1Input: Li2_STO_aeOptimized Power ModeDefault20406080100Min: 91.11 / Avg: 92.67 / Max: 96.4Min: 93.62 / Avg: 94.38 / Max: 94.991. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl

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: 1200Optimized Power ModeDefault1020304050SE +/- 0.41, N = 15SE +/- 0.28, N = 342.5636.551. (CXX) g++ options: -O3 -fopenmp
MinAvgMaxOptimized Power Mode80034503907Default80034693908OpenBenchmarking.orgMegahertz, More Is BettereasyWave r34CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode168.2327.1497.9Default199.5390.6501.4OpenBenchmarking.orgWatts, Fewer Is BettereasyWave r34CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 15787 Joules per run.2. Default: Approximate power consumption of 16795 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200Optimized Power ModeDefault918273645Min: 40.92 / Avg: 42.56 / Max: 46.3Min: 36.05 / Avg: 36.55 / Max: 37.011. (CXX) g++ options: -O3 -fopenmp

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1MOptimized Power ModeDefault20406080100SE +/- 0.17, N = 3SE +/- 0.14, N = 386.3085.82
MinAvgMaxOptimized Power Mode80031533907Default80031383908OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode89537741Default144568757OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 65122 Joules per run.2. Default: Approximate power consumption of 67742 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1MOptimized Power ModeDefault1632486480Min: 85.99 / Avg: 86.3 / Max: 86.56Min: 85.59 / Avg: 85.82 / Max: 86.06

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bird Strike on WindshieldOptimized Power ModeDefault306090120150SE +/- 0.28, N = 3SE +/- 0.65, N = 3111.73111.23
MinAvgMaxOptimized Power Mode80029523907Default80029243915OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode178644730Default101657757OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 76688 Joules per run.2. Default: Approximate power consumption of 77975 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bird Strike on WindshieldOptimized Power ModeDefault20406080100Min: 111.34 / Avg: 111.73 / Max: 112.28Min: 110.57 / Avg: 111.23 / Max: 112.52

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: INIVOL and Fluid Structure Interaction Drop ContainerOptimized Power ModeDefault20406080100SE +/- 0.08, N = 3SE +/- 0.07, N = 398.4997.87
MinAvgMaxOptimized Power Mode80030243907Default80029933905OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode96623713Default201639756OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 69121 Joules per run.2. Default: Approximate power consumption of 70270 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: INIVOL and Fluid Structure Interaction Drop ContainerOptimized Power ModeDefault20406080100Min: 98.36 / Avg: 98.49 / Max: 98.62Min: 97.75 / Avg: 97.87 / Max: 97.99

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: NinjaOptimized Power ModeDefault20406080100SE +/- 0.20, N = 3SE +/- 0.29, N = 398.9196.52
MinAvgMaxOptimized Power Mode80033183908Default249133243908OpenBenchmarking.orgMegahertz, More Is BetterTimed LLVM Compilation 16.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode89460758Default103521759OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 52591 Joules per run.2. Default: Approximate power consumption of 57459 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaOptimized Power ModeDefault20406080100Min: 98.68 / Avg: 98.91 / Max: 99.3Min: 96.08 / Avg: 96.52 / Max: 97.08

VVenC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FastOptimized Power ModeDefault246810SE +/- 0.066, N = 3SE +/- 0.067, N = 36.3406.9211. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FastOptimized Power ModeDefault0.00470.00940.01410.01880.02350.0210.017
MinAvgMaxOptimized Power Mode80038733908Default80038533916OpenBenchmarking.orgMegahertz, More Is BetterVVenC 1.9CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode182.5307.5432.6Default207.3418.4548.0OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.9CPU Power Consumption Monitor1402804205607001. Optimized Power Mode: Approximate power consumption of 32085 Joules per run.2. Default: Approximate power consumption of 40025 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FastOptimized Power ModeDefault3691215Min: 6.22 / Avg: 6.34 / Max: 6.45Min: 6.83 / Avg: 6.92 / Max: 7.051. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500Optimized Power ModeDefault60K120K180K240K300KSE +/- 10.52, N = 3SE +/- 25.30, N = 3202507.42273684.711. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.23.2Connections: 500Optimized Power ModeDefault100200300400500429.69449.51
MinAvgMaxOptimized Power Mode80029253905Default80029033904OpenBenchmarking.orgMegahertz, More Is Betternginx 1.23.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode183471554Default199609655OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 46030 Joules per run.2. Default: Approximate power consumption of 59261 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500Optimized Power ModeDefault50K100K150K200K250KMin: 202494.42 / Avg: 202507.42 / Max: 202528.25Min: 273634.53 / Avg: 273684.71 / Max: 273715.511. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Apache HTTP Server

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

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 500Optimized Power ModeDefault20K40K60K80K100KSE +/- 184.86, N = 3SE +/- 265.12, N = 380817.7390823.061. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 500Optimized Power ModeDefault60120180240300266.08216.64
MinAvgMaxOptimized Power Mode80028893907Default80028903905OpenBenchmarking.orgMegahertz, More Is BetterApache HTTP Server 2.4.56CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode181.8303.7320.2Default196.4419.2442.6OpenBenchmarking.orgWatts, Fewer Is BetterApache HTTP Server 2.4.56CPU Power Consumption Monitor1202403604806001. Optimized Power Mode: Approximate power consumption of 29664 Joules per run.2. Default: Approximate power consumption of 40806 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 500Optimized Power ModeDefault16K32K48K64K80KMin: 80494.85 / Avg: 80817.73 / Max: 81135.15Min: 90495.89 / Avg: 90823.06 / Max: 91348.021. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Rubber O-Ring Seal InstallationOptimized Power ModeDefault20406080100SE +/- 0.13, N = 3SE +/- 0.03, N = 389.3781.69
MinAvgMaxOptimized Power Mode80029753906Default80029943905OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode93580640Default187640756OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 56865 Joules per run.2. Default: Approximate power consumption of 58006 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Rubber O-Ring Seal InstallationOptimized Power ModeDefault20406080100Min: 89.11 / Avg: 89.37 / Max: 89.54Min: 81.66 / Avg: 81.69 / Max: 81.75

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 57Optimized Power ModeDefault600M1200M1800M2400M3000MSE +/- 20734086.19, N = 15SE +/- 24169149.30, N = 3255657333328101666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 57Optimized Power ModeDefault1000K2000K3000K4000K5000K4774859.274449269.38
MinAvgMaxOptimized Power Mode80038093907Default80038433905OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode183535623Default208632708OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 18276 Joules per run.2. Default: Approximate power consumption of 21896 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 57Optimized Power ModeDefault500M1000M1500M2000M2500MMin: 2447400000 / Avg: 2556573333.33 / Max: 2686800000Min: 2785400000 / Avg: 2810166666.67 / Max: 28585000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bumper BeamOptimized Power ModeDefault20406080100SE +/- 0.13, N = 3SE +/- 0.18, N = 382.7384.78
MinAvgMaxOptimized Power Mode80029303906Default80029453911OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode173641735Default104651755OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 57702 Joules per run.2. Default: Approximate power consumption of 59209 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bumper BeamOptimized Power ModeDefault1632486480Min: 82.48 / Avg: 82.73 / Max: 82.87Min: 84.43 / Avg: 84.78 / Max: 85.04

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression SpeedOptimized Power ModeDefault30060090012001500SE +/- 1.74, N = 5SE +/- 1.98, N = 31282.71422.71. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s Per Watt, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression SpeedOptimized Power ModeDefault2468106.1054.516
MinAvgMaxOptimized Power Mode80038443905Default80038823910OpenBenchmarking.orgMegahertz, More Is BetterZstd Compression 1.5.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode90.4210.1264.7Default143.9315.1371.3OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4CPU Power Consumption Monitor1002003004005001. Optimized Power Mode: Approximate power consumption of 14245 Joules per run.2. Default: Approximate power consumption of 21214 Joules per run.
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression SpeedOptimized Power ModeDefault2004006008001000Min: 1278.9 / Avg: 1282.66 / Max: 1288.4Min: 1419.6 / Avg: 1422.73 / Max: 1426.41. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression SpeedOptimized Power ModeDefault70140210280350SE +/- 2.98, N = 5SE +/- 3.46, N = 3272.2333.61. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression SpeedOptimized Power ModeDefault60120180240300Min: 265.2 / Avg: 272.16 / Max: 282.9Min: 328.3 / Avg: 333.6 / Max: 340.11. (CC) gcc options: -O3 -pthread -lz -llzma

Redis

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

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 500Optimized Power ModeDefault500K1000K1500K2000K2500KSE +/- 19286.75, N = 15SE +/- 7546.74, N = 32389636.672503177.671. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 500Optimized Power ModeDefault140028004200560070006737.206160.26
MinAvgMaxOptimized Power Mode80032053905Default80033493905OpenBenchmarking.orgMegahertz, More Is BetterRedis 7.0.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode93.8354.7522.3Default206.4406.3549.1OpenBenchmarking.orgWatts, Fewer Is BetterRedis 7.0.4CPU Power Consumption Monitor1402804205607001. Optimized Power Mode: Approximate power consumption of 11161 Joules per run.2. Default: Approximate power consumption of 12597 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 500Optimized Power ModeDefault400K800K1200K1600K2000KMin: 2252191.25 / Avg: 2389636.67 / Max: 2484516.5Min: 2488101.75 / Avg: 2503177.67 / Max: 25113461. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault90180270360450SE +/- 0.71, N = 3SE +/- 3.53, N = 3392.45397.77
MinAvgMaxOptimized Power Mode80032443908Default80031503907OpenBenchmarking.orgMegahertz, More Is BetterNeural Magic DeepSparse 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode93400759Default207470759OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 34803 Joules per run.2. Default: Approximate power consumption of 38392 Joules per run.
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault70140210280350Min: 391.04 / Avg: 392.45 / Max: 393.25Min: 393.65 / Avg: 397.77 / Max: 404.81

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault4080120160200SE +/- 0.33, N = 3SE +/- 1.36, N = 3162.59160.41
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault306090120150Min: 162.03 / Avg: 162.59 / Max: 163.18Min: 157.74 / Avg: 160.41 / Max: 162.25

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression SpeedOptimized Power ModeDefault30060090012001500SE +/- 2.17, N = 3SE +/- 16.60, N = 31094.21183.81. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s Per Watt, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression SpeedOptimized Power ModeDefault1.30192.60383.90575.20766.50955.7864.121
MinAvgMaxOptimized Power Mode80038883906Default80038363907OpenBenchmarking.orgMegahertz, More Is BetterZstd Compression 1.5.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode182.1189.1202.2Default199.4287.2314.9OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4CPU Power Consumption Monitor801602403204001. Optimized Power Mode: Approximate power consumption of 16515 Joules per run.2. Default: Approximate power consumption of 23075 Joules per run.
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression SpeedOptimized Power ModeDefault2004006008001000Min: 1091.5 / Avg: 1094.2 / Max: 1098.5Min: 1150.6 / Avg: 1183.8 / Max: 1200.61. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression SpeedOptimized Power ModeDefault3691215SE +/- 0.01, N = 3SE +/- 0.02, N = 38.569.901. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression SpeedOptimized Power ModeDefault3691215Min: 8.55 / Avg: 8.56 / Max: 8.57Min: 9.87 / Avg: 9.9 / Max: 9.941. (CC) gcc options: -O3 -pthread -lz -llzma

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: defconfigOptimized Power ModeDefault612182430SE +/- 0.18, N = 11SE +/- 0.21, N = 824.4823.76
MinAvgMaxOptimized Power Mode80034913908Default80034543911OpenBenchmarking.orgMegahertz, More Is BetterTimed Linux Kernel Compilation 6.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode90320761Default104388760OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.1CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 10383 Joules per run.2. Default: Approximate power consumption of 12304 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigOptimized Power ModeDefault612182430Min: 24.12 / Avg: 24.48 / Max: 26.19Min: 23.38 / Avg: 23.76 / Max: 25.18

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 1000Optimized Power ModeDefault50K100K150K200K250KSE +/- 72.63, N = 2SE +/- 397.04, N = 3184861.99243384.191. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.23.2Connections: 1000Optimized Power ModeDefault90180270360450395.64389.82
MinAvgMaxOptimized Power Mode80029663907Default80028693905OpenBenchmarking.orgMegahertz, More Is Betternginx 1.23.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode183467530Default207624666OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 48360 Joules per run.2. Default: Approximate power consumption of 60771 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 1000Optimized Power ModeDefault40K80K120K160K200KMin: 184789.35 / Avg: 184861.99 / Max: 184934.62Min: 242942.63 / Avg: 243384.19 / Max: 244176.541. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression SpeedOptimized Power ModeDefault30060090012001500SE +/- 2.93, N = 3SE +/- 1.19, N = 31044.61173.51. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s Per Watt, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression SpeedOptimized Power ModeDefault1.19682.39363.59044.78725.9845.3193.953
MinAvgMaxOptimized Power Mode80038603907Default80038813905OpenBenchmarking.orgMegahertz, More Is BetterZstd Compression 1.5.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode98.9196.4223.8Default164.0296.9335.4OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4CPU Power Consumption Monitor801602403204001. Optimized Power Mode: Approximate power consumption of 15253 Joules per run.2. Default: Approximate power consumption of 21176 Joules per run.
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression SpeedOptimized Power ModeDefault2004006008001000Min: 1041.1 / Avg: 1044.57 / Max: 1050.4Min: 1171.3 / Avg: 1173.47 / Max: 1175.41. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression SpeedOptimized Power ModeDefault510152025SE +/- 0.19, N = 3SE +/- 0.06, N = 316.219.11. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression SpeedOptimized Power ModeDefault510152025Min: 15.8 / Avg: 16.17 / Max: 16.4Min: 19 / Avg: 19.1 / Max: 19.21. (CC) gcc options: -O3 -pthread -lz -llzma

Xmrig

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

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MOptimized Power ModeDefault4K8K12K16K20KSE +/- 22.03, N = 3SE +/- 67.39, N = 313832.416522.51. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MOptimized Power ModeDefault61218243027.3225.21
MinAvgMaxOptimized Power Mode80029393904Default80029383905OpenBenchmarking.orgMegahertz, More Is BetterXmrig 6.21CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode175506548Default204655739OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 40005 Joules per run.2. Default: Approximate power consumption of 43914 Joules per run.
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MOptimized Power ModeDefault3K6K9K12K15KMin: 13788.9 / Avg: 13832.4 / Max: 13860.2Min: 16450.6 / Avg: 16522.53 / Max: 16657.21. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-50Optimized Power ModeDefault1020304050SE +/- 0.39, N = 3SE +/- 0.55, N = 432.8343.91MIN: 15.85 / MAX: 36.48MIN: 17.29 / MAX: 46.23
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-50Optimized Power ModeDefault0.01910.03820.05730.07640.09550.0820.085
MinAvgMaxOptimized Power Mode80030083905Default80029803907OpenBenchmarking.orgMegahertz, More Is BetterPyTorch 2.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode181.0398.9479.9Default207.1519.2581.2OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.1CPU Power Consumption Monitor1603204806408001. Optimized Power Mode: Approximate power consumption of 28718 Joules per run.2. Default: Approximate power consumption of 28427 Joules per run.
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-50Optimized Power ModeDefault918273645Min: 32.34 / Avg: 32.83 / Max: 33.6Min: 42.3 / Avg: 43.91 / Max: 44.79

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50Optimized Power ModeDefault1020304050SE +/- 0.02, N = 3SE +/- 0.51, N = 431.5844.58MIN: 14.91 / MAX: 34.67MIN: 19.44 / MAX: 46.72
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50Optimized Power ModeDefault0.01910.03820.05730.07640.09550.0790.085
MinAvgMaxOptimized Power Mode80029433906Default80029513908OpenBenchmarking.orgMegahertz, More Is BetterPyTorch 2.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode181.1397.8477.5Default207.1523.6583.9OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.1CPU Power Consumption Monitor1603204806408001. Optimized Power Mode: Approximate power consumption of 29038 Joules per run.2. Default: Approximate power consumption of 28277 Joules per run.
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50Optimized Power ModeDefault918273645Min: 31.55 / Avg: 31.58 / Max: 31.63Min: 43.51 / Avg: 44.58 / Max: 45.91

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: Face Detection FP16-INT8 - Device: CPUOptimized Power ModeDefault50100150200250SE +/- 0.55, N = 3SE +/- 0.35, N = 3237.36236.70MIN: 160.6 / MAX: 286.17MIN: 157.14 / MAX: 268.191. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxOptimized Power Mode80027923907Default80027063904OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2023.2.devCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode182615731Default207635764OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 44702 Joules per run.2. Default: Approximate power consumption of 45280 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUOptimized Power ModeDefault4080120160200Min: 236.27 / Avg: 237.36 / Max: 237.93Min: 236.15 / Avg: 236.7 / Max: 237.361. (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-INT8 - Device: CPUOptimized Power ModeDefault120240360480600SE +/- 1.35, N = 3SE +/- 0.65, N = 3538.20539.691. (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-INT8 - Device: CPUOptimized Power ModeDefault100200300400500Min: 536.78 / Avg: 538.2 / Max: 540.9Min: 538.48 / Avg: 539.69 / Max: 540.711. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100Optimized Power ModeDefault700K1400K2100K2800K3500KSE +/- 42725.42, N = 3SE +/- 25091.90, N = 33274425.323441439.711. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100Optimized Power ModeDefault150030004500600075006801.696692.76
MinAvgMaxOptimized Power Mode80029083905Default80028913910OpenBenchmarking.orgMegahertz, More Is BetterMemcached 1.6.19CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode183.2481.4564.7Default206.7514.2607.5OpenBenchmarking.orgWatts, Fewer Is BetterMemcached 1.6.19CPU Power Consumption Monitor1603204806408001. Optimized Power Mode: Approximate power consumption of 33859 Joules per run.2. Default: Approximate power consumption of 35994 Joules per run.
OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100Optimized Power ModeDefault600K1200K1800K2400K3000KMin: 3191357.02 / Avg: 3274425.32 / Max: 3333312.49Min: 3407736.01 / Avg: 3441439.71 / Max: 3490491.811. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

VVenC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FasterOptimized Power ModeDefault3691215SE +/- 0.072, N = 3SE +/- 0.081, N = 39.09610.8361. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FasterOptimized Power ModeDefault0.0070.0140.0210.0280.0350.0310.027
MinAvgMaxOptimized Power Mode80038153907Default80038613907OpenBenchmarking.orgMegahertz, More Is BetterVVenC 1.9CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode135.6296.9410.2Default207.0407.8523.1OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.9CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 22664 Joules per run.2. Default: Approximate power consumption of 26505 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FasterOptimized Power ModeDefault3691215Min: 8.96 / Avg: 9.1 / Max: 9.19Min: 10.68 / Avg: 10.84 / Max: 10.951. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

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: CPUOptimized Power ModeDefault3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 312.5512.51MIN: 10.77 / MAX: 42.91MIN: 10.84 / MAX: 42.361. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxOptimized Power Mode80025623921Default80024923908OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2023.2.devCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode179628762Default207644768OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 43928 Joules per run.2. Default: Approximate power consumption of 44425 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUOptimized Power ModeDefault48121620Min: 12.54 / Avg: 12.55 / Max: 12.56Min: 12.5 / Avg: 12.51 / Max: 12.531. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUOptimized Power ModeDefault2K4K6K8K10KSE +/- 6.61, N = 3SE +/- 7.22, N = 310168.0610205.611. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUOptimized Power ModeDefault2K4K6K8K10KMin: 10157.98 / Avg: 10168.06 / Max: 10180.52Min: 10191.24 / Avg: 10205.61 / Max: 10213.941. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUOptimized Power ModeDefault1224364860SE +/- 0.16, N = 3SE +/- 0.08, N = 353.4553.51MIN: 45.01 / MAX: 111.52MIN: 43.94 / MAX: 101.681. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxOptimized Power Mode80025553906Default80025283908OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2023.2.devCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode178636758Default207648756OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 43443 Joules per run.2. Default: Approximate power consumption of 44067 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUOptimized Power ModeDefault1122334455Min: 53.15 / Avg: 53.45 / Max: 53.68Min: 53.38 / Avg: 53.51 / Max: 53.641. (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-INT8 - Device: CPUOptimized Power ModeDefault5001000150020002500SE +/- 7.16, N = 3SE +/- 3.42, N = 32392.382390.251. (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-INT8 - Device: CPUOptimized Power ModeDefault400800120016002000Min: 2381.08 / Avg: 2392.38 / Max: 2405.65Min: 2384.38 / Avg: 2390.25 / Max: 2396.241. (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: CPUOptimized Power ModeDefault1020304050SE +/- 0.05, N = 3SE +/- 0.04, N = 342.5942.72MIN: 32.12 / MAX: 128.96MIN: 31.92 / MAX: 84.11. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxOptimized Power Mode80028643906Default80026013905OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2023.2.devCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode181634803Default207650802OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 42470 Joules per run.2. Default: Approximate power consumption of 43580 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUOptimized Power ModeDefault918273645Min: 42.5 / Avg: 42.59 / Max: 42.68Min: 42.65 / Avg: 42.72 / Max: 42.791. (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: CPUOptimized Power ModeDefault160320480640800SE +/- 0.90, N = 3SE +/- 0.71, N = 3750.43748.101. (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: CPUOptimized Power ModeDefault130260390520650Min: 748.76 / Avg: 750.43 / Max: 751.85Min: 746.9 / Avg: 748.1 / Max: 749.351. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUOptimized Power ModeDefault48121620SE +/- 0.01, N = 3SE +/- 0.01, N = 314.3014.32MIN: 12.18 / MAX: 47.3MIN: 12.39 / MAX: 39.161. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxOptimized Power Mode80024083907Default80024383911OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2023.2.devCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode178650760Default206658763OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 43323 Joules per run.2. Default: Approximate power consumption of 43415 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUOptimized Power ModeDefault48121620Min: 14.29 / Avg: 14.3 / Max: 14.31Min: 14.3 / Avg: 14.32 / Max: 14.331. (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: CPUOptimized Power ModeDefault2K4K6K8K10KSE +/- 4.32, N = 3SE +/- 5.30, N = 38943.888930.001. (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: CPUOptimized Power ModeDefault16003200480064008000Min: 8935.41 / Avg: 8943.88 / Max: 8949.6Min: 8921.1 / Avg: 8930 / Max: 8939.441. (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: CPUOptimized Power ModeDefault714212835SE +/- 0.08, N = 3SE +/- 0.23, N = 328.9928.85MIN: 22.06 / MAX: 222.83MIN: 21.11 / MAX: 222.121. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxOptimized Power Mode80029533906Default80026963904OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2023.2.devCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode179638710Default207655751OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 42740 Joules per run.2. Default: Approximate power consumption of 43422 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUOptimized Power ModeDefault612182430Min: 28.85 / Avg: 28.99 / Max: 29.11Min: 28.39 / Avg: 28.85 / Max: 29.111. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUOptimized Power ModeDefault2004006008001000SE +/- 3.05, N = 3SE +/- 9.12, N = 31100.761106.321. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUOptimized Power ModeDefault2004006008001000Min: 1096.05 / Avg: 1100.76 / Max: 1106.48Min: 1096.2 / Avg: 1106.32 / Max: 1124.511. (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 Retail FP16-INT8 - Device: CPUOptimized Power ModeDefault1.15882.31763.47644.63525.794SE +/- 0.00, N = 3SE +/- 0.01, N = 35.135.15MIN: 4.64 / MAX: 29.56MIN: 4.63 / MAX: 27.91. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxOptimized Power Mode80025043910Default80024553908OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2023.2.devCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode178648743Default207657771OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 42971 Joules per run.2. Default: Approximate power consumption of 43563 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUOptimized Power ModeDefault246810Min: 5.12 / Avg: 5.13 / Max: 5.13Min: 5.13 / Avg: 5.15 / Max: 5.161. (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-INT8 - Device: CPUOptimized Power ModeDefault5K10K15K20K25KSE +/- 6.86, N = 3SE +/- 42.09, N = 324922.4024795.171. (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-INT8 - Device: CPUOptimized Power ModeDefault4K8K12K16K20KMin: 24912.05 / Avg: 24922.4 / Max: 24935.37Min: 24737.97 / Avg: 24795.17 / Max: 24877.251. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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-ThreadedOptimized Power ModeDefault80K160K240K320K400KSE +/- 52.43, N = 3SE +/- 127.57, N = 3391468.4388447.21. (CXX) g++ options: -O3 -march=native -fPIE -pie
OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedOptimized Power ModeDefault130260390520650606.16596.03
MinAvgMaxOptimized Power Mode80027353906Default80026843904OpenBenchmarking.orgMegahertz, More Is BetterQuantLib 1.32CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode181646759Default199652758OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 42409 Joules per run.2. Default: Approximate power consumption of 43014 Joules per run.
OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedOptimized Power ModeDefault70K140K210K280K350KMin: 391379.6 / Avg: 391468.37 / Max: 391561.1Min: 388279.3 / Avg: 388447.17 / Max: 388697.51. (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.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUOptimized Power ModeDefault918273645SE +/- 0.08, N = 3SE +/- 0.08, N = 338.7938.41MIN: 36.26 / MAX: 60.12MIN: 35.95 / MAX: 58.711. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxOptimized Power Mode80029573906Default80029423912OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2023.2.devCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode179569617Default206657735OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 37366 Joules per run.2. Default: Approximate power consumption of 43114 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUOptimized Power ModeDefault816243240Min: 38.67 / Avg: 38.79 / Max: 38.94Min: 38.29 / Avg: 38.41 / Max: 38.571. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUOptimized Power ModeDefault7001400210028003500SE +/- 6.73, N = 3SE +/- 7.06, N = 33297.813330.191. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUOptimized Power ModeDefault6001200180024003000Min: 3285.15 / Avg: 3297.81 / Max: 3308.1Min: 3316.88 / Avg: 3330.19 / Max: 3340.931. (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: CPUOptimized Power ModeDefault0.09230.18460.27690.36920.4615SE +/- 0.01, N = 3SE +/- 0.00, N = 30.410.40MIN: 0.19 / MAX: 15.84MIN: 0.18 / MAX: 14.471. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxOptimized Power Mode80032583905Default80031683907OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2023.2.devCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode178.9411.8522.8Default206.6468.0594.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor1603204806408001. Optimized Power Mode: Approximate power consumption of 27319 Joules per run.2. Default: Approximate power consumption of 31045 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUOptimized Power ModeDefault12345Min: 0.4 / Avg: 0.41 / Max: 0.42Min: 0.39 / Avg: 0.4 / Max: 0.41. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUOptimized Power ModeDefault30K60K90K120K150KSE +/- 1361.46, N = 3SE +/- 775.18, N = 3117369.55121577.551. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUOptimized Power ModeDefault20K40K60K80K100KMin: 114910.81 / Avg: 117369.55 / Max: 119612.18Min: 120668.78 / Avg: 121577.55 / Max: 123119.741. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUOptimized Power ModeDefault0.55131.10261.65392.20522.7565SE +/- 0.00, N = 3SE +/- 0.01, N = 32.422.45MIN: 1.96 / MAX: 28.3MIN: 2.03 / MAX: 23.831. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxOptimized Power Mode80024073907Default80023403905OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2023.2.devCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode179650730Default206658766OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 42927 Joules per run.2. Default: Approximate power consumption of 43207 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUOptimized Power ModeDefault246810Min: 2.42 / Avg: 2.42 / Max: 2.42Min: 2.43 / Avg: 2.45 / Max: 2.461. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUOptimized Power ModeDefault11K22K33K44K55KSE +/- 229.19, N = 3SE +/- 490.25, N = 349494.0648795.971. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUOptimized Power ModeDefault9K18K27K36K45KMin: 49048.51 / Avg: 49494.06 / Max: 49810.11Min: 48250.28 / Avg: 48795.97 / Max: 49774.31. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: LiveOptimized Power ModeDefault306090120150SE +/- 0.79, N = 3SE +/- 1.03, N = 3118.24131.811. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: LiveOptimized Power ModeDefault0.12960.25920.38880.51840.6480.5760.439
MinAvgMaxOptimized Power Mode80038243917Default80038503920OpenBenchmarking.orgMegahertz, More Is BetterFFmpeg 6.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode129.0205.4267.0Default198.9300.2361.3OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor1002003004005001. Optimized Power Mode: Approximate power consumption of 13694 Joules per run.2. Default: Approximate power consumption of 18311 Joules per run.
OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: LiveOptimized Power ModeDefault20406080100Min: 116.69 / Avg: 118.24 / Max: 119.24Min: 130.43 / Avg: 131.81 / Max: 133.841. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Apache Hadoop

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

OpenBenchmarking.orgOps per sec, More Is BetterApache Hadoop 3.3.6Operation: Create - Threads: 100 - Files: 100000Optimized Power ModeDefault12002400360048006000SE +/- 62.35, N = 3SE +/- 32.35, N = 348145490
OpenBenchmarking.orgOps per sec Per Watt, More Is BetterApache Hadoop 3.3.6Operation: Create - Threads: 100 - Files: 100000Optimized Power ModeDefault61218243025.2921.24
MinAvgMaxOptimized Power Mode80034803907Default80035723911OpenBenchmarking.orgMegahertz, More Is BetterApache Hadoop 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode93.8190.3214.7Default205.8258.4316.7OpenBenchmarking.orgWatts, Fewer Is BetterApache Hadoop 3.3.6CPU Power Consumption Monitor801602403204001. Optimized Power Mode: Approximate power consumption of 12182 Joules per run.2. Default: Approximate power consumption of 15506 Joules per run.
OpenBenchmarking.orgOps per sec, More Is BetterApache Hadoop 3.3.6Operation: Create - Threads: 100 - Files: 100000Optimized Power ModeDefault10002000300040005000Min: 4688.89 / Avg: 4813.57 / Max: 4878.29Min: 5446.03 / Avg: 5489.56 / Max: 5552.78

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault48121620SE +/- 0.01, N = 3SE +/- 0.02, N = 313.9113.95
MinAvgMaxOptimized Power Mode80029943907Default80030153909OpenBenchmarking.orgMegahertz, More Is BetterNeural Magic DeepSparse 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode176525694Default206568757OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 27995 Joules per run.2. Default: Approximate power consumption of 29519 Joules per run.
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault48121620Min: 13.89 / Avg: 13.91 / Max: 13.92Min: 13.92 / Avg: 13.95 / Max: 13.98

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault10002000300040005000SE +/- 2.64, N = 3SE +/- 6.99, N = 34590.344580.63
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault8001600240032004000Min: 4586.12 / Avg: 4590.34 / Max: 4595.19Min: 4566.76 / Avg: 4580.63 / Max: 4589.08

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault816243240SE +/- 0.01, N = 3SE +/- 0.03, N = 333.9033.64
MinAvgMaxOptimized Power Mode80029543926Default80029493905OpenBenchmarking.orgMegahertz, More Is BetterNeural Magic DeepSparse 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode174526714Default145568758OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 28045 Joules per run.2. Default: Approximate power consumption of 29515 Joules per run.
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault714212835Min: 33.88 / Avg: 33.9 / Max: 33.92Min: 33.58 / Avg: 33.64 / Max: 33.67

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault400800120016002000SE +/- 0.88, N = 3SE +/- 1.67, N = 31883.661899.22
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault30060090012001500Min: 1882.24 / Avg: 1883.66 / Max: 1885.25Min: 1897.13 / Avg: 1899.22 / Max: 1902.51

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault100200300400500SE +/- 0.42, N = 3SE +/- 0.27, N = 3461.15463.09
MinAvgMaxOptimized Power Mode80026823914Default80026163905OpenBenchmarking.orgMegahertz, More Is BetterNeural Magic DeepSparse 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode177539759Default207572759OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 28410 Joules per run.2. Default: Approximate power consumption of 29341 Joules per run.
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault80160240320400Min: 460.3 / Avg: 461.15 / Max: 461.59Min: 462.64 / Avg: 463.09 / Max: 463.56

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault306090120150SE +/- 0.12, N = 3SE +/- 0.21, N = 3138.01137.34
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault306090120150Min: 137.84 / Avg: 138.01 / Max: 138.24Min: 136.99 / Avg: 137.34 / Max: 137.71

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault100200300400500SE +/- 0.70, N = 3SE +/- 0.03, N = 3460.69462.99
MinAvgMaxOptimized Power Mode80026523911Default80025933909OpenBenchmarking.orgMegahertz, More Is BetterNeural Magic DeepSparse 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode175541760Default206571760OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 28131 Joules per run.2. Default: Approximate power consumption of 29330 Joules per run.
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault80160240320400Min: 459.91 / Avg: 460.69 / Max: 462.09Min: 462.93 / Avg: 462.99 / Max: 463.05

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault306090120150SE +/- 0.30, N = 3SE +/- 0.09, N = 3138.15137.35
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault306090120150Min: 137.58 / Avg: 138.15 / Max: 138.56Min: 137.19 / Avg: 137.35 / Max: 137.47

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 512Optimized Power ModeDefault110M220M330M440M550MSE +/- 3588947.54, N = 3SE +/- 5123258.57, N = 64914266675082450001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 512Optimized Power ModeDefault300K600K900K1200K1500K1384860.491124172.64
MinAvgMaxOptimized Power Mode80038413911Default80037743908OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode183.1354.9394.7Default206.4452.1497.1OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 12302 Joules per run.2. Default: Approximate power consumption of 15522 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 512Optimized Power ModeDefault90M180M270M360M450MMin: 487100000 / Avg: 491426666.67 / Max: 498550000Min: 497980000 / Avg: 508245000 / Max: 5317600001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 32Optimized Power ModeDefault1300M2600M3900M5200M6500MSE +/- 61606333.10, N = 6SE +/- 7150058.27, N = 3630148333361856000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 32Optimized Power ModeDefault2M4M6M8M10M10558400.849739696.86
MinAvgMaxOptimized Power Mode80029443905Default80028243908OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode183597744Default139635755OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 20391 Joules per run.2. Default: Approximate power consumption of 22017 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 32Optimized Power ModeDefault1100M2200M3300M4400M5500MMin: 6228500000 / Avg: 6301483333.33 / Max: 6609100000Min: 6178400000 / Avg: 6185600000 / Max: 61999000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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 RatingOptimized Power ModeDefault140K280K420K560K700KSE +/- 9574.07, N = 3SE +/- 4040.78, N = 36381366373111. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS Per Watt, More Is Better7-Zip Compression 22.01Test: Decompression RatingOptimized Power ModeDefault20040060080010001145.351062.10
MinAvgMaxOptimized Power Mode80030063909Default80029403908OpenBenchmarking.orgMegahertz, More Is Better7-Zip Compression 22.01CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode179557760Default205600762OpenBenchmarking.orgWatts, Fewer Is Better7-Zip Compression 22.01CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 27672 Joules per run.2. Default: Approximate power consumption of 29202 Joules per run.
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingOptimized Power ModeDefault110K220K330K440K550KMin: 620072 / Avg: 638135.67 / Max: 652669Min: 633021 / Avg: 637310.67 / Max: 6453871. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingOptimized Power ModeDefault150K300K450K600K750KSE +/- 1440.87, N = 3SE +/- 869.44, N = 36544596895161. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingOptimized Power ModeDefault120K240K360K480K600KMin: 651684 / Avg: 654458.67 / Max: 656520Min: 687781 / Avg: 689516.33 / Max: 6904801. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault80160240320400SE +/- 0.05, N = 3SE +/- 0.69, N = 3346.74350.90
MinAvgMaxOptimized Power Mode80028443907Default80028753907OpenBenchmarking.orgMegahertz, More Is BetterNeural Magic DeepSparse 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode176584755Default207604750OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 27250 Joules per run.2. Default: Approximate power consumption of 27991 Joules per run.
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault60120180240300Min: 346.66 / Avg: 346.74 / Max: 346.81Min: 349.65 / Avg: 350.9 / Max: 352.02

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault4080120160200SE +/- 0.02, N = 3SE +/- 0.43, N = 3183.71182.16
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault306090120150Min: 183.68 / Avg: 183.71 / Max: 183.73Min: 181.4 / Avg: 182.16 / Max: 182.89

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault1224364860SE +/- 0.07, N = 3SE +/- 0.05, N = 351.6251.70
MinAvgMaxOptimized Power Mode80028793908Default80026303909OpenBenchmarking.orgMegahertz, More Is BetterNeural Magic DeepSparse 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode179575751Default206593760OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 26823 Joules per run.2. Default: Approximate power consumption of 27295 Joules per run.
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault1020304050Min: 51.47 / Avg: 51.62 / Max: 51.7Min: 51.6 / Avg: 51.7 / Max: 51.78

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault30060090012001500SE +/- 2.51, N = 3SE +/- 1.85, N = 31237.031235.41
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault2004006008001000Min: 1233.52 / Avg: 1237.03 / Max: 1241.89Min: 1232.46 / Avg: 1235.41 / Max: 1238.82

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastOptimized Power ModeDefault1326395265SE +/- 0.45, N = 15SE +/- 0.07, N = 549.1056.06
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastOptimized Power ModeDefault0.03020.06040.09060.12080.1510.1340.125
MinAvgMaxOptimized Power Mode80036673928Default80036343920OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode182.9366.0531.1Default199.1448.8588.6OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor1603204806408001. Optimized Power Mode: Approximate power consumption of 6027 Joules per run.2. Default: Approximate power consumption of 6821 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastOptimized Power ModeDefault1122334455Min: 47.45 / Avg: 49.1 / Max: 53.33Min: 55.85 / Avg: 56.06 / Max: 56.23

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault1.33622.67244.00865.34486.681SE +/- 0.0065, N = 3SE +/- 0.0033, N = 35.93855.6732
MinAvgMaxOptimized Power Mode80028713907Default80028513905OpenBenchmarking.orgMegahertz, More Is BetterNeural Magic DeepSparse 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode178555660Default207614755OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 24410 Joules per run.2. Default: Approximate power consumption of 26822 Joules per run.
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault246810Min: 5.93 / Avg: 5.94 / Max: 5.95Min: 5.67 / Avg: 5.67 / Max: 5.68

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault2K4K6K8K10KSE +/- 12.41, N = 3SE +/- 7.42, N = 310738.1411244.79
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault2K4K6K8K10KMin: 10721.99 / Avg: 10738.14 / Max: 10762.53Min: 11232.11 / Avg: 11244.79 / Max: 11257.82

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault816243240SE +/- 0.14, N = 3SE +/- 0.08, N = 336.1335.93
MinAvgMaxOptimized Power Mode80028403914Default80028353928Xeon Platinun 8592+80027613910OpenBenchmarking.orgMegahertz, More Is BetterNeural Magic DeepSparse 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode179603760Default207616758Xeon Platinun 8592+207612758OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 26321 Joules per run.2. Default: Approximate power consumption of 26899 Joules per run.
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault816243240Min: 35.84 / Avg: 36.13 / Max: 36.28Min: 35.8 / Avg: 35.93 / Max: 36.06

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault400800120016002000SE +/- 6.86, N = 3SE +/- 3.42, N = 31768.911778.59
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault30060090012001500Min: 1761.71 / Avg: 1768.91 / Max: 1782.63Min: 1772.46 / Avg: 1778.59 / Max: 1784.27

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault20406080100SE +/- 0.04, N = 3SE +/- 0.04, N = 376.5076.54
MinAvgMaxOptimized Power Mode80025373904Default80024553905OpenBenchmarking.orgMegahertz, More Is BetterNeural Magic DeepSparse 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode178602760Default204612758OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 26477 Joules per run.2. Default: Approximate power consumption of 26724 Joules per run.
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault1530456075Min: 76.42 / Avg: 76.5 / Max: 76.55Min: 76.46 / Avg: 76.54 / Max: 76.59

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault2004006008001000SE +/- 0.60, N = 3SE +/- 0.97, N = 3834.27834.18
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault150300450600750Min: 833.08 / Avg: 834.27 / Max: 835.01Min: 832.62 / Avg: 834.18 / Max: 835.97

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault816243240SE +/- 0.07, N = 3SE +/- 0.16, N = 335.9635.67
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault816243240Min: 35.84 / Avg: 35.96 / Max: 36.09Min: 35.39 / Avg: 35.67 / Max: 35.94

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault400800120016002000SE +/- 3.31, N = 3SE +/- 7.80, N = 31776.531791.27
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault30060090012001500Min: 1769.97 / Avg: 1776.53 / Max: 1780.66Min: 1778.57 / Avg: 1791.27 / Max: 1805.48

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault1632486480SE +/- 0.03, N = 3SE +/- 0.05, N = 373.9974.07
MinAvgMaxOptimized Power Mode80024953907Default80024443904OpenBenchmarking.orgMegahertz, More Is BetterNeural Magic DeepSparse 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode179605760Default105617759OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 26420 Joules per run.2. Default: Approximate power consumption of 26752 Joules per run.
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault1428425670Min: 73.94 / Avg: 73.99 / Max: 74.02Min: 73.98 / Avg: 74.07 / Max: 74.17

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault2004006008001000SE +/- 0.10, N = 3SE +/- 0.30, N = 3863.35862.14
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamOptimized Power ModeDefault150300450600750Min: 863.16 / Avg: 863.35 / Max: 863.5Min: 861.66 / Avg: 862.14 / Max: 862.69

VVenC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: FastOptimized Power ModeDefault510152025SE +/- 0.11, N = 3SE +/- 0.15, N = 318.0519.921. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: FastOptimized Power ModeDefault0.01510.03020.04530.06040.07550.0670.053
MinAvgMaxOptimized Power Mode80037803905Default80038483908OpenBenchmarking.orgMegahertz, More Is BetterVVenC 1.9CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode160.6269.5332.4Default206.6376.5448.9OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.9CPU Power Consumption Monitor1202403604806001. Optimized Power Mode: Approximate power consumption of 11677 Joules per run.2. Default: Approximate power consumption of 14933 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: FastOptimized Power ModeDefault510152025Min: 17.84 / Avg: 18.05 / Max: 18.16Min: 19.74 / Avg: 19.92 / Max: 20.211. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Cell Phone Drop TestOptimized Power ModeDefault612182430SE +/- 0.12, N = 3SE +/- 0.14, N = 325.3725.74
MinAvgMaxOptimized Power Mode80032403906Default80031803905OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode156477732Default200518755OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 18923 Joules per run.2. Default: Approximate power consumption of 20380 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Cell Phone Drop TestOptimized Power ModeDefault612182430Min: 25.17 / Avg: 25.37 / Max: 25.58Min: 25.51 / Avg: 25.74 / Max: 26

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Classroom - Compute: CPU-OnlyOptimized Power ModeDefault816243240SE +/- 0.07, N = 3SE +/- 0.33, N = 333.4034.94
MinAvgMaxOptimized Power Mode80026963906Default80027283905OpenBenchmarking.orgMegahertz, More Is BetterBlender 4.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode181618758Default206621735OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 23896 Joules per run.2. Default: Approximate power consumption of 24651 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Classroom - Compute: CPU-OnlyOptimized Power ModeDefault714212835Min: 33.29 / Avg: 33.4 / Max: 33.52Min: 34.6 / Avg: 34.94 / Max: 35.6

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 512Optimized Power ModeDefault500M1000M1500M2000M2500MSE +/- 1101514.11, N = 3SE +/- 2968913.01, N = 3214100000021445666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 512Optimized Power ModeDefault700K1400K2100K2800K3500K3430132.223389797.47
MinAvgMaxOptimized Power Mode80027483907Default80026103904OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode181624755Default196633756OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 21846 Joules per run.2. Default: Approximate power consumption of 22143 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 512Optimized Power ModeDefault400M800M1200M1600M2000MMin: 2139800000 / Avg: 2141000000 / Max: 2143200000Min: 2141400000 / Avg: 2144566666.67 / Max: 21505000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Apache HTTP Server

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

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 1000Optimized Power ModeDefault20K40K60K80K100K76315.6580826.711. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 1000Optimized Power ModeDefault60120180240300262.58208.91
MinAvgMaxOptimized Power Mode80028633903Default80029533906OpenBenchmarking.orgMegahertz, More Is BetterApache HTTP Server 2.4.56CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode99.1290.6333.6Default195.5386.9451.6OpenBenchmarking.orgWatts, Fewer Is BetterApache HTTP Server 2.4.56CPU Power Consumption Monitor120240360480600

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 512Optimized Power ModeDefault300M600M900M1200M1500MSE +/- 13505101.92, N = 3SE +/- 4762352.36, N = 3151346666714739000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 512Optimized Power ModeDefault500K1000K1500K2000K2500K2561825.812318859.55
MinAvgMaxOptimized Power Mode80029143906Default80029053905OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode182591679Default207636728OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 20677 Joules per run.2. Default: Approximate power consumption of 21823 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 512Optimized Power ModeDefault300M600M900M1200M1500MMin: 1491700000 / Avg: 1513466666.67 / Max: 1538200000Min: 1466700000 / Avg: 1473900000 / Max: 14829000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 512Optimized Power ModeDefault200M400M600M800M1000MSE +/- 5205466.14, N = 3SE +/- 10474795.68, N = 399966333310123366671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 512Optimized Power ModeDefault400K800K1200K1600K2000K1823904.251627411.29
MinAvgMaxOptimized Power Mode80037973906Default80037323907OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode181548629Default200622737OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 19183 Joules per run.2. Default: Approximate power consumption of 21565 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 512Optimized Power ModeDefault200M400M600M800M1000MMin: 993420000 / Avg: 999663333.33 / Max: 1010000000Min: 992410000 / Avg: 1012336666.67 / Max: 10279000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 57Optimized Power ModeDefault1200M2400M3600M4800M6000MSE +/- 19835069.95, N = 3SE +/- 11767044.38, N = 3565660000058355000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 57Optimized Power ModeDefault2M4M6M8M10M9209885.669120590.64
MinAvgMaxOptimized Power Mode80029313904Default80025893900OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode187614691Default196640754OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 21087 Joules per run.2. Default: Approximate power consumption of 21967 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 57Optimized Power ModeDefault1000M2000M3000M4000M5000MMin: 5622600000 / Avg: 5656600000 / Max: 5691300000Min: 5815800000 / Avg: 5835500000 / Max: 58565000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 57Optimized Power ModeDefault900M1800M2700M3600M4500MSE +/- 34188302.09, N = 3SE +/- 11478143.48, N = 3412500000043298666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 57Optimized Power ModeDefault1.5M3M4.5M6M7.5M7072857.526804882.12
MinAvgMaxOptimized Power Mode80028633903Default80029563904OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode183583669Default201636742OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 20218 Joules per run.2. Default: Approximate power consumption of 22058 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 57Optimized Power ModeDefault800M1600M2400M3200M4000MMin: 4061200000 / Avg: 4125000000 / Max: 4178200000Min: 4307100000 / Avg: 4329866666.67 / Max: 43438000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 32Optimized Power ModeDefault800M1600M2400M3200M4000MSE +/- 3883440.63, N = 3SE +/- 1386041.53, N = 3374523333336118666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 32Optimized Power ModeDefault1.5M3M4.5M6M7.5M7101447.976080886.75
MinAvgMaxOptimized Power Mode80029313903Default80028973906OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode181527585Default207594674OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 18107 Joules per run.2. Default: Approximate power consumption of 20393 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 32Optimized Power ModeDefault600M1200M1800M2400M3000MMin: 3738000000 / Avg: 3745233333.33 / Max: 3751300000Min: 3609100000 / Avg: 3611866666.67 / Max: 36134000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 32Optimized Power ModeDefault500M1000M1500M2000M2500MSE +/- 13974301.81, N = 3SE +/- 6835284.27, N = 3246086666724760333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 32Optimized Power ModeDefault1.1M2.2M3.3M4.4M5.5M5140098.564283633.39
MinAvgMaxOptimized Power Mode80037453905Default80036863907OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode184479543Default194578650OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 16597 Joules per run.2. Default: Approximate power consumption of 19653 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 32Optimized Power ModeDefault400M800M1200M1600M2000MMin: 2446100000 / Avg: 2460866666.67 / Max: 2488800000Min: 2465600000 / Avg: 2476033333.33 / Max: 24889000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 32Optimized Power ModeDefault300M600M900M1200M1500MSE +/- 1193035.34, N = 3SE +/- 1273228.62, N = 3120450000012117666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 32Optimized Power ModeDefault800K1600K2400K3200K4000K3778050.232919266.29
MinAvgMaxOptimized Power Mode80038603906Default80037593905OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode184.1318.8341.0Default206.5415.1447.6OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor1202403604806001. Optimized Power Mode: Approximate power consumption of 10946 Joules per run.2. Default: Approximate power consumption of 14390 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 32Optimized Power ModeDefault200M400M600M800M1000MMin: 1202200000 / Avg: 1204500000 / Max: 1206200000Min: 1209900000 / Avg: 1211766666.67 / Max: 12142000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 57Optimized Power ModeDefault300M600M900M1200M1500MSE +/- 16392511.84, N = 3SE +/- 9950041.88, N = 3129333333314291000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 57Optimized Power ModeDefault800K1600K2400K3200K4000K3765376.513194605.47
MinAvgMaxOptimized Power Mode80037763906Default80036073906OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode184.2343.5374.7Default207.2447.3490.6OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 11907 Joules per run.2. Default: Approximate power consumption of 15508 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 57Optimized Power ModeDefault200M400M600M800M1000MMin: 1262500000 / Avg: 1293333333.33 / Max: 1318400000Min: 1410600000 / Avg: 1429100000 / Max: 14447000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

VVenC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: FasterOptimized Power ModeDefault714212835SE +/- 0.30, N = 4SE +/- 0.36, N = 328.9332.091. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: FasterOptimized Power ModeDefault0.02590.05180.07770.10360.12950.1150.092
MinAvgMaxOptimized Power Mode80037233906Default80036463910OpenBenchmarking.orgMegahertz, More Is BetterVVenC 1.9CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode182.4250.7297.9Default206.9349.1415.3OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.9CPU Power Consumption Monitor1102203304405501. Optimized Power Mode: Approximate power consumption of 7645 Joules per run.2. Default: Approximate power consumption of 10009 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: FasterOptimized Power ModeDefault714212835Min: 28.35 / Avg: 28.93 / Max: 29.77Min: 31.47 / Avg: 32.09 / Max: 32.711. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4KOptimized Power ModeDefault246810SE +/- 0.006, N = 3SE +/- 0.098, N = 36.6457.2971. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4KOptimized Power ModeDefault0.00560.01120.01680.02240.0280.0250.020
MinAvgMaxOptimized Power Mode80037443915Default80037303906OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 1.8CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode178.5264.7423.6Default198.8363.8531.7OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 8735 Joules per run.2. Default: Approximate power consumption of 11035 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4KOptimized Power ModeDefault3691215Min: 6.64 / Avg: 6.65 / Max: 6.66Min: 7.12 / Avg: 7.3 / Max: 7.461. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Redis

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

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 50Optimized Power ModeDefault700K1400K2100K2800K3500KSE +/- 1584.15, N = 3SE +/- 12726.60, N = 33050498.003060186.421. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 50Optimized Power ModeDefault4K8K12K16K20K16432.1811959.07
MinAvgMaxOptimized Power Mode80036253904Default80035543904OpenBenchmarking.orgMegahertz, More Is BetterRedis 7.0.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode183.2185.6189.5Default206.7255.9290.9OpenBenchmarking.orgWatts, Fewer Is BetterRedis 7.0.4CPU Power Consumption Monitor701402102803501. Optimized Power Mode: Approximate power consumption of 4950 Joules per run.2. Default: Approximate power consumption of 6909 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 50Optimized Power ModeDefault500K1000K1500K2000K2500KMin: 3047348.5 / Avg: 3050498 / Max: 3052371.25Min: 3034771.5 / Avg: 3060186.42 / Max: 3074102.251. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: SlowOptimized Power ModeDefault612182430SE +/- 0.08, N = 3SE +/- 0.08, N = 326.7127.20
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: SlowOptimized Power ModeDefault0.01150.0230.03450.0460.05750.0510.048
MinAvgMaxOptimized Power Mode80037753908Default80037283908OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode184520693Default207567719OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 14226 Joules per run.2. Default: Approximate power consumption of 15112 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: SlowOptimized Power ModeDefault612182430Min: 26.62 / Avg: 26.71 / Max: 26.86Min: 27.09 / Avg: 27.2 / Max: 27.36

Redis

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

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 500Optimized Power ModeDefault700K1400K2100K2800K3500KSE +/- 36270.68, N = 3SE +/- 482.98, N = 33152359.753240001.581. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 500Optimized Power ModeDefault2K4K6K8K10K10408.059025.17
MinAvgMaxOptimized Power Mode80033323903Default80032493907OpenBenchmarking.orgMegahertz, More Is BetterRedis 7.0.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode184.3302.9456.0Default206.6359.0511.5OpenBenchmarking.orgWatts, Fewer Is BetterRedis 7.0.4CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 8178 Joules per run.2. Default: Approximate power consumption of 9573 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 500Optimized Power ModeDefault600K1200K1800K2400K3000KMin: 3080011 / Avg: 3152359.75 / Max: 3193109Min: 3239239.25 / Avg: 3240001.58 / Max: 3240896.51. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

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-ThreadedOptimized Power ModeDefault8001600240032004000SE +/- 2.92, N = 3SE +/- 1.44, N = 33641.43650.51. (CXX) g++ options: -O3 -march=native -fPIE -pie
OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterQuantLib 1.32Configuration: Single-ThreadedOptimized Power ModeDefault51015202520.0018.03
MinAvgMaxOptimized Power Mode80037833903Default80036653905OpenBenchmarking.orgMegahertz, More Is BetterQuantLib 1.32CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode179.2182.1191.9Default195.7202.5274.3OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32CPU Power Consumption Monitor701402102803501. Optimized Power Mode: Approximate power consumption of 4795 Joules per run.2. Default: Approximate power consumption of 5332 Joules per run.
OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Single-ThreadedOptimized Power ModeDefault6001200180024003000Min: 3635.6 / Avg: 3641.43 / Max: 3644.7Min: 3647.7 / Avg: 3650.5 / Max: 3652.51. (CXX) g++ options: -O3 -march=native -fPIE -pie

Xmrig

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

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Wownero - Hash Count: 1MOptimized Power ModeDefault16K32K48K64K80KSE +/- 24.14, N = 4SE +/- 677.05, N = 475701.775002.31. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: Wownero - Hash Count: 1MOptimized Power ModeDefault306090120150141.96134.73
MinAvgMaxOptimized Power Mode80029003904Default80028903908OpenBenchmarking.orgMegahertz, More Is BetterXmrig 6.21CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode185533759Default207557766OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 10799 Joules per run.2. Default: Approximate power consumption of 10995 Joules per run.
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Wownero - Hash Count: 1MOptimized Power ModeDefault13K26K39K52K65KMin: 75648.7 / Avg: 75701.7 / Max: 75757.6Min: 72971.4 / Avg: 75002.28 / Max: 75700.21. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Redis

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

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 50Optimized Power ModeDefault1000K2000K3000K4000K5000KSE +/- 1281.58, N = 3SE +/- 8167.04, N = 43811819.504744838.901. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 50Optimized Power ModeDefault4K8K12K16K20K20690.4118984.61
MinAvgMaxOptimized Power Mode80037563906Default80037063905OpenBenchmarking.orgMegahertz, More Is BetterRedis 7.0.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode94.4184.2188.8Default206.0249.9290.9OpenBenchmarking.orgWatts, Fewer Is BetterRedis 7.0.4CPU Power Consumption Monitor701402102803501. Optimized Power Mode: Approximate power consumption of 4422 Joules per run.2. Default: Approximate power consumption of 5249 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 50Optimized Power ModeDefault800K1600K2400K3200K4000KMin: 3809882.5 / Avg: 3811819.5 / Max: 3814241.75Min: 4723750 / Avg: 4744838.88 / Max: 47624111. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

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 TimeOptimized Power ModeDefault61218243023.3523.471. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
MinAvgMaxOptimized Power Mode280031213907Default80030673910OpenBenchmarking.orgMegahertz, More Is BetterOpenFOAM 10CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode169556717Default206590755OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh TimeOptimized Power ModeDefault71421283527.7130.041. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4KOptimized Power ModeDefault50100150200250SE +/- 1.56, N = 9SE +/- 1.12, N = 5199.55218.761. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4KOptimized Power ModeDefault0.20180.40360.60540.80721.0090.8970.820
MinAvgMaxOptimized Power Mode80034963921Default80034593919OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 1.8CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode94.9222.4429.6Default188.4266.9496.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 2891 Joules per run.2. Default: Approximate power consumption of 3363 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4KOptimized Power ModeDefault4080120160200Min: 192.99 / Avg: 199.55 / Max: 210.29Min: 215.42 / Avg: 218.76 / Max: 222.011. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumOptimized Power ModeDefault714212835SE +/- 0.19, N = 3SE +/- 0.08, N = 329.6229.79
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumOptimized Power ModeDefault0.01310.02620.03930.05240.06550.0580.054
MinAvgMaxOptimized Power Mode80037523917Default80035853904OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode185513661Default201556727OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 12827 Joules per run.2. Default: Approximate power consumption of 13893 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumOptimized Power ModeDefault714212835Min: 29.42 / Avg: 29.62 / Max: 29.99Min: 29.66 / Avg: 29.79 / Max: 29.92

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Super FastOptimized Power ModeDefault306090120150SE +/- 1.05, N = 15SE +/- 1.01, N = 15145.75158.23
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Super FastOptimized Power ModeDefault0.12310.24620.36930.49240.61550.5470.526
MinAvgMaxOptimized Power Mode80033043923Default80033433917OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode94.6266.6405.6Default195.4300.9474.5OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor1202403604806001. Optimized Power Mode: Approximate power consumption of 2221 Joules per run.2. Default: Approximate power consumption of 2387 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Super FastOptimized Power ModeDefault306090120150Min: 140.33 / Avg: 145.75 / Max: 151.79Min: 149.36 / Avg: 158.23 / Max: 164.54

Xmrig

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

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Femto UPX2 - Hash Count: 1MOptimized Power ModeDefault15K30K45K60K75KSE +/- 443.65, N = 3SE +/- 844.15, N = 469847.969677.81. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: CryptoNight-Femto UPX2 - Hash Count: 1MOptimized Power ModeDefault306090120150130.14123.55
MinAvgMaxOptimized Power Mode80029233903Default80028623904OpenBenchmarking.orgMegahertz, More Is BetterXmrig 6.21CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode187537759Default204564759OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 11450 Joules per run.2. Default: Approximate power consumption of 11843 Joules per run.
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Femto UPX2 - Hash Count: 1MOptimized Power ModeDefault12K24K36K48K60KMin: 68960.8 / Avg: 69847.87 / Max: 70308.7Min: 67163.7 / Avg: 69677.8 / Max: 70676.41. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: SlowOptimized Power ModeDefault918273645SE +/- 0.06, N = 4SE +/- 0.06, N = 441.1341.451. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: SlowOptimized Power ModeDefault0.01820.03640.05460.07280.0910.0810.077
MinAvgMaxOptimized Power Mode80038163907Default80036893920OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode188506639Default200536673OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 9605 Joules per run.2. Default: Approximate power consumption of 10316 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: SlowOptimized Power ModeDefault918273645Min: 40.97 / Avg: 41.13 / Max: 41.23Min: 41.3 / Avg: 41.45 / Max: 41.571. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Xmrig

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

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: KawPow - Hash Count: 1MOptimized Power ModeDefault15K30K45K60K75KSE +/- 943.50, N = 3SE +/- 82.14, N = 469196.770383.21. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: KawPow - Hash Count: 1MOptimized Power ModeDefault306090120150128.19125.63
MinAvgMaxOptimized Power Mode80026733906Default80027523908OpenBenchmarking.orgMegahertz, More Is BetterXmrig 6.21CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode185540759Default200560759OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 11696 Joules per run.2. Default: Approximate power consumption of 11625 Joules per run.
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: KawPow - Hash Count: 1MOptimized Power ModeDefault12K24K36K48K60KMin: 67317.4 / Avg: 69196.7 / Max: 70283.9Min: 70180.4 / Avg: 70383.2 / Max: 70561.71. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Monero - Hash Count: 1MOptimized Power ModeDefault15K30K45K60K75KSE +/- 41.44, N = 3SE +/- 27.69, N = 470298.870469.81. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: Monero - Hash Count: 1MOptimized Power ModeDefault306090120150130.23125.59
MinAvgMaxOptimized Power Mode80029143906Default80026983904OpenBenchmarking.orgMegahertz, More Is BetterXmrig 6.21CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode183540759Default207561759OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 11516 Joules per run.2. Default: Approximate power consumption of 11363 Joules per run.
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Monero - Hash Count: 1MOptimized Power ModeDefault12K24K36K48K60KMin: 70229.7 / Avg: 70298.83 / Max: 70373Min: 70407.7 / Avg: 70469.75 / Max: 70541.81. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Heavy - Hash Count: 1MOptimized Power ModeDefault15K30K45K60K75KSE +/- 96.69, N = 3SE +/- 49.63, N = 470338.670573.01. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: CryptoNight-Heavy - Hash Count: 1MOptimized Power ModeDefault306090120150131.15126.16
MinAvgMaxOptimized Power Mode80028253905Default80028103906OpenBenchmarking.orgMegahertz, More Is BetterXmrig 6.21CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode182536759Default205559759OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 11263 Joules per run.2. Default: Approximate power consumption of 11607 Joules per run.
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Heavy - Hash Count: 1MOptimized Power ModeDefault12K24K36K48K60KMin: 70234.6 / Avg: 70338.6 / Max: 70531.8Min: 70467.2 / Avg: 70573 / Max: 70686.41. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumOptimized Power ModeDefault1020304050SE +/- 0.05, N = 4SE +/- 0.06, N = 441.6941.991. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumOptimized Power ModeDefault0.01890.03780.05670.07560.09450.0840.078
MinAvgMaxOptimized Power Mode80038143928Default80036883907OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode188494633Default203537704OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 9386 Joules per run.2. Default: Approximate power consumption of 10077 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumOptimized Power ModeDefault918273645Min: 41.6 / Avg: 41.69 / Max: 41.83Min: 41.91 / Avg: 41.99 / Max: 42.181. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: CPU-OnlyOptimized Power ModeDefault3691215SE +/- 0.04, N = 4SE +/- 0.03, N = 412.6712.89
MinAvgMaxOptimized Power Mode80029573909Default80028183905OpenBenchmarking.orgMegahertz, More Is BetterBlender 4.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode181539759Default207550738OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 9565 Joules per run.2. Default: Approximate power consumption of 9768 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: CPU-OnlyOptimized Power ModeDefault48121620Min: 12.61 / Avg: 12.67 / Max: 12.77Min: 12.81 / Avg: 12.89 / Max: 12.95

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 1080pOptimized Power ModeDefault510152025SE +/- 0.11, N = 5SE +/- 0.16, N = 519.6720.951. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 1080pOptimized Power ModeDefault0.01940.03880.05820.07760.0970.0860.068
MinAvgMaxOptimized Power Mode80036153905Default80035513907OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 1.8CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode179.0229.9287.8Default188.7309.8398.3OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor1102203304405501. Optimized Power Mode: Approximate power consumption of 3494 Joules per run.2. Default: Approximate power consumption of 4337 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 1080pOptimized Power ModeDefault510152025Min: 19.32 / Avg: 19.67 / Max: 19.92Min: 20.35 / Avg: 20.95 / Max: 21.321. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastOptimized Power ModeDefault1326395265SE +/- 0.48, N = 4SE +/- 0.15, N = 550.6857.87
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastOptimized Power ModeDefault0.03240.06480.09720.12960.1620.1440.131
MinAvgMaxOptimized Power Mode80036603923Default80037193916OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode188.7351.0476.3Default206.2440.6569.5OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor1402804205607001. Optimized Power Mode: Approximate power consumption of 5704 Joules per run.2. Default: Approximate power consumption of 6521 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastOptimized Power ModeDefault1122334455Min: 49.52 / Avg: 50.68 / Max: 51.87Min: 57.46 / Avg: 57.87 / Max: 58.2

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastOptimized Power ModeDefault1326395265SE +/- 0.21, N = 4SE +/- 0.37, N = 550.3659.59
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastOptimized Power ModeDefault0.03580.07160.10740.14320.1790.1590.145
MinAvgMaxOptimized Power Mode80037063922Default80035093921OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode183.0316.8389.0Default207.2411.1535.8OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor1402804205607001. Optimized Power Mode: Approximate power consumption of 5306 Joules per run.2. Default: Approximate power consumption of 6002 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastOptimized Power ModeDefault1224364860Min: 49.76 / Avg: 50.36 / Max: 50.75Min: 58.36 / Avg: 59.59 / Max: 60.54

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra FastOptimized Power ModeDefault20406080100SE +/- 0.70, N = 6SE +/- 0.23, N = 670.8777.531. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra FastOptimized Power ModeDefault0.05240.10480.15720.20960.2620.2330.213
MinAvgMaxOptimized Power Mode80036113914Default80034253909OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode187.6303.7417.2Default195.7364.2476.1OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor1202403604806001. Optimized Power Mode: Approximate power consumption of 3897 Joules per run.2. Default: Approximate power consumption of 4431 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra FastOptimized Power ModeDefault1530456075Min: 68.39 / Avg: 70.87 / Max: 72.57Min: 76.84 / Avg: 77.53 / Max: 78.091. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4KOptimized Power ModeDefault1530456075SE +/- 0.56, N = 4SE +/- 0.39, N = 461.9169.471. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4KOptimized Power ModeDefault0.05060.10120.15180.20240.2530.2250.192
MinAvgMaxOptimized Power Mode80035363907Default80038443916OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 1.8CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode178.6275.5394.3Default207.4361.1517.2OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 4683 Joules per run.2. Default: Approximate power consumption of 5778 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4KOptimized Power ModeDefault1326395265Min: 60.44 / Avg: 61.91 / Max: 63.13Min: 68.72 / Avg: 69.47 / Max: 70.551. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4KOptimized Power ModeDefault50100150200250SE +/- 2.06, N = 5SE +/- 0.90, N = 6198.74218.451. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4KOptimized Power ModeDefault0.20180.40360.60540.80721.0090.8970.808
MinAvgMaxOptimized Power Mode80037003906Default80036093920OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 1.8CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode178.4221.4396.1Default194.7270.4503.0OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 2967 Joules per run.2. Default: Approximate power consumption of 3380 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4KOptimized Power ModeDefault4080120160200Min: 195 / Avg: 198.74 / Max: 206.71Min: 214.86 / Avg: 218.45 / Max: 221.081. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Ultra FastOptimized Power ModeDefault4080120160200SE +/- 1.12, N = 15SE +/- 1.12, N = 9153.17166.47
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Ultra FastOptimized Power ModeDefault0.13250.2650.39750.530.66250.5890.566
MinAvgMaxOptimized Power Mode80034123925Default80034323920OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode187.2260.1393.2Default195.5294.4446.2OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor1202403604806001. Optimized Power Mode: Approximate power consumption of 2116 Joules per run.2. Default: Approximate power consumption of 2322 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Ultra FastOptimized Power ModeDefault306090120150Min: 147.04 / Avg: 153.17 / Max: 161.05Min: 159.93 / Avg: 166.47 / Max: 170.71

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: SlowOptimized Power ModeDefault20406080100SE +/- 0.19, N = 6SE +/- 0.10, N = 678.9380.30
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: SlowOptimized Power ModeDefault0.05130.10260.15390.20520.25650.2280.208
MinAvgMaxOptimized Power Mode80035683909Default80033793909OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode188.3346.5464.1Default203.8386.0506.0OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 4158 Joules per run.2. Default: Approximate power consumption of 4568 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: SlowOptimized Power ModeDefault1530456075Min: 78.21 / Avg: 78.93 / Max: 79.43Min: 79.99 / Avg: 80.3 / Max: 80.55

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastOptimized Power ModeDefault1530456075SE +/- 0.44, N = 5SE +/- 0.26, N = 564.9769.361. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastOptimized Power ModeDefault0.03940.07880.11820.15760.1970.1750.164
MinAvgMaxOptimized Power Mode80037503911Default80038383907OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode185.0372.2523.5Default195.9424.1563.7OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor1402804205607001. Optimized Power Mode: Approximate power consumption of 5136 Joules per run.2. Default: Approximate power consumption of 5599 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastOptimized Power ModeDefault1326395265Min: 63.8 / Avg: 64.97 / Max: 66Min: 68.83 / Avg: 69.36 / Max: 70.291. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pOptimized Power ModeDefault120240360480600SE +/- 9.88, N = 15SE +/- 2.30, N = 9493.26542.981. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pOptimized Power ModeDefault0.51191.02381.53572.04762.55952.2752.003
MinAvgMaxOptimized Power Mode80036123910Default80033963909OpenBenchmarking.orgMegahertz, More Is BetterSVT-VP9 0.3CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode94.5216.8399.4Default195.4271.1486.7OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 1735 Joules per run.2. Default: Approximate power consumption of 2048 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pOptimized Power ModeDefault100200300400500Min: 356.57 / Avg: 493.26 / Max: 513.71Min: 533.41 / Avg: 542.98 / Max: 554.71. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastOptimized Power ModeDefault1632486480SE +/- 0.12, N = 5SE +/- 0.25, N = 567.2171.051. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastOptimized Power ModeDefault0.04390.08780.13170.17560.21950.1950.178
MinAvgMaxOptimized Power Mode80036033912Default80037003908OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode186.6344.9484.9Default207.0398.5519.8OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 4622 Joules per run.2. Default: Approximate power consumption of 5181 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastOptimized Power ModeDefault1428425670Min: 66.93 / Avg: 67.21 / Max: 67.63Min: 70.53 / Avg: 71.05 / Max: 71.891. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyOptimized Power ModeDefault1.0622.1243.1864.2485.31SE +/- 0.01, N = 6SE +/- 0.01, N = 64.724.53
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyOptimized Power ModeDefault0.00230.00460.00690.00920.01150.010.01
MinAvgMaxOptimized Power Mode80029613904Default80031493901OpenBenchmarking.orgMegahertz, More Is BetterIntel Open Image Denoise 2.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode183467708Default200473676OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.1CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 5368 Joules per run.2. Default: Approximate power consumption of 5519 Joules per run.
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyOptimized Power ModeDefault246810Min: 4.67 / Avg: 4.72 / Max: 4.76Min: 4.48 / Avg: 4.53 / Max: 4.55

Y-Cruncher

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.2Pi Digits To Calculate: 1BOptimized Power ModeDefault1.16982.33963.50944.67925.849SE +/- 0.009, N = 5SE +/- 0.018, N = 54.6975.199
MinAvgMaxOptimized Power Mode80032353905Default80031363912OpenBenchmarking.orgMegahertz, More Is BetterY-Cruncher 0.8.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode97361742Default207398728OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.8.2CPU Power Consumption Monitor20040060080010001. Optimized Power Mode: Approximate power consumption of 4691 Joules per run.2. Default: Approximate power consumption of 5100 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.2Pi Digits To Calculate: 1BOptimized Power ModeDefault246810Min: 4.68 / Avg: 4.7 / Max: 4.72Min: 5.16 / Avg: 5.2 / Max: 5.25

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 1080pOptimized Power ModeDefault306090120150SE +/- 0.77, N = 6SE +/- 0.36, N = 7126.70142.271. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 1080pOptimized Power ModeDefault0.12620.25240.37860.50480.6310.5610.478
MinAvgMaxOptimized Power Mode80034393938Default80035453922OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 1.8CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode178.6225.9330.4Default199.8297.7432.0OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor1102203304405501. Optimized Power Mode: Approximate power consumption of 2523 Joules per run.2. Default: Approximate power consumption of 3020 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 1080pOptimized Power ModeDefault306090120150Min: 124.68 / Avg: 126.7 / Max: 129.02Min: 140.83 / Avg: 142.27 / Max: 143.51. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: MediumOptimized Power ModeDefault20406080100SE +/- 0.25, N = 6SE +/- 0.08, N = 686.7888.46
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: MediumOptimized Power ModeDefault0.05780.11560.17340.23120.2890.2570.236
MinAvgMaxOptimized Power Mode80036543908Default80036493910OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode188.2337.9473.2Default199.5374.9505.3OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 3829 Joules per run.2. Default: Approximate power consumption of 4186 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: MediumOptimized Power ModeDefault20406080100Min: 85.6 / Avg: 86.78 / Max: 87.35Min: 88.21 / Avg: 88.46 / Max: 88.75

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: SlowOptimized Power ModeDefault306090120150SE +/- 0.35, N = 8SE +/- 0.38, N = 8125.18127.251. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: SlowOptimized Power ModeDefault0.09810.19620.29430.39240.49050.4360.360
MinAvgMaxOptimized Power Mode80033833905Default80035023906OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode142.7287.0393.6Default205.7353.2497.3OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 2619 Joules per run.2. Default: Approximate power consumption of 3179 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: SlowOptimized Power ModeDefault20406080100Min: 124.01 / Avg: 125.18 / Max: 126.67Min: 125.92 / Avg: 127.25 / Max: 128.91. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Very FastOptimized Power ModeDefault4080120160200SE +/- 1.07, N = 11SE +/- 0.74, N = 8147.08160.63
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Very FastOptimized Power ModeDefault0.12040.24080.36120.48160.6020.5350.526
MinAvgMaxOptimized Power Mode80035073923Default80032443911OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode183.2274.9402.4Default149.6305.7483.7OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor1202403604806001. Optimized Power Mode: Approximate power consumption of 2274 Joules per run.2. Default: Approximate power consumption of 2483 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Very FastOptimized Power ModeDefault306090120150Min: 141.96 / Avg: 147.08 / Max: 153.57Min: 158.38 / Avg: 160.63 / Max: 165.07

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 1080pOptimized Power ModeDefault110220330440550SE +/- 4.01, N = 15SE +/- 3.53, N = 9439.48502.711. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 1080pOptimized Power ModeDefault0.48560.97121.45681.94242.4282.1582.042
MinAvgMaxOptimized Power Mode80035773907Default80035223920OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 1.8CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode119.4203.6319.3Default195.6246.2402.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor1102203304405501. Optimized Power Mode: Approximate power consumption of 1480 Joules per run.2. Default: Approximate power consumption of 1751 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 1080pOptimized Power ModeDefault90180270360450Min: 416.15 / Avg: 439.48 / Max: 472.01Min: 484.02 / Avg: 502.71 / Max: 517.771. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: MediumOptimized Power ModeDefault306090120150SE +/- 0.58, N = 8SE +/- 0.46, N = 8130.64131.141. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: MediumOptimized Power ModeDefault0.10130.20260.30390.40520.50650.4500.372
MinAvgMaxOptimized Power Mode80034713914Default80034903908OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode184.0290.5415.7Default199.2352.8497.3OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 2579 Joules per run.2. Default: Approximate power consumption of 3131 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: MediumOptimized Power ModeDefault20406080100Min: 127.72 / Avg: 130.64 / Max: 132.64Min: 129.53 / Avg: 131.14 / Max: 133.211. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pOptimized Power ModeDefault100200300400500SE +/- 2.86, N = 8SE +/- 1.93, N = 8433.53463.271. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pOptimized Power ModeDefault0.43790.87581.31371.75162.18951.9461.666
MinAvgMaxOptimized Power Mode80035343907Default80037003921OpenBenchmarking.orgMegahertz, More Is BetterSVT-VP9 0.3CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode179.1222.8433.3Default199.6278.1500.7OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 1894 Joules per run.2. Default: Approximate power consumption of 2260 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pOptimized Power ModeDefault80160240320400Min: 422.26 / Avg: 433.53 / Max: 442.47Min: 456.28 / Avg: 463.27 / Max: 473.461. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pOptimized Power ModeDefault120240360480600SE +/- 3.72, N = 8SE +/- 4.34, N = 9502.05542.171. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pOptimized Power ModeDefault0.51461.02921.54382.05842.5732.2871.999
MinAvgMaxOptimized Power Mode80036143917Default80035753909OpenBenchmarking.orgMegahertz, More Is BetterSVT-VP9 0.3CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode178.7219.5408.7Default199.9271.3493.1OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor1302603905206501. Optimized Power Mode: Approximate power consumption of 1783 Joules per run.2. Default: Approximate power consumption of 2080 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pOptimized Power ModeDefault100200300400500Min: 481.52 / Avg: 502.05 / Max: 520.31Min: 530.7 / Avg: 542.17 / Max: 573.681. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 1080pOptimized Power ModeDefault140280420560700SE +/- 3.16, N = 10SE +/- 4.69, N = 11574.60628.761. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 1080pOptimized Power ModeDefault0.6391.2781.9172.5563.1952.842.64
MinAvgMaxOptimized Power Mode80032103922Default80032053925OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 1.8CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode177.1202.4313.6Default193.8238.2383.1OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor1002003004005001. Optimized Power Mode: Approximate power consumption of 1416 Joules per run.2. Default: Approximate power consumption of 1602 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 1080pOptimized Power ModeDefault110220330440550Min: 560.66 / Avg: 574.6 / Max: 590.69Min: 608.76 / Avg: 628.75 / Max: 657.491. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Super FastOptimized Power ModeDefault60120180240300SE +/- 1.69, N = 10SE +/- 1.09, N = 10251.33263.881. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Super FastOptimized Power ModeDefault0.22280.44560.66840.89121.1140.990.94
MinAvgMaxOptimized Power Mode80032633907Default80034063908OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode184.6253.9385.9Default195.0280.7447.3OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor1202403604806001. Optimized Power Mode: Approximate power consumption of 1701 Joules per run.2. Default: Approximate power consumption of 1825 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Super FastOptimized Power ModeDefault50100150200250Min: 240.04 / Avg: 251.33 / Max: 256.84Min: 259.16 / Avg: 263.88 / Max: 272.31. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Ultra FastOptimized Power ModeDefault60120180240300SE +/- 1.93, N = 10SE +/- 2.07, N = 11263.96282.051. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Ultra FastOptimized Power ModeDefault0.25020.50040.75061.00081.2511.1121.051
MinAvgMaxOptimized Power Mode80035053908Default80035233912OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode146.9237.4350.4Default195.4268.4416.5OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor1102203304405501. Optimized Power Mode: Approximate power consumption of 1543 Joules per run.2. Default: Approximate power consumption of 1708 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Ultra FastOptimized Power ModeDefault50100150200250Min: 251.12 / Avg: 263.96 / Max: 273.61Min: 265.24 / Avg: 282.05 / Max: 293.061. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Very FastOptimized Power ModeDefault60120180240300SE +/- 1.04, N = 10SE +/- 1.16, N = 10256.19268.491. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Very FastOptimized Power ModeDefault0.21560.43120.64680.86241.0780.9580.925
MinAvgMaxOptimized Power Mode80033103909Default80035303907OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode188.2267.5439.5Default195.3290.3469.1OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor1202403604806001. Optimized Power Mode: Approximate power consumption of 1765 Joules per run.2. Default: Approximate power consumption of 1887 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Very FastOptimized Power ModeDefault50100150200250Min: 251.65 / Avg: 256.19 / Max: 261.96Min: 263.87 / Avg: 268.49 / Max: 273.991. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenFOAM

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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: motorBike - Execution TimeOptimized Power ModeDefault1.23952.4793.71854.9586.19755.508974.132881. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
MinAvgMaxOptimized Power Mode388939003908Default80035753908OpenBenchmarking.orgMegahertz, More Is BetterOpenFOAM 10CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMaxOptimized Power Mode175.6200.2221.0Default206.9278.4337.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption Monitor80160240320400

SVT-VP9

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

Tuning: VMAF Optimized - Input: Bosphorus 4K

Default: The test quit with a non-zero exit status.

Optimized Power Mode: The test quit with a non-zero exit status.

Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K

Default: The test quit with a non-zero exit status.

Optimized Power Mode: The test quit with a non-zero exit status.

Tuning: Visual Quality Optimized - Input: Bosphorus 4K

Default: The test quit with a non-zero exit status.

Optimized Power Mode: The test quit with a non-zero exit status.

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringOptimized Power ModeDefault140280420560700Min: 88.73 / Avg: 366.23 / Max: 802.53Min: 101.15 / Avg: 445.93 / Max: 802.3

CPU Peak Freq (Highest CPU Core Frequency) Monitor

OpenBenchmarking.orgMegahertzCPU Peak Freq (Highest CPU Core Frequency) MonitorPhoronix Test Suite System MonitoringOptimized Power ModeDefault10002000300040005000Min: 800 / Avg: 3437 / Max: 5154Min: 500 / Avg: 3374.53 / Max: 5474

181 Results Shown

PyTorch:
  CPU - 64 - Efficientnet_v2_l
  CPU - 256 - Efficientnet_v2_l
Timed GCC Compilation
PostgreSQL:
  100 - 1000 - Read Only - Average Latency
  100 - 1000 - Read Only
Apache Spark TPC-H:
  10 - Q22
  10 - Q21
  10 - Q20
  10 - Q19
  10 - Q18
  10 - Q17
  10 - Q16
  10 - Q15
  10 - Q14
  10 - Q13
  10 - Q12
  10 - Q11
  10 - Q10
  10 - Q09
  10 - Q08
  10 - Q07
  10 - Q06
  10 - Q05
  10 - Q04
  10 - Q03
  10 - Q02
  10 - Q01
  10 - Geometric Mean Of All Queries
PyTorch
Memcached
PyTorch
Blender
easyWave
DuckDB:
  TPC-H Parquet
  IMDB
Timed LLVM Compilation
FFmpeg:
  libx265 - Upload
  libx265 - Video On Demand
  libx265 - Platform
Timed Linux Kernel Compilation
PostgreSQL:
  100 - 1000 - Read Write - Average Latency
  100 - 1000 - Read Write
QMCPACK
easyWave
OpenRadioss:
  Chrysler Neon 1M
  Bird Strike on Windshield
  INIVOL and Fluid Structure Interaction Drop Container
Timed LLVM Compilation
VVenC
nginx
Apache HTTP Server
OpenRadioss
Liquid-DSP
OpenRadioss
Zstd Compression:
  12 - Decompression Speed
  12 - Compression Speed
Redis
Neural Magic DeepSparse:
  BERT-Large, NLP Question Answering - Asynchronous Multi-Stream:
    ms/batch
    items/sec
Zstd Compression:
  19, Long Mode - Decompression Speed
  19, Long Mode - Compression Speed
Timed Linux Kernel Compilation
nginx
Zstd Compression:
  19 - Decompression Speed
  19 - Compression Speed
Xmrig
PyTorch:
  CPU - 64 - ResNet-50
  CPU - 256 - ResNet-50
OpenVINO:
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
Memcached
VVenC
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU:
    ms
    FPS
  Road Segmentation ADAS FP16-INT8 - CPU:
    ms
    FPS
  Person Detection FP16 - CPU:
    ms
    FPS
  Vehicle Detection FP16-INT8 - CPU:
    ms
    FPS
  Machine Translation EN To DE FP16 - CPU:
    ms
    FPS
  Face Detection Retail FP16-INT8 - CPU:
    ms
    FPS
QuantLib
OpenVINO:
  Handwritten English Recognition FP16-INT8 - CPU:
    ms
    FPS
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
FFmpeg
Apache Hadoop
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
Liquid-DSP:
  32 - 256 - 512
  256 - 256 - 32
7-Zip Compression:
  Decompression Rating
  Compression Rating
Neural Magic DeepSparse:
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    ms/batch
    items/sec
uvg266
Neural Magic DeepSparse:
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  ResNet-50, Baseline - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
VVenC
OpenRadioss
Blender
Liquid-DSP
Apache HTTP Server
Liquid-DSP:
  128 - 256 - 512
  64 - 256 - 512
  256 - 256 - 57
  128 - 256 - 57
  128 - 256 - 32
  64 - 256 - 32
  32 - 256 - 32
  32 - 256 - 57
VVenC
SVT-AV1
Redis
uvg266
Redis
QuantLib
Xmrig
Redis
OpenFOAM:
  drivaerFastback, Small Mesh Size - Execution Time
  drivaerFastback, Small Mesh Size - Mesh Time
SVT-AV1
uvg266:
  Bosphorus 4K - Medium
  Bosphorus 1080p - Super Fast
Xmrig
Kvazaar
Xmrig:
  KawPow - 1M
  Monero - 1M
  CryptoNight-Heavy - 1M
Kvazaar
Blender
SVT-AV1
uvg266:
  Bosphorus 4K - Super Fast
  Bosphorus 4K - Ultra Fast
Kvazaar
SVT-AV1:
  Preset 8 - Bosphorus 4K
  Preset 12 - Bosphorus 4K
uvg266:
  Bosphorus 1080p - Ultra Fast
  Bosphorus 1080p - Slow
Kvazaar
SVT-VP9
Kvazaar
Intel Open Image Denoise
Y-Cruncher
SVT-AV1
uvg266
Kvazaar
uvg266
SVT-AV1
Kvazaar
SVT-VP9:
  Visual Quality Optimized - Bosphorus 1080p
  PSNR/SSIM Optimized - Bosphorus 1080p
SVT-AV1
Kvazaar:
  Bosphorus 1080p - Super Fast
  Bosphorus 1080p - Ultra Fast
  Bosphorus 1080p - Very Fast
OpenFOAM
CPU Power Consumption Monitor:
  Phoronix Test Suite System Monitoring:
    Watts
    Megahertz

Default

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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
Processor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x21000161
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 14 December 2023 16:53 by user phoronix.

Optimized Power Mode

Processor: 2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Intel X710 for 10GBASE-T

OS: Ubuntu 23.10, Kernel: 6.5.0-13-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-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
Processor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x21000161
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 15 December 2023 10:44 by user phoronix.