eee

2 x Intel Xeon Gold 5220R testing with a TYAN S7106 (V2.01.B40 BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2304029-NE-EEE72972408
Jump To Table - Results

View

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

Limit displaying results to tests within:

Timed Code Compilation 5 Tests
C/C++ Compiler Tests 9 Tests
CPU Massive 11 Tests
Creator Workloads 9 Tests
Cryptography 2 Tests
Database Test Suite 4 Tests
Encoding 4 Tests
Game Development 3 Tests
HPC - High Performance Computing 3 Tests
Common Kernel Benchmarks 4 Tests
Machine Learning 3 Tests
Multi-Core 15 Tests
Intel oneAPI 2 Tests
Programmer / Developer System Benchmarks 6 Tests
Python Tests 6 Tests
Server 7 Tests
Server CPU Tests 7 Tests
Video Encoding 4 Tests

Statistics

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

Graph Settings

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

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
April 02 2023
  6 Hours, 3 Minutes
b
April 01 2023
  3 Hours, 58 Minutes
bb
April 02 2023
  6 Hours, 7 Minutes
Invert Hiding All Results Option
  5 Hours, 22 Minutes

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

b

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-Av3uEd/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x5003302
Python Notes: Python 2.7.18 + Python 3.8.10
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Stuffing + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

bb

a

Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: TYAN S7106 (V2.01.B40 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 94GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel I210 + 2 x QLogic cLOM8214 1/10GbE

OS: Ubuntu 20.04, Kernel: 6.1.0-phx (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1920x1080

eeeOpenBenchmarking.orgPhoronix Test Suite2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads)TYAN S7106 (V2.01.B40 BIOS)Intel Sky Lake-E DMI3 Registers94GB500GB Samsung SSD 860ASPEEDVE2282 x Intel I210 + 2 x QLogic cLOM8214 1/10GbEUbuntu 20.046.1.0-phx (x86_64)GNOME Shell 3.36.9X Server 1.20.13GCC 9.4.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionEee BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-Av3uEd/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x5003302 - Python 2.7.18 + Python 3.8.10- itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Stuffing + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

bbbaResult OverviewPhoronix Test Suite100%103%105%108%111%MemcachedPostgreSQLTensorFlowTimed LLVM CompilationClickHouseoneDNNSVT-AV1John The RipperBuild2Zstd CompressionFFmpegTimed Godot Game Engine CompilationTimed FFmpeg CompilationSPECFEM3DTimed Node.js CompilationEmbreeOpenSSLVVenCuvg266

eeetensorflow: CPU - 512 - ResNet-50tensorflow: CPU - 256 - ResNet-50blender: Barbershop - CPU-Onlytensorflow: CPU - 512 - GoogLeNetclickhouse: 100M Rows Hits Dataset, Third Runclickhouse: 100M Rows Hits Dataset, Second Runclickhouse: 100M Rows Hits Dataset, First Run / Cold Cachebuild-llvm: Unix Makefilesffmpeg: libx265 - Platformffmpeg: libx265 - Platformffmpeg: libx265 - Video On Demandffmpeg: libx265 - Video On Demandbuild-llvm: Ninjaffmpeg: libx264 - Uploadffmpeg: libx264 - Uploadtensorflow: CPU - 64 - ResNet-50ffmpeg: libx265 - Uploadffmpeg: libx265 - Uploadbuild-nodejs: Time To Compilerocksdb: Seq Filltensorflow: CPU - 256 - GoogLeNettensorflow: CPU - 512 - AlexNetbuild-godot: Time To Compileffmpeg: libx264 - Video On Demandffmpeg: libx264 - Video On Demandffmpeg: libx264 - Platformffmpeg: libx264 - Platformtensorflow: CPU - 32 - ResNet-50blender: Pabellon Barcelona - CPU-Onlyopenssl: ChaCha20-Poly1305openssl: AES-256-GCMopenssl: AES-128-GCMopenssl: ChaCha20openssl: SHA512openssl: SHA256vvenc: Bosphorus 4K - Fastblender: Classroom - CPU-Onlyffmpeg: libx265 - Liveffmpeg: libx265 - Livepgbench: 100 - 50 - Read Only - Average Latencypgbench: 100 - 50 - Read Onlypgbench: 100 - 50 - Read Write - Average Latencypgbench: 100 - 50 - Read Writetensorflow: CPU - 256 - AlexNetpgbench: 1 - 50 - Read Write - Average Latencypgbench: 1 - 50 - Read Writepgbench: 1 - 50 - Read Only - Average Latencypgbench: 1 - 50 - Read Onlytensorflow: CPU - 16 - ResNet-50vvenc: Bosphorus 4K - Fasterbuild2: Time To Compiletensorflow: CPU - 64 - GoogLeNetnginx: 1000nginx: 500nginx: 200nginx: 100deepsparse: 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-Streamonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamuvg266: Bosphorus 4K - Slowblender: Fishy Cat - CPU-Onlysvt-av1: Preset 4 - Bosphorus 4Krocksdb: Rand Fill Syncuvg266: Bosphorus 4K - Mediumspecfem3d: Layered Halfspacetensorflow: CPU - 32 - GoogLeNetmemcached: 1:100compress-zstd: 19 - Decompression Speedcompress-zstd: 19 - Compression Speedmemcached: 1:5memcached: 1:10specfem3d: Water-layered Halfspacecompress-zstd: 3, Long Mode - Decompression Speedcompress-zstd: 3, Long Mode - Compression Speedcompress-zstd: 8, Long Mode - Decompression Speedcompress-zstd: 8, Long Mode - Compression Speedcompress-zstd: 3 - Decompression Speedcompress-zstd: 3 - Compression Speedvvenc: Bosphorus 1080p - Fastcompress-zstd: 12 - Decompression Speedcompress-zstd: 12 - Compression Speeddeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamcompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedcompress-zstd: 8 - Decompression Speedcompress-zstd: 8 - Compression Speeddeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamffmpeg: libx264 - Liveffmpeg: libx264 - Liverocksdb: Rand Fillrocksdb: Update Randrocksdb: Read While Writingjohn-the-ripper: MD5rocksdb: Read Rand Write Randjohn-the-ripper: HMAC-SHA512rocksdb: Rand Readopenssl: RSA4096openssl: RSA4096blender: BMW27 - CPU-Onlydeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamtensorflow: CPU - 64 - AlexNetdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamtensorflow: CPU - 16 - GoogLeNetdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamvvenc: Bosphorus 1080p - Fasterdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamembree: Pathtracer - Asian Dragon Objtensorflow: CPU - 32 - AlexNetspecfem3d: Homogeneous Halfspacebuild-ffmpeg: Time To Compileuvg266: Bosphorus 4K - Very Fastembree: Pathtracer ISPC - Asian Dragon Objuvg266: Bosphorus 1080p - Slowjohn-the-ripper: WPA PSKjohn-the-ripper: bcryptjohn-the-ripper: Blowfishuvg266: Bosphorus 1080p - Mediumuvg266: Bosphorus 4K - Super Fastsvt-av1: Preset 4 - Bosphorus 1080pspecfem3d: Tomographic Modeluvg266: Bosphorus 4K - Ultra Fastspecfem3d: Mount St. Helenssvt-av1: Preset 8 - Bosphorus 4Ktensorflow: CPU - 16 - AlexNetembree: Pathtracer - Crownembree: Pathtracer ISPC - Crownonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUembree: Pathtracer - Asian Dragonembree: Pathtracer ISPC - Asian Dragononednn: IP Shapes 1D - bf16bf16bf16 - CPUonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUuvg266: Bosphorus 1080p - Very Fastuvg266: Bosphorus 1080p - Super Fastuvg266: Bosphorus 1080p - Ultra Fastsvt-av1: Preset 12 - Bosphorus 4Kdraco: Church Facadesvt-av1: Preset 8 - Bosphorus 1080ponednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 3D - bf16bf16bf16 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUdraco: Lionsvt-av1: Preset 13 - Bosphorus 4Konednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUsvt-av1: Preset 12 - Bosphorus 1080psvt-av1: Preset 13 - Bosphorus 1080ponednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUapache: 200bbba210.46211.36157.77439.28220.52369.21978633320.61367.613657159339.91210.42242.2427549322.2710.58238.65309.311104.62227.85234.22138.16198.5038.07198.96034061718.31805125573301185964209501597819726501500740050901016759845091020320203.57943.62115.7655491780.0599126213.853610212.561.6568110.047105284815.16.02699.15177.641386.621385.411381.33785.39788.652797.5917.952.6088.8264.46254943664.041550585.25846.712.81672007.691478446.7861.3673565521144.52831097.9289.91095.11640.69.641996.4153.9833.26.451093.7545.9153.9632.80471900091970000536533.88026.7146.4850.9616.89729.4408109.7431.08993581633.27318.1132.556518.45213811488644840520.0520.336.34425.26886065821.4824.12549029836.22584.4828.493829.502314.80338.689120.56274433.177837.71045.687281.71781.7481642.6245.148.24117.74286.9513.093644.306171.28042111.1544.901444.787996.35868235.271201.7329.510192.738210.68833230.9529.43580.85109.27211.12200.24154.30419.84720.50369.54018218820.68366.29338.88510.47241.1322.3510.70235.941449418309.086249987104.2227232.0238.28197.89616466438.21198.2718.3192.11805137550001184999934601591609346201500592428401019337361092063849303.634159.2740.56124.510.0599366016.4973031213.3261.9138080.047106795415.095.97100.74777.79139997.58143874.15149820.05151733.73961.134618.7109961.970718.70791374.191377.451380.03196.741291.353787.693789.003789.808440.408540.86297.9174.632.64775278.8564.48091452563.781587757.5484912.91937351.981700246.1860.5133289091140.2310.51100.7279.41095.81584.19.746996.5151.428.615334.9308834.26.791097.6572.3115.40548.6642115.02918.692550.695319.7168153.82210733432.8324368022870348754804712000225151798271000114830146534630.58109.855.76180.283299.754445.5898394.4534145.41100.1536179.56868.8977112.227923.644342.269751.0891352.043515.118566.0925128.8102139.49951.1518.387954.329816.6759.1226109.451829.4853109.0731.06573373833.17818.1432.443818.47214200489124856220.2220.076.22225.007749221.6224.63982217735.89382.2228.745529.536214.64648.672110.56227333.171137.71765.686511.732571.6933642.3245.2348.4117.555938186.4843.171733.330731.282536713110.2864.358624.774986.35249228.891201.4449.512522.73830.69103731.129.63579.52109.76206.05205.05163.13439.1220.45370.33863891420.66366.57343.24210.44241.76402751222.210.64237.23567868309.57259650103.29227.16232.64138.03199.1838.19198.34755398618.25191.67805164665501182502628001591512877701501767603501014572533091733113303.657159.5640.28125.3747564240.0599465512.673946212.6561.8428090.047106870715.115.991100.2777.76139200.66141761.59147630.66152180.63977.29418.3814965.213418.41721384.141379.971374.37196.561191.4064788.804786.003786.919446.167240.33477.9174.472.5569718.8363.68210572143.321290869.25840.612.82007905.011719545.4860.2371675811137325.91105.7282.71102.71664.39.605987.6146.228.792734.71458266.711093.3579.4115.15838.6827115.35298.66851.111719.5562152.1133.2025148723337549102004691000222891891245000115209715534883.88029.456.07180.716699.486844.6206403.0469146.93100.5244178.91988.8732112.535523.433142.649951.1119351.833215.283665.3784128.7775139.560850.7118.387854.334316.7298.8739112.506529.595109.5331.37921095633.4818.0732.499618.3212818488214875620.0420.296.22325.34943935421.824.14800530136.41383.228.638329.711414.75138.670710.56351533.034937.88385.693531.733541.6387842.9344.6448.17110.282941085.6593.455994.05731.299786694110.6384.394633.52976.35319232.248200.8029.566672.743470.693934OpenBenchmarking.org

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: ResNet-50abb71421283531.1030.95

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: ResNet-50abb71421283529.6329.43

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Barbershop - Compute: CPU-Onlyabb130260390520650579.52580.85

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: GoogLeNetabb20406080100109.76109.27

ClickHouse

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

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third Runabbb50100150200250206.05211.12210.46MIN: 18.75 / MAX: 1090.91MIN: 18.35 / MAX: 1875MIN: 18.39 / MAX: 1276.6

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second Runabbb50100150200250205.05200.24211.36MIN: 18.52 / MAX: 1363.64MIN: 18.21 / MAX: 1714.29MIN: 18.65 / MAX: 2500

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold Cacheabbb4080120160200163.13154.30157.77MIN: 16.41 / MAX: 1200MIN: 15.97 / MAX: 1578.95MIN: 16.57 / MAX: 1621.62

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 Makefilesabbb100200300400500439.12419.85439.28

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 6.0Encoder: libx265 - Scenario: Platformabbb51015202520.4520.5020.521. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Platformabbb80160240320400370.34369.54369.221. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Video On Demandabbb51015202520.6620.6820.611. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Video On Demandabbb80160240320400366.57366.29367.611. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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: Ninjaabbb70140210280350343.24338.89339.91

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 6.0Encoder: libx264 - Scenario: Uploadabbb369121510.4410.4710.421. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Uploadabbb50100150200250241.76241.13242.241. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50abbb51015202522.2022.3522.27

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 6.0Encoder: libx265 - Scenario: Uploadabbb369121510.6410.7010.581. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Uploadabbb50100150200250237.24235.94238.651. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Timed Node.js Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 19.8.1Time To Compileabbb70140210280350309.57309.09309.31

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Sequential Fillabb60K120K180K240K300K2596502499871. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: GoogLeNetabbb20406080100103.29104.20104.62

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: AlexNetabbb50100150200250227.16227.00227.85

Timed Godot Game Engine Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To Compileabbb50100150200250232.64232.02234.22

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 6.0Encoder: libx264 - Scenario: Video On Demandabbb91827364538.0338.2838.161. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Video On Demandabbb4080120160200199.18197.90198.501. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Platformabbb91827364538.1938.2138.071. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Platformabbb4080120160200198.35198.27198.961. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: ResNet-50abbb51015202518.2518.3018.31

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Pabellon Barcelona - Compute: CPU-Onlyabb4080120160200191.67192.11

OpenSSL

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

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly1305abbb20000M40000M60000M80000M100000M8051646655080513755000805125573301. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCMabbb30000M60000M90000M120000M150000M1182502628001184999934601185964209501. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCMabbb30000M60000M90000M120000M150000M1591512877701591609346201597819726501. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20abbb30000M60000M90000M120000M150000M1501767603501500592428401500740050901. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA512abbb2000M4000M6000M8000M10000M1014572533010193373610101675984501. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA256abbb2000M4000M6000M8000M10000M9173311330920638493091020320201. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: Fastabbb0.82281.64562.46843.29124.1143.6573.6343.5791. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto -lpthread

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Classroom - Compute: CPU-Onlyabb4080120160200159.56159.27

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 6.0Encoder: libx265 - Scenario: Liveabbb102030405040.2840.5643.621. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Liveabbb306090120150125.37124.51115.771. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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 15Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latencyabbb0.01130.02260.03390.04520.05650.050.050.051. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 50 - Mode: Read Onlyabbb200K400K600K800K1000K9946559936609912621. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latencyabbb4812162012.6716.5013.851. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 50 - Mode: Read Writeabbb80016002400320040003946303136101. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: AlexNetabbb50100150200250212.65213.32212.50

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 15Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latencyabbb142842567061.8461.9161.661. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 50 - Mode: Read Writeabbb20040060080010008098088111. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latencyabbb0.01060.02120.03180.04240.0530.0470.0470.0471. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 50 - Mode: Read Onlyabbb200K400K600K800K1000K1068707106795410528481. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50abbb4812162015.1115.0915.10

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: Fasterabbb2468105.9915.9706.0261. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto -lpthread

Build2

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.15Time To Compileabbb20406080100100.27100.7599.15

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: GoogLeNetabbb2040608010077.7677.7977.64

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: 1000abb30K60K90K120K150K139200.66139997.581. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500abb30K60K90K120K150K141761.59143874.151. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 200abb30K60K90K120K150K147630.66149820.051. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 100abb30K60K90K120K150K152180.63151733.731. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabb2004006008001000977.29961.13

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabb51015202518.3818.71

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabb2004006008001000965.21961.97

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabb51015202518.4218.71

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUabbb300600900120015001384.141374.191386.62MIN: 1379.57MIN: 1367.79MIN: 1378.881. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUabbb300600900120015001379.971377.451385.41MIN: 1367.35MIN: 1371.04MIN: 1377.531. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUabbb300600900120015001374.371380.031381.33MIN: 1363.77MIN: 1374.88MIN: 1376.641. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamabb4080120160200196.56196.74

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamabb2040608010091.4191.35

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUabbb2004006008001000788.80787.69785.39MIN: 782.96MIN: 778.68MIN: 775.341. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUabbb2004006008001000786.00789.00788.65MIN: 779.97MIN: 779.2MIN: 781.041. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUabbb2004006008001000786.92789.81797.59MIN: 779.8MIN: 783.36MIN: 783.041. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabb100200300400500446.17440.41

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabb91827364540.3340.86

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: Slowabbb2468107.917.917.95

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Fishy Cat - Compute: CPU-Onlyabb2040608010074.4774.63

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 4 - Input: Bosphorus 4Kabbb0.59561.19121.78682.38242.9782.5502.6472.6081. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Random Fill Syncabb16003200480064008000697175271. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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: Mediumabbb2468108.838.858.82

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Layered Halfspaceabbb142842567063.6864.4864.461. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: GoogLeNetabbb142842567043.3263.7864.04

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: 1:100abbb300K600K900K1200K1500K1290869.251587757.541550585.251. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

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 Speedabbb2004006008001000840.6849.0846.71. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression Speedabbb369121512.812.912.81. (CC) gcc options: -O3 -pthread -lz -llzma

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: 1:5abbb400K800K1200K1600K2000K2007905.011937351.981672007.691. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10abbb400K800K1200K1600K2000K1719545.481700246.181478446.781. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Water-layered Halfspaceabbb142842567060.2460.5161.371. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

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: 3, Long Mode - Decompression Speedabbb20040060080010001137.01140.21144.51. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3, Long Mode - Compression Speedabbb70140210280350325.9310.5283.01. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Decompression Speedabbb20040060080010001105.71100.71097.91. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Compression Speedabbb60120180240300282.7279.4289.91. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3 - Decompression Speedabbb20040060080010001102.71095.81095.11. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3 - Compression Speedabbb4008001200160020001664.31584.11640.61. (CC) gcc options: -O3 -pthread -lz -llzma

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 1080p - Video Preset: Fastabbb36912159.6059.7469.6411. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto -lpthread

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression Speedabbb2004006008001000987.6996.5996.41. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression Speedabbb306090120150146.2151.4153.91. (CC) gcc options: -O3 -pthread -lz -llzma

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamabb71421283528.7928.62

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamabb81624324034.7134.93

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 Speedabbb2004006008001000826.0834.2833.21. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression Speedabbb2468106.716.796.451. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Decompression Speedabbb20040060080010001093.31097.61093.71. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Compression Speedabbb130260390520650579.4572.3545.91. (CC) gcc options: -O3 -pthread -lz -llzma

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabb306090120150115.16115.41

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabb2468108.68278.6642

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabb306090120150115.35115.03

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabb2468108.66808.6925

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabb122436486051.1150.70

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabb51015202519.5619.72

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 6.0Encoder: libx264 - Scenario: Liveabbb306090120150152.11153.82153.961. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Liveabbb81624324033.2032.8332.801. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Random Fillabb50K100K150K200K250K2514872436801. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Update Randomabb50K100K150K200K250K2333752287031. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Read While Writingabb1.1M2.2M3.3M4.4M5.5M491020048754801. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5abbb1000K2000K3000K4000K5000K4691000471200047190001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lrt -lz -ldl -lcrypt -lbz2

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Read Random Write Randomabb500K1000K1500K2000K2500K222891822515171. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: HMAC-SHA512abbb20M40M60M80M100M9124500098271000919700001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lrt -lz -ldl -lcrypt -lbz2

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Random Readabb20M40M60M80M100M1152097151148301461. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenSSL

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

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096abbb110K220K330K440K550K534883.8534630.5536533.81. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096abbb2K4K6K8K10K8029.48109.88026.71. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: BMW27 - Compute: CPU-Onlyabb132639526556.0755.76

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamabb4080120160200180.72180.28

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamabb2040608010099.4999.75

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamabb102030405044.6245.59

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamabb90180270360450403.05394.45

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: AlexNetabbb306090120150146.93145.41146.48

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabb20406080100100.52100.15

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabb4080120160200178.92179.57

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamabb2468108.87328.8977

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamabb306090120150112.54112.23

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamabb61218243023.4323.64

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamabb102030405042.6542.27

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabb122436486051.1151.09

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabb80160240320400351.83352.04

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabb4812162015.2815.12

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabb153045607565.3866.09

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabb306090120150128.78128.81

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabb306090120150139.56139.50

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: GoogLeNetabbb122436486050.7151.1550.96

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabb51015202518.3918.39

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabb122436486054.3354.33

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 1080p - Video Preset: Fasterabbb4812162016.7316.6816.901. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto -lpthread

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabb36912158.87399.1226

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabb306090120150112.51109.45

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer - Model: Asian Dragon Objabbb71421283529.6029.4929.44MIN: 29.37 / MAX: 30.06MIN: 29.24 / MAX: 29.77MIN: 29.24 / MAX: 29.86

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: AlexNetabbb20406080100109.53109.07109.74

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Homogeneous Halfspaceabbb71421283531.3831.0731.091. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Timed FFmpeg Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 6.0Time To Compileabbb81624324033.4833.1833.27

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 Fastabbb4812162018.0718.1418.11

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer ISPC - Model: Asian Dragon Objabbb81624324032.5032.4432.56MIN: 32.25 / MAX: 32.9MIN: 32.17 / MAX: 32.79MIN: 32.27 / MAX: 32.95

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: Slowabbb51015202518.3018.4718.45

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKabbb50K100K150K200K250K2128182142002138111. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lrt -lz -ldl -lcrypt -lbz2

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptabbb10K20K30K40K50K4882148912488641. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lrt -lz -ldl -lcrypt -lbz2

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: Blowfishabbb10K20K30K40K50K4875648562484051. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lrt -lz -ldl -lcrypt -lbz2

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: Mediumabbb51015202520.0420.2220.05

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super Fastabbb51015202520.2920.0720.33

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 4 - Input: Bosphorus 1080pabbb2468106.2236.2226.3441. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Tomographic Modelabbb61218243025.3525.0125.271. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

uvg266

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

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra Fastabbb51015202521.8021.6221.48

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Mount St. Helensabbb61218243024.1524.6424.131. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 8 - Input: Bosphorus 4Kabbb81624324036.4135.8936.231. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: AlexNetabbb2040608010083.2082.2284.48

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer - Model: Crownabbb71421283528.6428.7528.49MIN: 28.27 / MAX: 29.08MIN: 28.39 / MAX: 29.15MIN: 28.14 / MAX: 29

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer ISPC - Model: Crownabbb71421283529.7129.5429.50MIN: 29.3 / MAX: 30.17MIN: 29.06 / MAX: 30.1MIN: 29.05 / MAX: 30.07

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUabbb4812162014.7514.6514.80MIN: 12.24MIN: 12.43MIN: 12.391. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUabbb2468108.670718.672118.68912MIN: 8.58MIN: 8.57MIN: 8.581. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUabbb0.12680.25360.38040.50720.6340.5635150.5622730.562744MIN: 0.54MIN: 0.54MIN: 0.541. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer - Model: Asian Dragonabbb81624324033.0333.1733.18MIN: 32.82 / MAX: 33.48MIN: 32.95 / MAX: 33.5MIN: 32.97 / MAX: 33.5

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer ISPC - Model: Asian Dragonabbb91827364537.8837.7237.71MIN: 37.64 / MAX: 38.3MIN: 37.47 / MAX: 38.19MIN: 37.4 / MAX: 38.13

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUabbb1.2812.5623.8435.1246.4055.693535.686515.68728MIN: 5.55MIN: 5.55MIN: 5.541. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUabbb0.390.781.171.561.951.733541.732571.71780MIN: 1.65MIN: 1.64MIN: 1.641. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUabbb0.39330.78661.17991.57321.96651.638781.693361.74816MIN: 1.5MIN: 1.56MIN: 1.561. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 Fastabbb102030405042.9342.3242.62

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Super Fastabbb102030405044.6445.2345.10

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Ultra Fastabbb112233445548.1748.4048.24

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 12 - Input: Bosphorus 4Kabbb306090120150110.28117.56117.741. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Google Draco

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

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Church Facadeabb2K4K6K8K10K941093811. (CXX) g++ options: -O3

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 8 - Input: Bosphorus 1080pabbb2040608010085.6686.4886.951. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUabbb0.77761.55522.33283.11043.8883.455993.171733.09364MIN: 1.83MIN: 1.84MIN: 1.811. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUabbb0.96891.93782.90673.87564.84454.057303.330734.30617MIN: 2.84MIN: 2.9MIN: 2.981. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUabbb0.29250.5850.87751.171.46251.299781.282531.28042MIN: 1.08MIN: 1.1MIN: 1.071. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Google Draco

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

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Lionabb14002800420056007000669467131. (CXX) g++ options: -O3

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 13 - Input: Bosphorus 4Kabbb20406080100110.64110.29111.151. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUabbb1.10282.20563.30844.41125.5144.394634.358624.90144MIN: 2.48MIN: 2.47MIN: 2.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUabbb1.07732.15463.23194.30925.38653.529704.774984.78799MIN: 2.77MIN: 2.76MIN: 2.751. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUabbb2468106.353196.352496.35868MIN: 6.3MIN: 6.3MIN: 6.31. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 12 - Input: Bosphorus 1080pabbb50100150200250232.25228.89235.271. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 13 - Input: Bosphorus 1080pabbb4080120160200200.80201.44201.731. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUabbb36912159.566679.512529.51019MIN: 9.44MIN: 9.44MIN: 9.441. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUabbb0.61731.23461.85192.46923.08652.743472.738302.73821MIN: 2.72MIN: 2.72MIN: 2.721. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUabbb0.15610.31220.46830.62440.78050.6939340.6910370.688332MIN: 0.69MIN: 0.68MIN: 0.681. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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.

Concurrent Requests: 100

bb: The test quit with a non-zero exit status. E: unable to connect to 127.0.0.1:8088 Connection refused

a: The test quit with a non-zero exit status. E: unable to connect to 127.0.0.1:8088 Connection refused

Concurrent Requests: 1000

bb: The test quit with a non-zero exit status. E: unable to connect to 127.0.0.1:8088 Connection refused

a: The test quit with a non-zero exit status. E: unable to connect to 127.0.0.1:8088 Connection refused

Concurrent Requests: 500

bb: The test quit with a non-zero exit status. E: unable to connect to 127.0.0.1:8088 Connection refused

a: The test quit with a non-zero exit status. E: unable to connect to 127.0.0.1:8088 Connection refused

Concurrent Requests: 200

bb: The test quit with a non-zero exit status. E: unable to connect to 127.0.0.1:8088 Connection refused

a: The test quit with a non-zero exit status. E: unable to connect to 127.0.0.1:8088 Connection refused

186 Results Shown

TensorFlow:
  CPU - 512 - ResNet-50
  CPU - 256 - ResNet-50
Blender
TensorFlow
ClickHouse:
  100M Rows Hits Dataset, Third Run
  100M Rows Hits Dataset, Second Run
  100M Rows Hits Dataset, First Run / Cold Cache
Timed LLVM Compilation
FFmpeg:
  libx265 - Platform:
    FPS
    Seconds
  libx265 - Video On Demand:
    FPS
    Seconds
Timed LLVM Compilation
FFmpeg:
  libx264 - Upload:
    FPS
    Seconds
TensorFlow
FFmpeg:
  libx265 - Upload:
    FPS
    Seconds
Timed Node.js Compilation
RocksDB
TensorFlow:
  CPU - 256 - GoogLeNet
  CPU - 512 - AlexNet
Timed Godot Game Engine Compilation
FFmpeg:
  libx264 - Video On Demand:
    FPS
    Seconds
  libx264 - Platform:
    FPS
    Seconds
TensorFlow
Blender
OpenSSL:
  ChaCha20-Poly1305
  AES-256-GCM
  AES-128-GCM
  ChaCha20
  SHA512
  SHA256
VVenC
Blender
FFmpeg:
  libx265 - Live:
    FPS
    Seconds
PostgreSQL:
  100 - 50 - Read Only - Average Latency
  100 - 50 - Read Only
  100 - 50 - Read Write - Average Latency
  100 - 50 - Read Write
TensorFlow
PostgreSQL:
  1 - 50 - Read Write - Average Latency
  1 - 50 - Read Write
  1 - 50 - Read Only - Average Latency
  1 - 50 - Read Only
TensorFlow
VVenC
Build2
TensorFlow
nginx:
  1000
  500
  200
  100
Neural Magic DeepSparse:
  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
oneDNN:
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
oneDNN:
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
Neural Magic DeepSparse:
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    ms/batch
    items/sec
uvg266
Blender
SVT-AV1
RocksDB
uvg266
SPECFEM3D
TensorFlow
Memcached
Zstd Compression:
  19 - Decompression Speed
  19 - Compression Speed
Memcached:
  1:5
  1:10
SPECFEM3D
Zstd Compression:
  3, Long Mode - Decompression Speed
  3, Long Mode - Compression Speed
  8, Long Mode - Decompression Speed
  8, Long Mode - Compression Speed
  3 - Decompression Speed
  3 - Compression Speed
VVenC
Zstd Compression:
  12 - Decompression Speed
  12 - Compression Speed
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream:
    ms/batch
    items/sec
Zstd Compression:
  19, Long Mode - Decompression Speed
  19, Long Mode - Compression Speed
  8 - Decompression Speed
  8 - Compression Speed
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream:
    ms/batch
    items/sec
FFmpeg:
  libx264 - Live:
    FPS
    Seconds
RocksDB:
  Rand Fill
  Update Rand
  Read While Writing
John The Ripper
RocksDB
John The Ripper
RocksDB
OpenSSL:
  RSA4096:
    verify/s
    sign/s
Blender
Neural Magic DeepSparse:
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream:
    ms/batch
    items/sec
TensorFlow
Neural Magic DeepSparse:
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream:
    ms/batch
    items/sec
TensorFlow
Neural Magic DeepSparse:
  CV Detection, YOLOv5s COCO - Synchronous Single-Stream:
    ms/batch
    items/sec
VVenC
Neural Magic DeepSparse:
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream:
    ms/batch
    items/sec
Embree
TensorFlow
SPECFEM3D
Timed FFmpeg Compilation
uvg266
Embree
uvg266
John The Ripper:
  WPA PSK
  bcrypt
  Blowfish
uvg266:
  Bosphorus 1080p - Medium
  Bosphorus 4K - Super Fast
SVT-AV1
SPECFEM3D
uvg266
SPECFEM3D
SVT-AV1
TensorFlow
Embree:
  Pathtracer - Crown
  Pathtracer ISPC - Crown
oneDNN:
  Deconvolution Batch shapes_1d - f32 - CPU
  Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
Embree:
  Pathtracer - Asian Dragon
  Pathtracer ISPC - Asian Dragon
oneDNN:
  IP Shapes 1D - bf16bf16bf16 - CPU
  IP Shapes 1D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
uvg266:
  Bosphorus 1080p - Very Fast
  Bosphorus 1080p - Super Fast
  Bosphorus 1080p - Ultra Fast
SVT-AV1
Google Draco
SVT-AV1
oneDNN:
  IP Shapes 3D - f32 - CPU
  IP Shapes 3D - bf16bf16bf16 - CPU
  IP Shapes 3D - u8s8f32 - CPU
Google Draco
SVT-AV1
oneDNN:
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
  Convolution Batch Shapes Auto - bf16bf16bf16 - CPU
SVT-AV1:
  Preset 12 - Bosphorus 1080p
  Preset 13 - Bosphorus 1080p
oneDNN:
  Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU

b

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-Av3uEd/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x5003302
Python Notes: Python 2.7.18 + Python 3.8.10
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Stuffing + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

Testing initiated at 1 April 2023 18:24 by user phoronix.

bb

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-Av3uEd/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x5003302
Python Notes: Python 2.7.18 + Python 3.8.10
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Stuffing + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

Testing initiated at 2 April 2023 02:36 by user phoronix.

a

Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: TYAN S7106 (V2.01.B40 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 94GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel I210 + 2 x QLogic cLOM8214 1/10GbE

OS: Ubuntu 20.04, Kernel: 6.1.0-phx (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, Compiler: GCC 9.4.0, 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-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-Av3uEd/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x5003302
Python Notes: Python 2.7.18 + Python 3.8.10
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Stuffing + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled

Testing initiated at 2 April 2023 03:16 by user phoronix.