9654 new

2 x AMD EPYC 9654 96-Core testing with a AMD Titanite_4G (RTI1004D BIOS) and llvmpipe on Red Hat Enterprise Linux 9.1 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2303114-NE-9654NEW5019&sor&grs.

9654 newProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionOpenGLabcno smt ano smt bsmt asmt bsmt csmt dAMD EPYC 9654 96-Core @ 2.40GHz (96 Cores / 192 Threads)AMD Titanite_4G (RTI1004D BIOS)AMD Device 14a4768GB2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007ASPEEDVGA HDMIBroadcom NetXtreme BCM5720 PCIeRed Hat Enterprise Linux 9.15.14.0-162.6.1.el9_1.x86_64 (x86_64)GNOME Shell 40.10X Server 1.20.11GCC 11.3.1 20220421xfs1600x12002 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores)1520GBllvmpipe4.5 Mesa 22.1.5 (LLVM 14.0.6 256 bits)1024x7682 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads)OpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler Details- --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl Processor Details- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Python Details- Python 3.9.14Security Details- a: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - b: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - c: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - no smt a: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - no smt b: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - smt a: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - smt b: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - smt c: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - smt d: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

9654 newstress-ng: MMAPonednn: IP Shapes 1D - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: IP Shapes 1D - f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUstress-ng: Context Switchingstress-ng: NUMAonednn: Deconvolution Batch shapes_1d - f32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUstress-ng: Pthreadrocksdb: Rand Readstress-ng: Matrix Mathstress-ng: CPU Cachestress-ng: CPU Stressstress-ng: Vector Mathstress-ng: Mutexstress-ng: Cryptoonednn: IP Shapes 3D - f32 - CPUstress-ng: SENDFILEstress-ng: Function Callonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUstress-ng: Atomicdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamstress-ng: Glibc Qsort Data Sortingdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUstress-ng: Glibc C String Functionsdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamonednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUstress-ng: Hashopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUonednn: IP Shapes 3D - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Training - f32 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Person Detection FP32 - CPUdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamstress-ng: Mallocopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUrocksdb: Read While Writingdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUstress-ng: MEMFDstress-ng: Memory Copyingstress-ng: Forkingstress-ng: Futexgromacs: MPI CPU - water_GMX50_barerocksdb: Read Rand Write Randonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUmemcached: 1:5stress-ng: System V Message Passingonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUkvazaar: Bosphorus 4K - Slowmemcached: 1:10onednn: Convolution Batch Shapes Auto - u8s8f32 - CPUkvazaar: Bosphorus 4K - Mediumuvg266: Bosphorus 4K - Slowopenvino: Age Gender Recognition Retail 0013 FP16 - CPUonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUmemcached: 1:100stress-ng: Semaphoresbuild-linux-kernel: defconfigstress-ng: Pollopenvkl: vklBenchmark Scalardeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamuvg266: Bosphorus 4K - Mediumdeepsparse: 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 - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamuvg266: Bosphorus 1080p - Super Fastuvg266: Bosphorus 1080p - Ultra Fastcompress-zstd: 12 - Compression Speedrocksdb: Update Randrocksdb: Seq Filldeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamuvg266: Bosphorus 1080p - Very Fastclickhouse: 100M Rows Hits Dataset, Second Runrocksdb: Rand Fillclickhouse: 100M Rows Hits Dataset, First Run / Cold Cachedeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamclickhouse: 100M Rows Hits Dataset, Third Runvpxenc: Speed 5 - Bosphorus 4Kopenvino: Age Gender Recognition Retail 0013 FP16 - CPUuvg266: Bosphorus 4K - Ultra Fastopenvkl: vklBenchmark ISPCcompress-zstd: 8 - Compression Speedcompress-zstd: 3 - Compression Speedbuild-ffmpeg: Time To Compilekvazaar: Bosphorus 1080p - Very Fastuvg266: Bosphorus 4K - Very Fastkvazaar: Bosphorus 1080p - Slowkvazaar: Bosphorus 1080p - Super Fastuvg266: Bosphorus 4K - Super Fastdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamcompress-zstd: 3, Long Mode - Compression Speedkvazaar: Bosphorus 1080p - Mediumdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamrocksdb: Rand Fill Syncdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamkvazaar: Bosphorus 4K - Very Fastkvazaar: Bosphorus 1080p - Ultra Fastkvazaar: Bosphorus 4K - Super Fastkvazaar: Bosphorus 4K - Ultra Fastopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamvpxenc: Speed 0 - Bosphorus 4Kuvg266: Bosphorus 1080p - Slowuvg266: Bosphorus 1080p - Mediumopenvino: Weld Porosity Detection FP16-INT8 - CPUcompress-zstd: 8, Long Mode - Compression Speeddeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamvpxenc: Speed 0 - Bosphorus 1080pcompress-zstd: 19, Long Mode - Compression Speeddeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamvvenc: Bosphorus 1080p - Fastercompress-zstd: 19 - Compression Speeddeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamstress-ng: Socket Activitycompress-zstd: 19 - Decompression Speedcompress-zstd: 12 - Decompression Speedvvenc: Bosphorus 4K - Fastcompress-zstd: 19, Long Mode - Decompression Speedvvenc: Bosphorus 4K - Fastercompress-zstd: 3 - Decompression Speedcompress-zstd: 8 - Decompression Speedvpxenc: Speed 5 - Bosphorus 1080pdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamvvenc: Bosphorus 1080p - Fastcompress-zstd: 8, Long Mode - Decompression Speedcompress-zstd: 3, Long Mode - Decompression Speedembree: Pathtracer - Crownabcno smt ano smt bsmt asmt bsmt csmt d1663.088.74576674.0882.01581671.69675.9153.1149718941003.97483.97.3574616.32941.47109397.78468231434382305.6977.51205134.87556875.5959479783.64203073.151.564611950323.96621015.340.263997174.7242.95811122.3942.98930.55527716257100.251009.84860.29021895493695.76962.149.729494.22499.321.87777907.4894914.179.76440.8533911.245909.691149.7446619.7531314.836127.978.115908.891701.7401.7766312709034.0528.471671.4674495.1792961851566.5640.415446540.4188.710.3570170.534450.304972518.4620106.5158156.362794694.3710.56929264581.170040.6933675750.748.344143044.2110473084.091.8314740.636861088.890.31140541.429.37112346.360.711588487886018128283.2925.76812653709.645565.1812192.880633.0399.149310.08115.3018188.537811.36287.9631238.68240.98330.854438454225616.582860.2522234.95625.91533927600.709.5962104.1178625.1617.360.6570.5610891233.83033.912.569296.9368.82139.92307.4969.3328.623334.9289892.7143.3134.826228.70773766011115.76021116.42680.9310.7381.983.451.09197.10185.071547.4647.6881.1691.3710.1938.5108.677514.699.22319.981577.336330.03919.1152.1377119.20678873.581472.61704.85.821383.712.3361514.81669.329.3730.592412.441677.91536.61664.759.1957671.6541.9234670.202668.9524.2785816313126.86498.677.2824315.543085.53109356.78466888888382304.0467.21217072.27556797.2760031543.97203147.151.562571913590.77621003.920.263373223.2942.83481132.3542.8970.55196616168655.171012.34940.29138718955118.195.48962.6349.729496.95500.831.72975903.2724915.429.75439.0373912.114917.077149.8207619.9442316.290728.238.135894.271685.26401.2053314418461.0228.421675.9674353.4186203521573.74960.578466541.0388.610.3568750.5130680.305731507.7420340.458664.972805836.5210.60928919621.166960.6890645720.98.384162812.4710471889.971.8417240.866792746.340.31272141.3929.29111378.390.7124954876951.3618100474.3625.74912661687.465575.1633193.530533.1398.617510.1365.498181.812311.187289.3355239.92240.9133254555654539616.674559.9222234.68627.20534681610.799.5793104.2908628.3717.370.6670.6810751239.3309512.434290.5968.79139.07303.996928.713734.8189909.4144.2135.096228.48663730021118.43831116.289981.61305.5280.6884.771.09196.54145.085947.35327.7181.4191.4710.1910.8109.112914.679.29319.964877.30529.84519.1151.6003119.37998851.651467.81716.75.8091378.212.3911516.6165129.530.460812.3991673.71537.51668.923.83017669.1461.88686671.233667.954.397216862185.54478.057.3811615.13174.04109609.15468069792382328.597.04217304.19556833.559929401.4203095.441.567421891202.37621041.930.26292183.3342.91521125.8642.74330.55685116537965.141013.73570.28543218961773.1895.59962.1549.779485.65500.31.6386906.1394910.139.76438.4372915.084911.762149.6905625.5512316.628227.898.135898.791704.02400.0427313768771.2628.331679.0374486.0883163791571.82810.417188535.7889.460.3531750.5469910.305599507.9720297.9164299.622794473.7510.58729100231.169190.6926675724.818.374155273.4610475486.391.8226440.766839975.870.31228941.4729.41112186.250.7085634852421.6718088584.6725.6812676101.415495.1696193.311933.198.592210.13845.5007181.724311.160589.547237.96238.77330.154357254456516.518560.4884237.44621.88536551614.248.8004113.5057636.1817.460.6671.1310661241.13049.412.465291.0369.04140.1301.469.9228.569834.9937916.9143.8135.118828.46873569221122.05841117.732380.31309.6484.5582.71.09197.66015.057347.29427.781.191.2910.11926.9109.246714.769.3320.050476.618130.08119.1151.3899119.70268876.11470.51715.65.808138412.3991517.41661.929.4630.491112.4411675.41540.94520.486.19257930.2572.04003913.201973.3184.8788347222624.4920.519.252926.017979.0568076.031209611055932248.1840.94328297.04920216.2763581395.67435615.352.196453284433.2829106.630.316665400.0397.39961978.897.44420.66435926755146.692204.75330.31677927408413.1208.82438.29109.0820836.1229.462.022861148.2610556.934.54941.24431151.251147.34308.42941291.9733649.30257.183.9512119.66833.99813.9832456657338.8457.58828.67127833.5276438313107.29570.2916871045.8145.860.3428360.5560690.160361303.5611342.6943094.963746361.5219.17520798040.6642950.403599784.094.92444886.827402514.741.6504147.134244908.830.25484547.9734.59160545.410.4623863192061.6813141129.6817.60610458275.246477.5856131.758638.3872.129813.85596.0118166.272514.463869.1063181.67186.24279.946201846570020.738548.1849196.25666.43478629635.489.8899101.0095665.0014.480.5757.7810981227.52804.210.597269.6257.13155.56288.4159.8331.922931.3187955.6159.6331.914631.327350673955.1631956.008870.02278.6275.576.051.01191.26055.226242.8057.0487.1598.219.18859.9100.241814.289.39304.207573.199328.68919.8145.3548116.15328968.281483.117285.891395.812.4771500.41669.729.6230.421312.3571684.81542.53591.717.98861901.0441.93126903.358939.5474.7930244683906.6819.789.317516.017979.8267451.31213540299925984.2455.84326819.72920642.3465500297.73437065.752.123793282827.5829445.380.293564395.9597.34411963.7597.38380.67057428009942.562203.15730.34049827422305.53210.14438.99109.0420849.75228.012.028331124.7510549.244.54938.90841119.171139.63308.30331292.8038647.759657.193.9512128.38834.17817.6313456651508.0457.49830.04127770.3979135683086.35910.2912291048.7445.730.3472310.6290260.164845308.6710949.945685.283802292.618.83720638310.6513010.4003259758.744.912460416.337372780.721.7005747.434220522.490.25579647.9334.68162294.470.4611743216133.9113192391.8517.58610393402.016526.4174155.735738.6571.887813.90396.065164.812614.417869.3266216.15209.85278.245222846404420.422348.9257183.75649.52468210622.739.9395100.509662.0114.50.5857.2311081234.22865.910.662268.7758.09159.79280.1858.3332.177831.071032.3161.429.754433.6012344040955.2386955.343869.94271.4574.0374.371.01175.31995.701542.83937.1688.1396.679.18892100.419813.729.76303.737773.208728.5219.8145.3627115.63698924.11483.81727.85.8951397.612.311511.51667.629.7130.640312.3741682.81538.88360.7615.42131877.605663269.053133.6511.432612895047.7324.8220.26956.027953.2174978.511225662852946032.8847.58487359.391291689.33136339636.91466292.123.391514329963.261414423.650.591738184.3497.29162564.4897.02491.2004935687958.372230.30990.62177641966139.67208.13439.41108.9320610.23230.213.388331912.1610544.034.54929.02461830.411888.1314.61861306.6677658.211157.293.9512117.16833.15817.7536634718750.4157.72827.07148316.88153172503114.68480.4514721049.1645.710.6744550.9753570.279638464.715914.136266.022333781.3918.81817876820.978590.5385399746.084.92252025310103952.132.7080764.634530948.620.4074365.5645.56173926.920.6725854383314.6520047519.0517.37615359471.737647.5225132.865547.5677.882712.83227.1865139.097313.63773.2924178.49216.15254.141319941416821.032347.506183.99524.04423027500.138.1914121.9232534.8213.90.5357.9613181023.92795.110.381250.7159.3132.67296.7259.0632.295630.95721051.4140.7831.759231.4805388052972.5163970.220275.91302.5576.6477.960.97188.58265.300442.95157.2480.1789.49.28853.8103.088814.089.78303.327273.30618.8145.3966117.12338748.991495.21723.71393.51515.61664.329.5430.74621682.51539.59017.1219.5493034.627.42273249.283222.937.3014712221058.3424.7720.5726.037949.05180407.591231168093946660.8844.38487987.321291704.57135855921.28466609.223.494534329824.381413555.440.600199186.6497.35282520.3896.9061.1813535996976.132245.80360.62090741989522.68208.19439.5108.8920610.62230.063.596431890.2810549.154.54927.6791937.651894.07314.24521306.5839658.34157.313.9612109.64832.7822.1552634995429.6657.67827.03147582.87138306893114.42930.4502611050.3745.660.6756640.9717040.291087564.0515430.1836020.162396325.9319.01517614160.9735550.5517839680.444.952507331.298586858.512.761466.224392934.750.40807465.6946.25175754.350.6727684357453.7619927313.5217.01715341564.168106.8844145.173646.6277.409612.91067.3054136.832414.635668.2924220.79179.56259.141151341370821.739845.9642209.55527.88417882516.098.3506119.5964538.6314.270.5357.5112431122.42513.410.259274.6357.86136.33267.0459.232.241531.00931038.9138.3331.780631.4593401295975.504969.212274.11295.1876.7770.97188.41475.305342.65366.9779.9589.79.28852.7103.190213.579.87304.078273.349619.5145.2745116.48138750.611483.51726.31392.41519.1167129.630.75081676.51540.47633.1618.65943011.219.349813153.223185.6412.01312328933.6524.7921.03015.997993.1877834.391234570512952461.4842.55490300.481295970.28138939958.5468159.213.601944351871.121422505.510.593299184.2496.90772517.2696.99751.2014634602827.772253.14110.63499241972765.93210.19437.51109.3620684.29227.933.365351888.2110603.844.52937.9921926.151925.68315.33181305.7137662.258557.713.9312168.05826.67818.6037639757070.5258.05821.93148047.13139489143132.38380.447821058.5745.310.6761240.995710.275917413.3415077.6934917.392067499.5819.04516139130.9728630.5451189773.264.92517750.478609357.682.7023565.494549313.420.39437765.5946.34173620.310.6767984394194.4919866440.8617.05315228320.077937.355135.890746.5770.141814.24866.1057163.711114.201170.3828178.78218.28249.841998541428220.488448.772192.25524.75416006495.8510.385296.1737530.4715.380.5357.3312351005.82604.610.407243.3657.44135.8288.0958.3433.987929.41631046.6140.8931.927731.3146394852971.8988971.667773.57303.4378.7276.140.96189.40545.277342.55216.9279.6389.169.25860.8102.099913.979.82303.254973.340719.2144.4661116.96898747.831475.21732.313891516.2166429.5430.57841683.71540.97273.1911.75733349.368.260783171.153172.1912.157112728401.4524.7120.972667990.4791735.751231916197951700.1740.56489998.751300693.93137579874.564680063.505634351920.421425621.440.602831182.897.89082516.0996.71691.233436111781.822255.4220.62713341965286.06209.24437.68109.2320679.68228.942.974271957.7710587.34.52931.82231883.761912.74316.03281301.1811660.213257.623.9312172.92828.01816.7562640853365.5458822.5149647.68130980973116.09090.4575541057.7445.340.6721150.9750910.247825394.4913370.3334685.852077119.7619.07717529040.9739840.630639767.994.912527084.8712418451.712.6730366.084569476.860.38922365.4946.25172228.340.6803954403267.4219842969.2817.07915403597.247817.064141.470546.2175.52413.23317.149139.824115.12666.083218.91224.31256.242051441404721.359346.7815181.83515.11415428500.1183407519.3656106.6518527.8015.110.5358.7612381024.82528.710.373270.7657.52135.56256.4558.6632.175831.07271059136.4230.249433.0514404463974.985966.760673.24303.6375.578.850.97183.9495.434142.47987.158088.919.26879.6102.764613.689.81301.919273.619619.6144.9144117.22198864.781479.11731.21391.71513.51664.229.6630.72471677.61543.6OpenBenchmarking.org

Stress-NG

Test: MMAP

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: MMAPsmt bsmt asmt csmt dno smt ano smt bcba2K4K6K8K10K9017.128360.767633.167273.194520.483591.711668.921664.751663.081. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

oneDNN

Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUcno smt ano smt babsmt dsmt asmt csmt b5101520253.830176.192577.988618.745769.1957011.7573015.4210018.6594019.54900MIN: 2.72MIN: 3.65MIN: 3.88MIN: 3.65MIN: 4.13MIN: 8.17MIN: 10.4MIN: 11.23MIN: 10.671. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUcbano smt bno smt asmt csmt bsmt asmt d7001400210028003500669.15671.65674.09901.04930.263011.213034.623187.003349.36MIN: 661.71MIN: 664.19MIN: 667.01MIN: 864.28MIN: 898.89MIN: 2853.26MIN: 2821.2MIN: 3034.82MIN: 3325.751. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUcbno smt bano smt asmt bsmt asmt dsmt c36912151.886861.923401.931262.015812.040037.422707.605668.260789.34981MIN: 1.68MIN: 1.72MIN: 1.77MIN: 1.81MIN: 1.78MIN: 6.44MIN: 6.54MIN: 7.09MIN: 7.731. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUbcano smt bno smt asmt csmt dsmt bsmt a7001400210028003500670.20671.23671.69903.36913.203153.223171.153249.283269.05MIN: 663.54MIN: 662.9MIN: 664.46MIN: 874.93MIN: 884.92MIN: 3059.88MIN: 3148.29MIN: 3226.78MIN: 3243.111. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUcbano smt bno smt asmt asmt dsmt csmt b7001400210028003500667.95668.95675.92939.55973.323133.653172.193185.643222.93MIN: 660.93MIN: 662.29MIN: 668.99MIN: 904.78MIN: 937.3MIN: 3037.06MIN: 3155.85MIN: 2949.58MIN: 2927.411. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUabcno smt bno smt asmt bsmt asmt csmt d36912153.114974.278584.397204.793024.878837.3014711.4326012.0130012.15710MIN: 2.47MIN: 3.37MIN: 3.21MIN: 3.4MIN: 3.53MIN: 5.77MIN: 7.59MIN: 8.02MIN: 8.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Stress-NG

Test: Context Switching

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Context Switchingno smt ano smt bacbsmt asmt dsmt csmt b10M20M30M40M50M47222624.4944683906.6818941003.9716862185.5416313126.8612895047.7312728401.4512328933.6512221058.341. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Stress-NG

Test: NUMA

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: NUMAbacsmt asmt csmt bsmt dno smt ano smt b110220330440550498.67483.90478.0524.8224.7924.7724.7120.5119.781. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUbacno smt ano smt bsmt asmt bsmt dsmt c5101520257.282437.357467.381169.252929.3175120.2695020.5720020.9726021.03010MIN: 6.58MIN: 4.85MIN: 6.77MIN: 7.79MIN: 8.07MIN: 17.68MIN: 18.25MIN: 18.21MIN: 17.961. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUsmt csmt dno smt ano smt bsmt asmt bcba481216205.996.006.016.016.026.0315.1015.5416.30MIN: 5.13 / MAX: 31.29MIN: 5.21 / MAX: 25.51MIN: 5.2 / MAX: 37.8MIN: 5.02 / MAX: 36.88MIN: 5.27 / MAX: 25.12MIN: 5.17 / MAX: 38.35MIN: 6.94 / MAX: 60.59MIN: 8.28 / MAX: 57.72MIN: 7.91 / MAX: 51.621. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUsmt csmt dno smt bno smt asmt asmt bcba2K4K6K8K10K7993.187990.477979.827979.057953.217949.053174.043085.532941.471. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

Stress-NG

Test: Pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Pthreadsmt bcabsmt dsmt csmt ano smt ano smt b40K80K120K160K200K180407.59109609.15109397.78109356.7891735.7577834.3974978.5168076.0367451.301. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

RocksDB

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 7.9.2Test: Random Readsmt csmt dsmt bsmt ano smt bno smt aacb300M600M900M1200M1500M1234570512123191619712311680931225662852121354029912096110554682314344680697924668888881. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Stress-NG

Test: Matrix Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Matrix Mathsmt csmt dsmt bsmt ano smt ano smt bcab200K400K600K800K1000K952461.48951700.17946660.88946032.88932248.18925984.24382328.50382305.69382304.041. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Stress-NG

Test: CPU Cache

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: CPU Cachecabno smt bsmt asmt bsmt cno smt asmt d2040608010097.0477.5167.2155.8447.5844.3842.5540.9440.561. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: CPU Stresssmt csmt dsmt bsmt ano smt ano smt bcba110K220K330K440K550K490300.48489998.75487987.32487359.39328297.04326819.72217304.19217072.27205134.871. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Stress-NG

Test: Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Vector Mathsmt dsmt csmt bsmt ano smt bno smt aacb300K600K900K1200K1500K1300693.931295970.281291704.571291689.33920642.34920216.27556875.59556833.50556797.271. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Stress-NG

Test: Mutex

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Mutexsmt csmt dsmt asmt bno smt bno smt abca30M60M90M120M150M138939958.50137579874.56136339636.91135855921.2865500297.7363581395.6760031543.9759929401.4059479783.641. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Stress-NG

Test: Crypto

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Cryptosmt csmt dsmt bsmt ano smt bno smt abca100K200K300K400K500K468159.21468006.00466609.22466292.12437065.75435615.35203147.15203095.44203073.151. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

oneDNN

Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUbacno smt bno smt asmt asmt bsmt dsmt c0.81041.62082.43123.24164.0521.562571.564611.567422.123792.196453.391513.494533.505633.60194MIN: 1.41MIN: 1.41MIN: 1.39MIN: 1.9MIN: 2MIN: 2.93MIN: 3.11MIN: 3.19MIN: 3.081. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Stress-NG

Test: SENDFILE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: SENDFILEsmt dsmt csmt asmt bno smt ano smt babc900K1800K2700K3600K4500K4351920.424351871.124329963.264329824.383284433.203282827.501950323.961913590.771891202.371. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Stress-NG

Test: Function Call

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Function Callsmt dsmt csmt asmt bno smt bno smt acab300K600K900K1200K1500K1425621.441422505.511414423.651413555.44829445.38829106.63621041.93621015.34621003.921. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUcbano smt bno smt asmt asmt csmt bsmt d0.13560.27120.40680.54240.6780.2629200.2633730.2639970.2935640.3166650.5917380.5932990.6001990.602831MIN: 0.2MIN: 0.2MIN: 0.18MIN: 0.22MIN: 0.24MIN: 0.43MIN: 0.39MIN: 0.38MIN: 0.481. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Stress-NG

Test: Atomic

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Atomicno smt ano smt bbsmt bsmt asmt ccsmt da90180270360450400.03395.95223.29186.64184.34184.24183.33182.80174.721. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamsmt dno smt asmt bno smt bsmt asmt cacb2040608010097.8997.4097.3597.3497.2996.9142.9642.9242.83

Stress-NG

Test: Glibc Qsort Data Sorting

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Glibc Qsort Data Sortingsmt asmt bsmt csmt dno smt ano smt bbca60012001800240030002564.482520.382517.262516.091978.801963.751132.351125.861122.391. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamno smt ano smt bsmt asmt csmt bsmt dabc2040608010097.4497.3897.0297.0096.9196.7242.9942.9042.74

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUbacno smt ano smt bsmt bsmt asmt csmt d0.27750.5550.83251.111.38750.5519660.5552770.5568510.6643590.6705741.1813501.2004901.2014601.233400MIN: 0.49MIN: 0.53MIN: 0.53MIN: 0.56MIN: 0.55MIN: 1.08MIN: 1.04MIN: 1.08MIN: 1.081. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Stress-NG

Test: Glibc C String Functions

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Glibc C String Functionssmt dsmt bsmt asmt cno smt bno smt acab8M16M24M32M40M36111781.8235996976.1335687958.3734602827.7728009942.5626755146.6916537965.1416257100.2516168655.171. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamsmt dsmt csmt bsmt ano smt ano smt bcba50010001500200025002255.422253.142245.802230.312204.752203.161013.741012.351009.85

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPUcabno smt ano smt bsmt bsmt asmt dsmt c0.14290.28580.42870.57160.71450.2854320.2902000.2913870.3167790.3404980.6209070.6217760.6271330.634992MIN: 0.24MIN: 0.25MIN: 0.23MIN: 0.25MIN: 0.28MIN: 0.41MIN: 0.45MIN: 0.4MIN: 0.551. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Stress-NG

Test: Hash

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Hashsmt bsmt csmt asmt dno smt bno smt acba9M18M27M36M45M41989522.6841972765.9341966139.6741965286.0627422305.5327408413.1018961773.1818955118.1018954936.001. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUsmt cno smt bsmt dno smt asmt bsmt aacb50100150200250210.19210.14209.24208.82208.19208.1395.7695.5995.481. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPUsmt csmt dno smt ano smt bsmt asmt bacb2004006008001000437.51437.68438.29438.99439.41439.50962.10962.15962.63MIN: 400.05 / MAX: 473.91MIN: 394.89 / MAX: 478.58MIN: 416.93 / MAX: 496.86MIN: 427.57 / MAX: 484.31MIN: 410.81 / MAX: 465.4MIN: 424.22 / MAX: 477.66MIN: 879.24 / MAX: 1018.81MIN: 888.7 / MAX: 1017.92MIN: 893.43 / MAX: 1015.711. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPUsmt csmt dno smt ano smt bsmt asmt bcba20406080100109.36109.23109.08109.04108.93108.8949.7749.7249.721. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUno smt bno smt asmt csmt dsmt bsmt abac4K8K12K16K20K20849.7520836.1020684.2920679.6820610.6220610.239496.959494.229485.651. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUsmt cno smt bsmt dno smt asmt bsmt aacb110220330440550227.93228.01228.94229.46230.06230.21499.32500.30500.83MIN: 210.46 / MAX: 252.96MIN: 212.99 / MAX: 267.17MIN: 214.92 / MAX: 248.29MIN: 217.93 / MAX: 265.81MIN: 210.58 / MAX: 251.42MIN: 211.56 / MAX: 253.58MIN: 264.54 / MAX: 537.26MIN: 410.04 / MAX: 531.93MIN: 418.76 / MAX: 546.621. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

oneDNN

Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUcbano smt ano smt bsmt dsmt csmt asmt b0.80921.61842.42763.23684.0461.638601.729751.877772.022862.028332.974273.365353.388333.59643MIN: 1.2MIN: 1.27MIN: 1.23MIN: 1.56MIN: 1.43MIN: 2.3MIN: 2.7MIN: 2.76MIN: 2.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUbcano smt bno smt asmt csmt bsmt asmt d400800120016002000903.27906.14907.491124.751148.261888.211890.281912.161957.77MIN: 894.76MIN: 898.41MIN: 897.95MIN: 1091.36MIN: 1108.42MIN: 1860.29MIN: 1864.29MIN: 1891.03MIN: 1929.471. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUsmt csmt dno smt ano smt bsmt bsmt abac2K4K6K8K10K10603.8410587.3010556.9310549.2410549.1510544.034915.424914.174910.131. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUsmt csmt dno smt ano smt bsmt asmt bbac36912154.524.524.544.544.544.549.759.769.76MIN: 4.12 / MAX: 33.17MIN: 4.03 / MAX: 45.52MIN: 4.12 / MAX: 27.91MIN: 4.09 / MAX: 55.78MIN: 4.07 / MAX: 35.16MIN: 4.11 / MAX: 42.14MIN: 5.25 / MAX: 35.53MIN: 5.03 / MAX: 28.1MIN: 4.98 / MAX: 36.121. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamno smt ano smt bsmt csmt dsmt asmt babc2004006008001000941.24938.91937.99931.82929.02927.68440.85439.04438.44

oneDNN

Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUabcno smt bno smt asmt asmt dsmt csmt b400800120016002000911.25912.11915.081119.171151.251830.411883.761926.151937.65MIN: 903.01MIN: 902.43MIN: 906.26MIN: 1086.08MIN: 1070.35MIN: 1807.97MIN: 1850.75MIN: 1901.09MIN: 1908.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUacbno smt bno smt asmt asmt bsmt dsmt c400800120016002000909.69911.76917.081139.631147.341888.101894.071912.741925.68MIN: 901.1MIN: 901.88MIN: 909.14MIN: 1100.83MIN: 1109.85MIN: 1865.76MIN: 1870.66MIN: 1890.93MIN: 1901.21. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamsmt dsmt csmt asmt bno smt ano smt bbac70140210280350316.03315.33314.62314.25308.43308.30149.82149.74149.69

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamsmt asmt bsmt csmt dno smt bno smt acba300600900120015001306.671306.581305.711301.181292.801291.97625.55619.94619.75

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamsmt csmt dsmt bsmt ano smt ano smt bcba140280420560700662.26660.21658.34658.21649.30647.76316.63316.29314.84

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUsmt csmt dsmt bsmt ano smt bno smt abac132639526557.7157.6257.3157.2957.1957.1828.2327.9727.891. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUsmt csmt dno smt ano smt bsmt asmt babc2468103.933.933.953.953.953.968.118.138.13MIN: 3.61 / MAX: 42.82MIN: 3.61 / MAX: 23.62MIN: 3.61 / MAX: 38MIN: 3.68 / MAX: 42.53MIN: 3.61 / MAX: 34.38MIN: 3.66 / MAX: 32.83MIN: 5.39 / MAX: 69.87MIN: 5.35 / MAX: 55.84MIN: 3.83 / MAX: 59.871. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUsmt dsmt cno smt bno smt asmt asmt bacb3K6K9K12K15K12172.9212168.0512128.3812119.6612117.1612109.645908.895898.795894.271. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUsmt csmt dsmt bsmt ano smt ano smt bbac400800120016002000826.67828.01832.70833.15833.99834.171685.261701.701704.02MIN: 724.1 / MAX: 1006.75MIN: 716.19 / MAX: 1018.34MIN: 723.65 / MAX: 1031.69MIN: 725.84 / MAX: 1017.38MIN: 723.91 / MAX: 1011.94MIN: 732.01 / MAX: 1006.46MIN: 891.16 / MAX: 1979.37MIN: 1395.71 / MAX: 2063.97MIN: 828.99 / MAX: 1969.021. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamsmt bsmt csmt ano smt bsmt dno smt aabc2004006008001000822.16818.60817.75817.63816.76813.98401.78401.21400.04

Stress-NG

Test: Malloc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Mallocsmt dsmt csmt bsmt ano smt ano smt bbca140M280M420M560M700M640853365.54639757070.52634995429.66634718750.41456657338.84456651508.04314418461.02313768771.26312709034.051. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUsmt csmt dsmt asmt bno smt ano smt babc132639526558.0558.0057.7257.6757.5857.4928.4728.4228.331. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUsmt csmt dsmt bsmt ano smt ano smt babc400800120016002000821.93822.50827.03827.07828.67830.041671.461675.961679.03MIN: 725.25 / MAX: 1010.56MIN: 717.65 / MAX: 997.43MIN: 723.77 / MAX: 1003.25MIN: 724.84 / MAX: 1037.91MIN: 730.29 / MAX: 1036.1MIN: 722.6 / MAX: 1015.67MIN: 924.15 / MAX: 1977.46MIN: 1231.52 / MAX: 1967.75MIN: 865.58 / MAX: 1995.121. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUsmt dsmt asmt csmt bno smt ano smt bacb30K60K90K120K150K149647.68148316.88148047.13147582.87127833.52127770.3974495.1774486.0874353.411. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 7.9.2Test: Read While Writingsmt asmt csmt bsmt dabcno smt bno smt a3M6M9M12M15M15317250139489141383068913098097929618586203528316379791356876438311. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamsmt csmt dsmt asmt bno smt ano smt bbca70014002100280035003132.383116.093114.683114.433107.303086.361573.751571.831566.56

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUno smt bno smt aacsmt csmt bsmt asmt db0.13020.26040.39060.52080.6510.2912290.2916870.4154460.4171880.4478200.4502610.4514720.4575540.578466MIN: 0.27MIN: 0.27MIN: 0.4MIN: 0.4MIN: 0.37MIN: 0.37MIN: 0.4MIN: 0.34MIN: 0.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUsmt csmt dsmt bsmt ano smt bno smt abac20040060080010001058.571057.741050.371049.161048.741045.81541.03540.41535.781. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUsmt csmt dsmt bsmt ano smt bno smt abac2040608010045.3145.3445.6645.7145.7345.8688.6188.7189.46MIN: 39.35 / MAX: 73.19MIN: 39.4 / MAX: 73.83MIN: 38.82 / MAX: 75.65MIN: 39.78 / MAX: 73.33MIN: 39.68 / MAX: 86.83MIN: 39.29 / MAX: 91.13MIN: 47.57 / MAX: 124.67MIN: 44.2 / MAX: 132.86MIN: 42.16 / MAX: 123.41. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUno smt ano smt bcbasmt dsmt asmt bsmt c0.15210.30420.45630.60840.76050.3428360.3472310.3531750.3568750.3570170.6721150.6744550.6756640.676124MIN: 0.28MIN: 0.3MIN: 0.31MIN: 0.31MIN: 0.31MIN: 0.49MIN: 0.49MIN: 0.55MIN: 0.491. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUbacno smt ano smt bsmt bsmt dsmt asmt c0.2240.4480.6720.8961.120.5130680.5344500.5469910.5560690.6290260.9717040.9750910.9753570.995710MIN: 0.47MIN: 0.49MIN: 0.5MIN: 0.46MIN: 0.51MIN: 0.82MIN: 0.91MIN: 0.92MIN: 0.871. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUno smt ano smt bsmt dsmt csmt asmt bacb0.06880.13760.20640.27520.3440.1603610.1648450.2478250.2759170.2796380.2910870.3049720.3055990.305731MIN: 0.15MIN: 0.15MIN: 0.23MIN: 0.23MIN: 0.23MIN: 0.23MIN: 0.28MIN: 0.28MIN: 0.281. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Stress-NG

Test: MEMFD

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: MEMFDsmt bacbsmt asmt csmt dno smt bno smt a120240360480600564.05518.46507.97507.74464.70413.34394.49308.67303.561. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Stress-NG

Test: Memory Copying

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Memory Copyingbcasmt asmt bsmt csmt dno smt ano smt b4K8K12K16K20K20340.4020297.9120106.5115914.1015430.1815077.6913370.3311342.6910949.901. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Stress-NG

Test: Forking

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Forkingcbano smt bno smt asmt asmt bsmt csmt d14K28K42K56K70K64299.6258664.9758156.3645685.2843094.9636266.0236020.1634917.3934685.851. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Stress-NG

Test: Futex

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Futexno smt bno smt abacsmt bsmt asmt dsmt c800K1600K2400K3200K4000K3802292.603746361.522805836.522794694.372794473.752396325.932333781.392077119.762067499.581. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareno smt asmt dsmt csmt bno smt bsmt abca51015202519.1819.0819.0519.0218.8418.8210.6110.5910.571. (CXX) g++ options: -O3

RocksDB

Test: Read Random Write Random

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 7.9.2Test: Read Random Write Randomacbno smt ano smt bsmt asmt bsmt dsmt c600K1200K1800K2400K3000K2926458291002328919622079804206383117876821761416175290416139131. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUno smt bno smt asmt csmt bsmt dsmt abca0.26330.52660.78991.05321.31650.6513010.6642950.9728630.9735550.9739840.9785901.1669601.1691901.170040MIN: 0.62MIN: 0.63MIN: 0.92MIN: 0.92MIN: 0.92MIN: 0.93MIN: 1.07MIN: 1.07MIN: 1.071. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUno smt bno smt asmt asmt csmt bsmt dbca0.1560.3120.4680.6240.780.4003250.4035900.5385390.5451180.5517830.6306300.6890640.6926670.693367MIN: 0.38MIN: 0.38MIN: 0.48MIN: 0.45MIN: 0.49MIN: 0.48MIN: 0.64MIN: 0.65MIN: 0.641. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUno smt asmt csmt dno smt bsmt asmt bacb2K4K6K8K10K9784.099773.269767.999758.749746.089680.445750.745724.815720.901. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUno smt asmt cno smt bsmt dsmt asmt bacb2468104.904.904.914.914.924.958.348.378.38MIN: 4.46 / MAX: 56.52MIN: 4.5 / MAX: 29.95MIN: 4.49 / MAX: 34.72MIN: 4.51 / MAX: 27.27MIN: 4.52 / MAX: 34.8MIN: 4.54 / MAX: 24.23MIN: 6.61 / MAX: 55.54MIN: 6.83 / MAX: 50.24MIN: 6.4 / MAX: 32.331. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

Memcached

Set To Get Ratio: 1:5

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.18Set To Get Ratio: 1:5bcasmt dsmt asmt csmt bno smt bno smt a900K1800K2700K3600K4500K4162812.474155273.464143044.212527084.872520253.002517750.472507331.292460416.332444886.821. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Stress-NG

Test: System V Message Passing

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: System V Message Passingsmt dcabsmt asmt csmt bno smt ano smt b3M6M9M12M15M12418451.7110475486.3910473084.0910471889.9710103952.138609357.688586858.517402514.747372780.721. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUno smt ano smt bcabsmt dsmt csmt asmt b0.62131.24261.86392.48523.10651.650411.700571.822641.831471.841722.673032.702352.708072.76140MIN: 1.41MIN: 1.5MIN: 1.71MIN: 1.73MIN: 1.76MIN: 2.09MIN: 2.27MIN: 2.09MIN: 2.461. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Slow

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Slowsmt bsmt dsmt csmt ano smt bno smt abca153045607566.2266.0865.4964.6347.4347.1340.8640.7640.631. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Memcached

Set To Get Ratio: 1:10

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.18Set To Get Ratio: 1:10acbsmt dsmt csmt asmt bno smt ano smt b1.5M3M4.5M6M7.5M6861088.896839975.876792746.344569476.864549313.424530948.624392934.754244908.834220522.491. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUno smt ano smt bacbsmt dsmt csmt asmt b0.09180.18360.27540.36720.4590.2548450.2557960.3114050.3122890.3127210.3892230.3943770.4074300.408074MIN: 0.18MIN: 0.18MIN: 0.3MIN: 0.28MIN: 0.28MIN: 0.29MIN: 0.29MIN: 0.27MIN: 0.271. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Mediumsmt bsmt csmt asmt dno smt ano smt bcab153045607565.6965.5965.5665.4947.9747.9341.4741.4041.391. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

uvg266

Video Input: Bosphorus 4K - Video Preset: Slow

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Slowsmt csmt dsmt bsmt ano smt bno smt acab112233445546.3446.2546.2545.5634.6834.5929.4129.3729.29

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUsmt bsmt asmt csmt dno smt bno smt aacb40K80K120K160K200K175754.35173926.92173620.31172228.34162294.47160545.41112346.36112186.25111378.391. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUno smt bno smt asmt asmt bsmt csmt dcab0.16030.32060.48090.64120.80150.4611740.4623860.6725850.6727680.6767980.6803950.7085630.7115880.712495MIN: 0.43MIN: 0.42MIN: 0.52MIN: 0.53MIN: 0.53MIN: 0.53MIN: 0.67MIN: 0.68MIN: 0.681. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Memcached

Set To Get Ratio: 1:100

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.18Set To Get Ratio: 1:100abcsmt dsmt csmt asmt bno smt bno smt a1000K2000K3000K4000K5000K4878860.004876951.364852421.674403267.424394194.494383314.654357453.763216133.913192061.681. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Stress-NG

Test: Semaphores

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Semaphoressmt asmt bsmt csmt dabcno smt bno smt a4M8M12M16M20M20047519.0519927313.5219866440.8619842969.2818128283.2918100474.3618088584.6713192391.8513141129.681. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigsmt bsmt csmt dsmt ano smt bno smt acba61218243017.0217.0517.0817.3817.5917.6125.6825.7525.77

Stress-NG

Test: Poll

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Pollsmt dsmt asmt bsmt ccbano smt ano smt b3M6M9M12M15M15403597.2415359471.7315341564.1615228320.0712676101.4112661687.4612653709.6410458275.2410393402.011. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

OpenVKL

Benchmark: vklBenchmark Scalar

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.3.1Benchmark: vklBenchmark Scalarsmt bsmt csmt dsmt ano smt bno smt abac2004006008001000810793781764652647557556549MIN: 138 / MAX: 3650MIN: 139 / MAX: 3583MIN: 139 / MAX: 3776MIN: 139 / MAX: 3808MIN: 102 / MAX: 3990MIN: 101 / MAX: 4024MIN: 61 / MAX: 6019MIN: 61 / MAX: 5994MIN: 60 / MAX: 5475

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streambcano smt bsmt bsmt dsmt csmt ano smt a2468105.16335.16965.18126.41746.88447.06407.35507.52257.5856

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streambcano smt bsmt bsmt dsmt csmt ano smt a4080120160200193.53193.31192.88155.74145.17141.47135.89132.87131.76

uvg266

Video Input: Bosphorus 4K - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Mediumsmt asmt bsmt csmt dno smt bno smt abca112233445547.5646.6246.5746.2138.6538.3833.1333.1033.03

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamabcsmt asmt bsmt dno smt ano smt bsmt c2040608010099.1598.6298.5977.8877.4175.5272.1371.8970.14

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamabcsmt asmt bsmt dno smt ano smt bsmt c4812162010.0810.1410.1412.8312.9113.2313.8613.9014.25

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcno smt ano smt bsmt csmt dsmt asmt b2468105.30185.49805.50076.01186.06506.10577.14907.18657.3054

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcno smt ano smt bsmt csmt dsmt asmt b4080120160200188.54181.81181.72166.27164.81163.71139.82139.10136.83

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamcbasmt asmt cno smt bno smt asmt bsmt d4812162011.1611.1911.3613.6414.2014.4214.4614.6415.13

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamcbasmt asmt cno smt bno smt asmt bsmt d2040608010089.5589.3487.9673.2970.3869.3369.1168.2966.08

uvg266

Video Input: Bosphorus 1080p - Video Preset: Super Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Super Fastbacsmt bsmt dno smt bno smt asmt csmt a50100150200250239.92238.68237.96220.79218.91216.15181.67178.78178.49

uvg266

Video Input: Bosphorus 1080p - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Ultra Fastabcsmt dsmt csmt ano smt bno smt asmt b50100150200250240.98240.91238.77224.31218.28216.15209.85186.24179.56

Zstd Compression

Compression Level: 12 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression Speedbacno smt ano smt bsmt bsmt dsmt asmt c70140210280350332.0330.8330.1279.9278.2259.1256.2254.1249.81. (CC) gcc options: -O3 -pthread -lz

RocksDB

Test: Update Random

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 7.9.2Test: Update Randombacno smt ano smt bsmt dsmt csmt asmt b120K240K360K480K600K5455565443845435724620184522284205144199854131994115131. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

RocksDB

Test: Sequential Fill

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 7.9.2Test: Sequential Fillbcano smt ano smt bsmt csmt asmt dsmt b120K240K360K480K600K5453965445655422564657004640444142824141684140474137081. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamcabno smt bsmt cno smt asmt asmt dsmt b51015202516.5216.5816.6720.4220.4920.7421.0321.3621.74

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamcabno smt bsmt cno smt asmt asmt dsmt b142842567060.4960.2559.9248.9348.7748.1847.5146.7845.96

uvg266

Video Input: Bosphorus 1080p - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Very Fastcabsmt bno smt asmt csmt ano smt bsmt d50100150200250237.44234.95234.68209.55196.25192.25183.99183.75181.83

ClickHouse

100M Rows Hits Dataset, Second Run

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second Runno smt ano smt bbacsmt bsmt csmt asmt d140280420560700666.43649.52627.20625.91621.88527.88524.75524.04515.11MIN: 85.11 / MAX: 6666.67MIN: 86.46 / MAX: 6000MIN: 58.54 / MAX: 6000MIN: 56.13 / MAX: 7500MIN: 58.54 / MAX: 6666.67MIN: 90.63 / MAX: 6666.67MIN: 90.23 / MAX: 6000MIN: 90.5 / MAX: 6666.67MIN: 88.5 / MAX: 6000

RocksDB

Test: Random Fill

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 7.9.2Test: Random Fillcbano smt ano smt bsmt asmt bsmt csmt d110K220K330K440K550K5365515346815339274786294682104230274178824160064154281. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

ClickHouse

100M Rows Hits Dataset, First Run / Cold Cache

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold Cacheno smt ano smt bcbasmt bsmt asmt dsmt c140280420560700635.48622.73614.24610.79600.70516.09500.13500.12495.85MIN: 85.35 / MAX: 6000MIN: 83.22 / MAX: 5454.55MIN: 57.14 / MAX: 6666.67MIN: 58.14 / MAX: 6666.67MIN: 57.75 / MAX: 6000MIN: 89.55 / MAX: 6000MIN: 65.15 / MAX: 6000MIN: 69.61 / MAX: 6000MIN: 51.06 / MAX: 6000

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamsmt asmt bcsmt dbano smt ano smt bsmt c36912158.19148.35068.80049.36569.57939.59629.88999.939510.3852

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamsmt asmt bcsmt dbano smt ano smt bsmt c306090120150121.92119.60113.51106.65104.29104.12101.01100.5196.17

ClickHouse

100M Rows Hits Dataset, Third Run

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third Runno smt ano smt bcbasmt bsmt asmt csmt d140280420560700665.00662.01636.18628.37625.16538.63534.82530.47527.80MIN: 85.84 / MAX: 6000MIN: 86.33 / MAX: 6000MIN: 58.03 / MAX: 6666.67MIN: 58.37 / MAX: 6666.67MIN: 57.69 / MAX: 6000MIN: 89.82 / MAX: 6000MIN: 91.32 / MAX: 6000MIN: 92.02 / MAX: 5454.55MIN: 81.52 / MAX: 6000

VP9 libvpx Encoding

Speed: Speed 5 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 5 - Input: Bosphorus 4Kcbasmt csmt dno smt bno smt asmt bsmt a4812162017.4617.3717.3615.3815.1114.5014.4814.2713.901. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUsmt asmt bsmt csmt dno smt ano smt babc0.14850.2970.44550.5940.74250.530.530.530.530.570.580.650.660.66MIN: 0.5 / MAX: 24.2MIN: 0.5 / MAX: 9.61MIN: 0.5 / MAX: 9.15MIN: 0.5 / MAX: 8.86MIN: 0.5 / MAX: 13.02MIN: 0.5 / MAX: 12.8MIN: 0.32 / MAX: 20.68MIN: 0.32 / MAX: 19.99MIN: 0.31 / MAX: 22.671. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

uvg266

Video Input: Bosphorus 4K - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra Fastcbasmt dsmt ano smt asmt bsmt cno smt b163248648071.1370.6870.5658.7657.9657.7857.5157.3357.23

OpenVKL

Benchmark: vklBenchmark ISPC

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.3.1Benchmark: vklBenchmark ISPCsmt asmt bsmt dsmt cno smt bno smt aabc30060090012001500131812431238123511081098108910751066MIN: 391 / MAX: 3855MIN: 390 / MAX: 3501MIN: 392 / MAX: 3738MIN: 392 / MAX: 4332MIN: 297 / MAX: 4208MIN: 297 / MAX: 4284MIN: 179 / MAX: 7194MIN: 179 / MAX: 6442MIN: 180 / MAX: 6427

Zstd Compression

Compression Level: 8 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Compression Speedcbno smt bano smt asmt bsmt dsmt asmt c300600900120015001241.11239.31234.21233.81227.51122.41024.81023.91005.81. (CC) gcc options: -O3 -pthread -lz

Zstd Compression

Compression Level: 3 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3 - Compression Speedbcano smt bno smt asmt asmt csmt dsmt b70014002100280035003095.03049.43033.92865.92804.22795.12604.62528.72513.41. (CC) gcc options: -O3 -pthread -lz

Timed FFmpeg Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 6.0Time To Compilesmt bsmt dsmt asmt cno smt ano smt bbca369121510.2610.3710.3810.4110.6010.6612.4312.4712.57

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Very Fastacbsmt bsmt dno smt ano smt bsmt asmt c60120180240300296.93291.03290.59274.63270.76269.62268.77250.71243.361. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

uvg266

Video Input: Bosphorus 4K - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very Fastcabsmt ano smt bsmt bsmt dsmt cno smt a153045607569.0468.8268.7959.3058.0957.8657.5257.4457.13

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Slow

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Slowno smt bno smt acabsmt bsmt csmt dsmt a4080120160200159.79155.56140.10139.92139.07136.33135.80135.56132.671. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Super Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Super Fastabcsmt ano smt asmt cno smt bsmt bsmt d70140210280350307.49303.99301.40296.72288.41288.09280.18267.04256.451. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

uvg266

Video Input: Bosphorus 4K - Video Preset: Super Fast

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super Fastcabno smt asmt bsmt asmt dsmt cno smt b163248648069.9269.3369.0059.8359.2059.0658.6658.3458.33

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamcabno smt asmt dno smt bsmt bsmt asmt c81624324028.5728.6228.7131.9232.1832.1832.2432.3033.99

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamcabno smt asmt dno smt bsmt bsmt asmt c81624324034.9934.9334.8231.3231.0731.0731.0130.9629.42

Zstd Compression

Compression Level: 3, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3, Long Mode - Compression Speedsmt dsmt asmt csmt bno smt bno smt acba20040060080010001059.01051.41046.61038.91032.3955.6916.9909.4892.71. (CC) gcc options: -O3 -pthread -lz

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Mediumno smt bno smt abcasmt csmt asmt bsmt d4080120160200161.40159.63144.21143.81143.31140.89140.78138.33136.421. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamcbasmt cno smt asmt bsmt asmt dno smt b81624324035.1235.1034.8331.9331.9131.7831.7630.2529.75

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamcbasmt cno smt asmt bsmt asmt dno smt b81624324028.4728.4928.7131.3131.3331.4631.4833.0533.60

RocksDB

Test: Random Fill Sync

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 7.9.2Test: Random Fill Syncsmt dsmt bsmt csmt aabcno smt ano smt b90K180K270K360K450K4044634012953948523880523766013730023569223506733440401. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamno smt ano smt bsmt csmt asmt dsmt babc2004006008001000955.16955.24971.90972.52974.99975.501115.761118.441122.06

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamno smt bno smt asmt dsmt bsmt asmt cbac2004006008001000955.34956.01966.76969.21970.22971.671116.291116.431117.73

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very Fastbacsmt asmt bsmt csmt dno smt ano smt b2040608010081.6180.9080.3175.9174.1173.5773.2470.0269.941. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Ultra Fastacbsmt dsmt csmt asmt bno smt ano smt b70140210280350310.73309.64305.52303.63303.43302.55295.18278.62271.451. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Super Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super Fastcabsmt csmt bsmt asmt dno smt ano smt b2040608010084.5581.9080.6878.7276.7076.6475.5075.5074.031. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra Fastbacsmt dsmt asmt bsmt cno smt ano smt b2040608010084.7783.4582.7078.8577.9677.0076.1476.0574.371. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUsmt csmt asmt bsmt dno smt ano smt babc0.24530.49060.73590.98121.22650.960.970.970.971.011.011.091.091.09MIN: 0.87 / MAX: 9.72MIN: 0.87 / MAX: 9.78MIN: 0.87 / MAX: 10.96MIN: 0.86 / MAX: 13.31MIN: 0.86 / MAX: 8.97MIN: 0.86 / MAX: 8.72MIN: 0.49 / MAX: 19.01MIN: 0.48 / MAX: 25.82MIN: 0.49 / MAX: 22.061. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamcabno smt asmt csmt asmt bsmt dno smt b4080120160200197.66197.10196.54191.26189.41188.58188.41183.95175.32

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamcabno smt asmt csmt asmt bsmt dno smt b1.28282.56563.84845.13126.4145.05735.07155.08595.22625.27735.30045.30535.43415.7015

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamsmt dsmt csmt bno smt ano smt bsmt acba112233445542.4842.5542.6542.8142.8442.9547.2947.3547.46

VP9 libvpx Encoding

Speed: Speed 0 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 0 - Input: Bosphorus 4Kbcasmt ano smt bsmt dno smt asmt bsmt c2468107.717.707.687.247.167.157.046.976.921. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

uvg266

Video Input: Bosphorus 1080p - Video Preset: Slow

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Slowno smt bno smt abacsmt asmt dsmt bsmt c2040608010088.1387.1581.4181.1681.1080.1780.0079.9579.63

uvg266

Video Input: Bosphorus 1080p - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Mediumno smt ano smt bbacsmt bsmt asmt csmt d2040608010098.2196.6791.4791.3791.2989.7089.4089.1688.91

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUno smt ano smt bsmt csmt dsmt asmt babc36912159.189.189.259.269.289.2810.1010.1010.11MIN: 8.17 / MAX: 31.1MIN: 8.21 / MAX: 24.31MIN: 8.12 / MAX: 19.04MIN: 8.12 / MAX: 30.29MIN: 8.1 / MAX: 22.87MIN: 8.13 / MAX: 24.28MIN: 5.46 / MAX: 35.41MIN: 5.47 / MAX: 28.16MIN: 5.43 / MAX: 36.271. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

Zstd Compression

Compression Level: 8, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Compression Speedacbno smt bsmt dsmt cno smt asmt asmt b2004006008001000938.5926.9910.8892.0879.6860.8859.9853.8852.71. (CC) gcc options: -O3 -pthread -lz

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamno smt ano smt bsmt csmt dsmt asmt babc20406080100100.24100.42102.10102.76103.09103.19108.68109.11109.25

VP9 libvpx Encoding

Speed: Speed 0 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 0 - Input: Bosphorus 1080pcabno smt asmt asmt cno smt bsmt dsmt b4812162014.7614.6914.6714.2814.0813.9713.7213.6813.571. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

Zstd Compression

Compression Level: 19, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression Speedsmt bsmt csmt dsmt ano smt bno smt acba36912159.879.829.819.789.769.399.309.299.221. (CC) gcc options: -O3 -pthread -lz

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamsmt dsmt csmt ano smt bsmt bno smt abac70140210280350301.92303.25303.33303.74304.08304.21319.96319.98320.05

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamno smt ano smt bsmt asmt csmt bsmt dcba2040608010073.2073.2173.3173.3473.3573.6276.6277.3177.34

VVenC

Video Input: Bosphorus 1080p - Video Preset: Faster

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 1080p - Video Preset: Fastercabno smt ano smt b71421283530.0830.0429.8528.6928.521. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

Zstd Compression

Compression Level: 19 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression Speedno smt bno smt asmt dsmt bsmt ccbasmt a51015202519.819.819.619.519.219.119.119.118.81. (CC) gcc options: -O3 -pthread -lz

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamsmt csmt dsmt bno smt ano smt bsmt acba306090120150144.47144.91145.27145.35145.36145.40151.39151.60152.14

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamno smt bno smt asmt bsmt csmt asmt dabc306090120150115.64116.15116.48116.97117.12117.22119.21119.38119.70

Stress-NG

Test: Socket Activity

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.04Test: Socket Activityno smt ano smt bcasmt dbsmt bsmt asmt c2K4K6K8K10K8968.288924.108876.108873.588864.788851.658750.618748.998747.831. (CC) gcc options: -std=gnu99 -O2 -lm -lc -lcrypt -ldl -lrt -pthread

Zstd Compression

Compression Level: 19 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression Speedsmt ano smt bsmt bno smt asmt dsmt cacb300600900120015001495.21483.81483.51483.11479.11475.21472.61470.51467.81. (CC) gcc options: -O3 -pthread -lz

Zstd Compression

Compression Level: 12 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression Speedsmt csmt dno smt ano smt bsmt bsmt abca4008001200160020001732.31731.21728.01727.81726.31723.71716.71715.61704.81. (CC) gcc options: -O3 -pthread -lz

VVenC

Video Input: Bosphorus 4K - Video Preset: Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: Fastno smt bno smt aabc1.32642.65283.97925.30566.6325.8955.8905.8205.8095.8081. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

Zstd Compression

Compression Level: 19, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression Speedno smt bno smt asmt asmt bsmt dsmt ccab300600900120015001397.61395.81393.51392.41391.71389.01384.01383.71378.21. (CC) gcc options: -O3 -pthread -lz

VVenC

Video Input: Bosphorus 4K - Video Preset: Faster

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: Fasterno smt acbano smt b369121512.4812.4012.3912.3412.311. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

Zstd Compression

Compression Level: 3 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3 - Decompression Speedsmt bcbsmt csmt aasmt dno smt bno smt a300600900120015001519.11517.41516.61516.21515.61514.81513.51511.51500.41. (CC) gcc options: -O3 -pthread -lz

Zstd Compression

Compression Level: 8 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Decompression Speedsmt bno smt aano smt bsmt asmt dsmt ccb4008001200160020001671.01669.71669.31667.61664.31664.21664.01661.91651.01. (CC) gcc options: -O3 -pthread -lz

VP9 libvpx Encoding

Speed: Speed 5 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 5 - Input: Bosphorus 1080pno smt bsmt dno smt asmt bsmt csmt abca71421283529.7129.6629.6229.6029.5429.5429.5029.4629.371. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamno smt abcsmt cano smt bsmt dsmt asmt b71421283530.4230.4630.4930.5830.5930.6430.7230.7530.75

VVenC

Video Input: Bosphorus 1080p - Video Preset: Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 1080p - Video Preset: Fastcabno smt bno smt a369121512.4412.4412.4012.3712.361. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

Zstd Compression

Compression Level: 8, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Decompression Speedno smt asmt cno smt bsmt aasmt dsmt bcb4008001200160020001684.81683.71682.81682.51677.91677.61676.51675.41673.71. (CC) gcc options: -O3 -pthread -lz

Zstd Compression

Compression Level: 3, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 3, Long Mode - Decompression Speedsmt dno smt asmt ccsmt bsmt ano smt bba300600900120015001543.61542.51540.91540.91540.41539.51538.81537.51536.61. (CC) gcc options: -O3 -pthread -lz

Phoronix Test Suite v10.8.4