extra tests

2 x AMD EPYC 9754 128-Core testing with a Supermicro H13DSH (1.5 BIOS) and astdrmfb on AlmaLinux 9.2 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2308305-NE-EXTRATEST07&grs&sro.

extra testsProcessorMotherboardMemoryDiskGraphicsOSKernelCompilerFile-SystemScreen Resolutiondefgh2 x AMD EPYC 9124 16-Core @ 3.00GHz (32 Cores / 64 Threads)Supermicro H13DSH (1.5 BIOS)24 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07astdrmfbAlmaLinux 9.25.14.0-284.25.1.el9_2.x86_64 (x86_64)GCC 11.3.1 20221121ext41024x7682 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads)23 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKETOpenBenchmarking.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- d: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113e- e: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116- f: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116- g: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116- h: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116Java Details- OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)Python Details- Python 3.9.16Security Details- 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

extra testsstress-ng: Semaphoresstress-ng: MEMFDstress-ng: Pipedeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamstress-ng: x86_64 RdRandstress-ng: Hashstress-ng: Context Switchingstress-ng: Vector Shuffledeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamncnn: CPU - regnety_400mstress-ng: Floating Pointstress-ng: CPU Stressstress-ng: Function Calldeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamstress-ng: Fused Multiply-Addstress-ng: Matrix Mathstress-ng: Vector Floating Pointstress-ng: Zlibblender: Classroom - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlystress-ng: Vector Mathstress-ng: AVX-512 VNNIstress-ng: Memory Copyingstress-ng: Wide Vector Mathstress-ng: Glibc Qsort Data Sortingstress-ng: Mallocstress-ng: Glibc C String Functionsblender: Barbershop - CPU-Onlyblender: BMW27 - CPU-Onlyospray: gravity_spheres_volume/dim_512/scivis/real_timeembree: Pathtracer - Asian Dragonembree: Pathtracer - Asian Dragon Objospray: gravity_spheres_volume/dim_512/ao/real_timeembree: Pathtracer - Crowndeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamembree: Pathtracer ISPC - Asian Dragonembree: Pathtracer ISPC - Crownstress-ng: Pollblender: Fishy Cat - CPU-Onlyncnn: CPU - blazefaceembree: Pathtracer ISPC - Asian Dragon Objstress-ng: SENDFILEstress-ng: Cryptoospray: particle_volume/ao/real_timeospray: particle_volume/scivis/real_timencnn: CPU - shufflenet-v2stress-ng: Forkingstress-ng: AVL Treestress-ng: MMAPncnn: CPU - efficientnet-b0ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - mnasnetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - FastestDetdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamoidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyncnn: CPU - squeezenet_ssdospray: gravity_spheres_volume/dim_512/pathtracer/real_timeoidn: RTLightmap.hdr.4096x4096 - CPU-Onlydeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamstress-ng: CPU Cachencnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - vgg16ncnn: CPU - resnet50deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamstress-ng: Socket Activitybrl-cad: VGR Performance Metricncnn: CPU - googlenetncnn: CPU - vision_transformerdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamncnn: CPU - mobilenetdeepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streambuild-linux-kernel: defconfigdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamstress-ng: Futexstress-ng: Matrix 3D Mathdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamncnn: CPU - yolov4-tinydeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamliquid-dsp: 64 - 256 - 512stress-ng: NUMAstress-ng: Pthreaddeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamcassandra: Writesdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamliquid-dsp: 2 - 256 - 32deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamliquid-dsp: 4 - 256 - 512liquid-dsp: 16 - 256 - 57liquid-dsp: 8 - 256 - 32svt-av1: Preset 13 - Bosphorus 4Kstress-ng: Mixed Schedulerstress-ng: Mutexliquid-dsp: 1 - 256 - 32liquid-dsp: 2 - 256 - 512deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamliquid-dsp: 16 - 256 - 32liquid-dsp: 2 - 256 - 57liquid-dsp: 4 - 256 - 32deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamliquid-dsp: 1 - 256 - 512svt-av1: Preset 12 - Bosphorus 1080pliquid-dsp: 8 - 256 - 57liquid-dsp: 1 - 256 - 57deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamliquid-dsp: 16 - 256 - 512liquid-dsp: 4 - 256 - 57liquid-dsp: 8 - 256 - 512liquid-dsp: 32 - 256 - 32liquid-dsp: 32 - 256 - 512deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamsvt-av1: Preset 12 - Bosphorus 4Kliquid-dsp: 64 - 256 - 57liquid-dsp: 32 - 256 - 57deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamstress-ng: Atomicdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamsvt-av1: Preset 4 - Bosphorus 1080psvt-av1: Preset 12 - Bosphorus 4Kdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamstress-ng: System V Message Passingliquid-dsp: 64 - 256 - 32svt-av1: Preset 4 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 1080pospray: particle_volume/pathtracer/real_timestress-ng: Cloningsvt-av1: Preset 12 - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 4Kdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamsvt-av1: Preset 4 - Bosphorus 4Ksvt-av1: Preset 4 - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 1080psvt-av1: Preset 13 - Bosphorus 1080pkripke: dragonflydb: 50 - 1:100dragonflydb: 20 - 1:100dragonflydb: 10 - 1:100dragonflydb: 50 - 1:10dragonflydb: 20 - 1:10dragonflydb: 10 - 1:10vvenc: Bosphorus 1080p - Fastervvenc: Bosphorus 1080p - Fastvvenc: Bosphorus 4K - Fastervvenc: Bosphorus 4K - Fastnekrs: TurboPipe Periodicnekrs: Kershawspecfem3d: Water-layered Halfspacespecfem3d: Homogeneous Halfspacespecfem3d: Tomographic Modelspecfem3d: Layered Halfspacespecfem3d: Mount St. Helensremhos: Sample Remap Examplelaghos: Sedov Blast Wave, ube_922_hex.meshlaghos: Triple Point Problembuild-linux-kernel: allmodconfigdefgh92019395.13912.6220249488.61373.0279257.4237258.5599757.47724.7153355.8877114.282113.6578168.724785.485419.876319.8112013602.067218607.1217931974.9225006.7336.384933.511939.4188466.5427731.162661.225532151217.03173878.7106715.852944.5494.88122.7234239.63667964.1513428.641543291.91916.74137476652.9340991307.95372.7237.939.8131842.764137.987610.077437.677106.146748.474639.38414337787.7248.955.6340.5726857324.89107643.4910.863410.845313.961007.46410.891131.5514.7611.6410.711.291614.745467.765714.663268.16211.361.3724.2211.90020.6571.3514.013971.836213.9192776708.7213.658.1328.6926.5340.734524.5369504.3854464829.0355.05150.27623.5558.827916.99615.994735.2834.9317202.50191.1189890.94484022496.0710869.4920.71448.251235.7519.635650.9089436.974910.081399.122250466000018.3570043.7811.086890.07567.1456139.793423040244.914868834000794.0387795.85249884000650410000271730000195.82935640.36438280.163519500024900000641.6051186.6482140.576754939000010563000013650000094.619712652000419.85333120000052765000139.612719551000017428000096449000107380000038746000021.0894199.5231778600000123450000061.8053236.9962.100614.97442.83376851573.220456000005.053545.195176.6141170.3172.3537.1228140.20147.1102140.4568136.07137207200017583489.3814250093.7111860591.6515253621.5315179164.8611686474.2633.57219.16612.6786.76874704900001152090000034.82222748218.85382887614.87771034638.48977964914.50564525320.904263.85195.40866657136.27120.85157840183.632584.39051773.16721776.2195158.6627163.82082319.8756767.6346755.21631125.0335567.9413129.8585128.444778670488.1545096278.1379639504.69153882.19216.8622191.2371642.41517736.81159228.5514145.4309179841973.66989961.32605694.416620.9517.1622.261287349.0220114751.5672762.678239176.314849.6712254498.06215179957.0671.237.4449.0832205.7092184.10650.3927189.4439447.142227.0315189.194921326879.3610.0521.74187.00513678593.69464310.6646.660646.596143.7330826.861473.154118.1948.5234.7529.3331.8843.015.5308180.50235.4651182.80173.243.1856.8528.17141.5032.984930.309134.816228.7153348317.2328.7516.755.5250.4822.757543.9014111104.17643465155.3102.96285.128143.0441.08924.33169.016222.7747.3697135.64251.6625600.57442781554.4313265.6716.516660.50748.0914.588868.5055584.60048.1721122.248165961000014.2654645.3513.997571.40858.9987111.076418591355.064257284000963.8636972.747841506000534940000228660000188.74429901.53363805.322919000020808000772.2797224.2533168.901445698000088038000113830000113.462410553000490.98427689000044113000166.16031643500001509300008171500091602000033049000024.7597169.8872066300000107110000071.8982205.0972.054113.185169.93249.42457717311.2418271000004.58594.839161.1961161.56495.8373.624195.35793.2817.2759137.35997.2672137.52854.1359.731133.868123.523602.213775690998.4116.441681425122593.45421774.43841775.03945181.3554168.09242295.6075765.8523755.34611127.3913570.6331128.9729129.132478670864.0745263381.8496067858.09154301.84215.6588197.271775.48516299.64159300.6215229.2711183254707.86990014.15606558.8716624.0717.2122.641284285.0920046142.6772822.868234696.934847.93714509917.7215059237.8771.047.5248.9006206.166180.137650.0857185.3561446.4994224.8996189.315321392880.4110.1122.12184.23923224251.14457992.6246.559946.594847.0930923.931444.962268.3448.7334.2930.9830.744.075.5536179.77745.4849182.1363.253.0760.5228.26841.4732.717830.555634.537728.9472352745.5330.3116.5461.0155.2622.834643.7545109282.45635368256.1598.31285.518942.5444.146522.64668.372523.477.4283134.56841.6716597.37032722241.6713014.8116.155761.859650.3916.637760.0758585.33648.9799111.264365997000014.0954748.8514.067571.05458.8905112.423819809055.652557194000972.5049969.173641015000553290000223690000161.81629475.62363091.112921400020873000752.5783222.9581169.046645814000088120000114360000113.240410563000503.07627814000044144000166.52171665000001465100008234300091364000033009000024.652183.4662081700000105520000071.981204.5671.979413.445196.31949.26177746308.6918279000004.646588.809160.9131158.86483.01171.712202.49393.6577.2453137.93857.2233138.36234.1799.873134.062124.81602.993800762640.1197.94173499514.942613.0881780.23791778.36165150.4252166.73352405.8755770.5065761.86571128.8846566.7259129.4385129.384978673620.1445298625.91110432440.32154267.34220.9069202.3471782.95523898.45156381.6314854.856180789739.08989553.8604724.8416624.0717.3122.41288008.2620133541.1172825.568237581.374846.22719479964.33215429087.6171.977.5149.5123217.591193.050250.4014183.4023497.8976239.4187193.604121346079.310.0226.9193.42973761786.29462528.7346.656746.605457.6731064.951564.423664.3447.6735.9629.9231.2444.275.4661182.64175.4478183.37173.403.2858.6628.35211.5030.223533.077931.451931.7865334039.1129.2615.156.3453.6220.598148.4989110254.19639840457.72108.73256.164241.2142.038823.78218.584323.0587.3831135.39551.6492605.46722951631.9614658.7515.022366.522348.0814.415969.3271573.35828.0302124.407265914000014.3854906.4313.847372.1848.7387114.378418513453.115655708000969.2352969.884941641000542300000228520000191.66529932.2364035.572921900020660000756.6198224.6455167.423645782000088109000114550000113.019110576000490.15427984000044187000165.51041651800001510100008309000091457000033124000024.7947189.1642076600000105730000071.8214204.4471.761913.575179.40548.88417729966.1718276000004.615600.23161.1691139.87511.79575.15203.00792.6417.2111138.5947.2026138.75844.1249.831134.875125.22599.573786069338.66115.83159491222.342633.5921784.35591786.17565175.4863168.75062429.7418774.4054764.73741127.7925569.3208131.5432131.101378690548.4945265797.34110991931.6154293.33222.8586201.5971790.06518600.85158994.2513153.4958181626937.85990104.85605340.5316625.5717.1222.351285121.420123210.1472800.748234456.234850.99725705488.15215308424.8171.397.450.0879207.2492172.206850.9618187.4161532.4594225.8305194.274320251576.3310.0223.63184.45373745995.16461785.3646.756246.552845.2230591.671628.913749.4748.7637.5629.5530.8942.35.4481183.23655.4268184.09213.533.4658.4128.25371.5430.365132.922630.723132.5406361173.7129.5617.3958.8554.4719.744650.5975113347.77627057755.3693.15239.191544.1435.850827.88499.697423.0467.4589134.01591.6419608.16112880825.1115802.8614.564968.612348.8213.96571.5654567.8557.6734130.192965282000014.4655328.7112.828677.91698.6016116.192719095552.57755923000952.8689954.944541052000546690000228090000177.36329481.45363892.12920000020837000751.7219223.8503166.756145742000088042000114390000113.202710567000485.59327725000044183000164.66051653900001553600008274900091187000032921000024.6777194.8632072000000106500000071.5355203.4971.581512.913187.67748.51077761412.6118221000004.593581.067160.871209.53507.01773.25197.0394.8317.1163140.44037.1792139.21454.2049.901134.38124.695600.762OpenBenchmarking.org

Stress-NG

Test: Semaphores

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Semaphoresdefgh200M400M600M800M1000M92019395.13866657136.27775690998.40800762640.11786069338.661. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: MEMFD

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: MEMFDdefgh2004006008001000912.62120.85116.4497.94115.831. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Pipe

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Pipedefgh40M80M120M160M200M20249488.61157840183.63168142512.00173499514.94159491222.341. (CXX) g++ options: -O2 -std=gnu99 -lc

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamdefgh6001200180024003000373.032584.392593.452613.092633.59

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamdefgh400800120016002000257.421773.171774.441780.241784.36

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamdefgh400800120016002000258.561776.221775.041778.361786.18

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamdefgh11002200330044005500757.485158.665181.365150.435175.49

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamdefgh408012016020024.72163.82168.09166.73168.75

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 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamdefgh5001000150020002500355.892319.882295.612405.882429.74

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamdefgh170340510680850114.28767.63765.85770.51774.41

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamdefgh160320480640800113.66755.22755.35761.87764.74

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamdefgh2004006008001000168.721125.031127.391128.881127.79

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamdefgh12024036048060085.49567.94570.63566.73569.32

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamdefgh30609012015019.88129.86128.97129.44131.54

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamdefgh30609012015019.81128.44129.13129.38131.10

Stress-NG

Test: x86_64 RdRand

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: x86_64 RdRanddefgh20M40M60M80M100M12013602.0678670488.1578670864.0778673620.1478690548.491. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Hash

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Hashdefgh10M20M30M40M50M7218607.1245096278.1345263381.8445298625.9145265797.341. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Context Switching

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Context Switchingdefgh20M40M60M80M100M17931974.9279639504.6996067858.09110432440.32110991931.601. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Vector Shuffle

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Shuffledefgh30K60K90K120K150K25006.73153882.19154301.84154267.34154293.331. (CXX) g++ options: -O2 -std=gnu99 -lc

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamdefgh5010015020025036.38216.86215.66220.91222.86

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400mdefgh408012016020033.50191.23197.20202.34201.59MIN: 33.26 / MAX: 37.92MIN: 183.47 / MAX: 798.79MIN: 189.74 / MAX: 813.26MIN: 187.7 / MAX: 1161.84MIN: 191.08 / MAX: 1525.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

Test: Floating Point

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Floating Pointdefgh15K30K45K60K75K11939.4171642.4171775.4871782.9571790.061. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: CPU Stressdefgh110K220K330K440K550K88466.54517736.81516299.64523898.45518600.851. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Function Call

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Function Calldefgh30K60K90K120K150K27731.16159228.55159300.62156381.63158994.251. (CXX) g++ options: -O2 -std=gnu99 -lc

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamdefgh3K6K9K12K15K2661.2314145.4315229.2714854.8613153.50

Stress-NG

Test: Fused Multiply-Add

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Fused Multiply-Adddefgh40M80M120M160M200M32151217.03179841973.66183254707.86180789739.08181626937.851. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Matrix Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Matrix Mathdefgh200K400K600K800K1000K173878.70989961.32990014.15989553.80990104.851. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Vector Floating Point

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Floating Pointdefgh130K260K390K520K650K106715.85605694.40606558.87604724.84605340.531. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Zlib

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Zlibdefgh4K8K12K16K20K2944.5416620.9516624.0716624.0716625.571. (CXX) g++ options: -O2 -std=gnu99 -lc

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Classroom - Compute: CPU-Onlydefgh2040608010094.8817.1617.2117.3117.12

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Pabellon Barcelona - Compute: CPU-Onlydefgh306090120150122.7022.2622.6422.4022.35

Stress-NG

Test: Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Mathdefgh300K600K900K1200K1500K234239.601287349.021284285.091288008.261285121.401. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: AVX-512 VNNI

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: AVX-512 VNNIdefgh4M8M12M16M20M3667964.1520114751.5620046142.6720133541.1120123210.141. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Memory Copying

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Memory Copyingdefgh16K32K48K64K80K13428.6472762.6772822.8672825.5672800.741. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Wide Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Wide Vector Mathdefgh2M4M6M8M10M1543291.918239176.318234696.938237581.378234456.231. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Glibc Qsort Data Sorting

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Glibc Qsort Data Sortingdefgh10002000300040005000916.744849.604847.934846.224850.991. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Malloc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Mallocdefgh160M320M480M640M800M137476652.93712254498.06714509917.70719479964.33725705488.151. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Glibc C String Functions

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Glibc C String Functionsdefgh50M100M150M200M250M40991307.95215179957.06215059237.87215429087.61215308424.811. (CXX) g++ options: -O2 -std=gnu99 -lc

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Barbershop - Compute: CPU-Onlydefgh80160240320400372.7271.2371.0471.9771.39

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: BMW27 - Compute: CPU-Onlydefgh91827364537.937.447.527.517.40

OSPRay

Benchmark: gravity_spheres_volume/dim_512/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/scivis/real_timedefgh11223344559.8131849.0832048.9006049.5123050.08790

Embree

Binary: Pathtracer - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer - Model: Asian Dragondefgh5010015020025042.76205.71206.17217.59207.25MIN: 42.48 / MAX: 43.18MIN: 201.09 / MAX: 214.82MIN: 199.24 / MAX: 215.7MIN: 211.81 / MAX: 228.26MIN: 203.29 / MAX: 214.14

Embree

Binary: Pathtracer - Model: Asian Dragon Obj

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer - Model: Asian Dragon Objdefgh408012016020037.99184.11180.14193.05172.21MIN: 37.71 / MAX: 38.4MIN: 161.71 / MAX: 195.69MIN: 156.79 / MAX: 192.08MIN: 174.03 / MAX: 205.21MIN: 150.53 / MAX: 183.32

OSPRay

Benchmark: gravity_spheres_volume/dim_512/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/ao/real_timedefgh112233445510.0850.3950.0950.4050.96

Embree

Binary: Pathtracer - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer - Model: Crowndefgh408012016020037.68189.44185.36183.40187.42MIN: 37.26 / MAX: 39.44MIN: 184.47 / MAX: 200.52MIN: 180.8 / MAX: 195.2MIN: 179.05 / MAX: 191.46MIN: 183.21 / MAX: 193.83

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 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamdefgh120240360480600106.15447.14446.50497.90532.46

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer ISPC - Model: Asian Dragondefgh5010015020025048.47227.03224.90239.42225.83MIN: 48.1 / MAX: 49.28MIN: 217.82 / MAX: 238.94MIN: 217.06 / MAX: 234.36MIN: 232.82 / MAX: 253.03MIN: 221.04 / MAX: 232.51

Embree

Binary: Pathtracer ISPC - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer ISPC - Model: Crowndefgh408012016020039.38189.19189.32193.60194.27MIN: 38.86 / MAX: 40.97MIN: 184.06 / MAX: 202.84MIN: 183.01 / MAX: 202.71MIN: 188.25 / MAX: 201.2MIN: 188.82 / MAX: 203.12

Stress-NG

Test: Poll

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Polldefgh5M10M15M20M25M4337787.7221326879.3621392880.4121346079.3020251576.331. (CXX) g++ options: -O2 -std=gnu99 -lc

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Fishy Cat - Compute: CPU-Onlydefgh112233445548.9510.0510.1110.0210.02

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefacedefgh6121824305.6321.7422.1226.9023.63MIN: 5.53 / MAX: 5.95MIN: 21.34 / MAX: 78.44MIN: 21.92 / MAX: 24.06MIN: 21.88 / MAX: 899.43MIN: 21.98 / MAX: 379.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon Obj

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer ISPC - Model: Asian Dragon Objdefgh408012016020040.57187.01184.24193.43184.45MIN: 40.28 / MAX: 41.19MIN: 157.55 / MAX: 203.21MIN: 158.98 / MAX: 198.61MIN: 170.24 / MAX: 203.63MIN: 159.04 / MAX: 199.2

Stress-NG

Test: SENDFILE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: SENDFILEdefgh800K1600K2400K3200K4000K857324.893678593.693224251.143761786.293745995.161. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Crypto

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Cryptodefgh100K200K300K400K500K107643.49464310.66457992.62462528.73461785.361. (CXX) g++ options: -O2 -std=gnu99 -lc

OSPRay

Benchmark: particle_volume/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/ao/real_timedefgh112233445510.8646.6646.5646.6646.76

OSPRay

Benchmark: particle_volume/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/scivis/real_timedefgh112233445510.8546.6046.5946.6146.55

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2defgh132639526513.9643.7347.0957.6745.22MIN: 13.65 / MAX: 18.71MIN: 40.38 / MAX: 347.86MIN: 41.43 / MAX: 934.54MIN: 40.74 / MAX: 1797.58MIN: 40.32 / MAX: 296.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

Test: Forking

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Forkingdefgh7K14K21K28K35K1007.4630826.8630923.9331064.9530591.671. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: AVL Tree

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: AVL Treedefgh30060090012001500410.891473.151444.961564.421628.911. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: MMAP

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: MMAPdefgh90018002700360045001131.554118.192268.343664.343749.471. (CXX) g++ options: -O2 -std=gnu99 -lc

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0defgh112233445514.7648.5248.7347.6748.76MIN: 14.47 / MAX: 29.12MIN: 46.31 / MAX: 227.29MIN: 45.75 / MAX: 396.94MIN: 47.05 / MAX: 112.46MIN: 47.17 / MAX: 210.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3defgh91827364511.6434.7534.2935.9637.56MIN: 11.48 / MAX: 15.48MIN: 33.3 / MAX: 84.81MIN: 33.52 / MAX: 74.33MIN: 34.15 / MAX: 266.64MIN: 33.74 / MAX: 351.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnetdefgh71421283510.7029.3330.9829.9229.55MIN: 10.22 / MAX: 14.66MIN: 27.57 / MAX: 174.05MIN: 27.55 / MAX: 508.86MIN: 27.82 / MAX: 234.43MIN: 28.64 / MAX: 97.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2defgh71421283511.2931.8830.7031.2430.89MIN: 10.83 / MAX: 11.91MIN: 29.92 / MAX: 138.47MIN: 29.73 / MAX: 58.64MIN: 30.27 / MAX: 71.7MIN: 29.59 / MAX: 58.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDetdefgh102030405016.0043.0144.0744.2742.30MIN: 15.86 / MAX: 20.49MIN: 41.43 / MAX: 170.26MIN: 42.4 / MAX: 239.24MIN: 40.55 / MAX: 822.5MIN: 41.82 / MAX: 83.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamdefgh4812162014.74545.53085.55365.46615.4481

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamdefgh408012016020067.77180.50179.78182.64183.24

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamdefgh4812162014.66325.46515.48495.44785.4268

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamdefgh408012016020068.16182.80182.14183.37184.09

Intel Open Image Denoise

Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.0Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Onlydefgh0.79431.58862.38293.17723.97151.363.243.253.403.53

Intel Open Image Denoise

Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.0Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Onlydefgh0.77851.5572.33553.1143.89251.373.183.073.283.46

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssddefgh142842567024.2256.8560.5258.6658.41MIN: 23.8 / MAX: 28.97MIN: 55.3 / MAX: 146.7MIN: 59.42 / MAX: 125.02MIN: 55.23 / MAX: 333.73MIN: 57.55 / MAX: 98.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OSPRay

Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timedefgh71421283511.9028.1728.2728.3528.25

Intel Open Image Denoise

Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.0Run: RTLightmap.hdr.4096x4096 - Device: CPU-Onlydefgh0.34650.6931.03951.3861.73250.651.501.471.501.54

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamdefgh163248648071.3532.9832.7230.2230.37

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamdefgh81624324014.0130.3130.5633.0832.92

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamdefgh163248648071.8434.8234.5431.4530.72

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamdefgh81624324013.9228.7228.9531.7932.54

Stress-NG

Test: CPU Cache

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: CPU Cachedefgh170K340K510K680K850K776708.72348317.23352745.53334039.11361173.711. (CXX) g++ options: -O2 -std=gnu99 -lc

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18defgh71421283513.6528.7530.3129.2629.56MIN: 13.29 / MAX: 15.11MIN: 27.58 / MAX: 199.58MIN: 29.56 / MAX: 32.56MIN: 26.62 / MAX: 124.57MIN: 27.99 / MAX: 114.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnetdefgh481216208.1316.7016.5415.1017.39MIN: 7.95 / MAX: 8.44MIN: 15.23 / MAX: 164.75MIN: 15.67 / MAX: 44.81MIN: 14.22 / MAX: 74.43MIN: 14.86 / MAX: 374.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16defgh142842567028.5755.5261.0156.3458.85MIN: 27.98 / MAX: 32.46MIN: 50.63 / MAX: 278.46MIN: 55.16 / MAX: 391.41MIN: 50.98 / MAX: 172.01MIN: 55.68 / MAX: 98.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50defgh122436486026.5350.4855.2653.6254.47MIN: 26.13 / MAX: 30.95MIN: 49.07 / MAX: 131.05MIN: 53.64 / MAX: 170.04MIN: 51.72 / MAX: 288.16MIN: 51.64 / MAX: 145.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamdefgh91827364540.7322.7622.8320.6019.74

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamdefgh112233445524.5443.9043.7548.5050.60

Stress-NG

Test: Socket Activity

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Socket Activitydefgh20K40K60K80K100K9504.38111104.17109282.45110254.19113347.771. (CXX) g++ options: -O2 -std=gnu99 -lc

BRL-CAD

VGR Performance Metric

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.36VGR Performance Metricdefgh1.4M2.8M4.2M5.6M7M54464864346516353682639840462705771. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenetdefgh132639526529.0355.3056.1557.7255.36MIN: 27.97 / MAX: 36.49MIN: 52.38 / MAX: 300.85MIN: 53.89 / MAX: 379.5MIN: 52.79 / MAX: 429.12MIN: 54.42 / MAX: 115.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformerdefgh2040608010055.05102.9698.31108.7393.15MIN: 54.24 / MAX: 72.37MIN: 93.93 / MAX: 746.86MIN: 93.92 / MAX: 519.01MIN: 94.5 / MAX: 1869.82MIN: 88.26 / MAX: 206.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamdefgh60120180240300150.28285.13285.52256.16239.19

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenetdefgh102030405023.5543.0442.5441.2144.14MIN: 23.18 / MAX: 27.8MIN: 41.85 / MAX: 91.85MIN: 41.2 / MAX: 128.05MIN: 40.54 / MAX: 69.23MIN: 42.79 / MAX: 118.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamdefgh132639526558.8341.0944.1542.0435.85

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamdefgh71421283517.0024.3322.6523.7827.88

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamdefgh36912155.99479.01628.37258.58439.6974

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigdefgh81624324035.2822.7723.4723.0623.05

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamdefgh2468104.93177.36977.42837.38317.4589

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamdefgh4080120160200202.50135.64134.57135.40134.02

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamdefgh0.37610.75221.12831.50441.88051.11891.66251.67161.64921.6419

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamdefgh2004006008001000890.94600.57597.37605.47608.16

Stress-NG

Test: Futex

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Futexdefgh900K1800K2700K3600K4500K4022496.072781554.432722241.672951631.962880825.111. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Matrix 3D Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Matrix 3D Mathdefgh3K6K9K12K15K10869.4913265.6713014.8114658.7515802.861. (CXX) g++ options: -O2 -std=gnu99 -lc

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 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamdefgh51015202520.7116.5216.1615.0214.56

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 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamdefgh153045607548.2560.5161.8666.5268.61

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tinydefgh112233445535.7548.0950.3948.0848.82MIN: 34.32 / MAX: 45.5MIN: 44.42 / MAX: 108.3MIN: 44.47 / MAX: 465.37MIN: 42.94 / MAX: 393.57MIN: 45.36 / MAX: 93.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamdefgh51015202519.6414.5916.6414.4213.97

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamdefgh163248648050.9168.5160.0869.3371.57

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamdefgh130260390520650436.97584.60585.34573.36567.86

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamdefgh369121510.08138.17218.97998.03027.6734

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamdefgh30609012015099.12122.25111.26124.41130.19

Liquid-DSP

Threads: 64 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 512defgh140M280M420M560M700M5046600006596100006599700006591400006528200001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Stress-NG

Test: NUMA

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: NUMAdefgh51015202518.3514.2614.0914.3814.461. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Pthreaddefgh15K30K45K60K75K70043.7854645.3554748.8554906.4355328.711. (CXX) g++ options: -O2 -std=gnu99 -lc

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamdefgh4812162011.0914.0014.0713.8512.83

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamdefgh2040608010090.0871.4171.0572.1877.92

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 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamdefgh36912157.14568.99878.89058.73878.6016

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 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamdefgh306090120150139.79111.08112.42114.38116.19

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.1.3Test: Writesdefgh50K100K150K200K250K230402185913198090185134190955

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 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamdefgh132639526544.9155.0655.6553.1252.58

Liquid-DSP

Threads: 2 - Buffer Length: 256 - Filter Length: 32

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 2 - Buffer Length: 256 - Filter Length: 32defgh15M30M45M60M75M68834000572840005719400055708000559230001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamdefgh2004006008001000794.04963.86972.50969.24952.87

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamdefgh2004006008001000795.85972.75969.17969.88954.94

Liquid-DSP

Threads: 4 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 4 - Buffer Length: 256 - Filter Length: 512defgh11M22M33M44M55M49884000415060004101500041641000410520001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 16 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 57defgh140M280M420M560M700M6504100005349400005532900005423000005466900001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 8 - Buffer Length: 256 - Filter Length: 32

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 8 - Buffer Length: 256 - Filter Length: 32defgh60M120M180M240M300M2717300002286600002236900002285200002280900001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.6Encoder Mode: Preset 13 - Input: Bosphorus 4Kdefgh4080120160200195.83188.74161.82191.67177.361. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Stress-NG

Test: Mixed Scheduler

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Mixed Schedulerdefgh8K16K24K32K40K35640.3629901.5329475.6229932.2029481.451. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Mutex

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Mutexdefgh90K180K270K360K450K438280.16363805.32363091.11364035.57363892.101. (CXX) g++ options: -O2 -std=gnu99 -lc

Liquid-DSP

Threads: 1 - Buffer Length: 256 - Filter Length: 32

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 32defgh8M16M24M32M40M35195000291900002921400029219000292000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 2 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 2 - Buffer Length: 256 - Filter Length: 512defgh5M10M15M20M25M24900000208080002087300020660000208370001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamdefgh170340510680850641.61772.28752.58756.62751.72

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamdefgh50100150200250186.65224.25222.96224.65223.85

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamdefgh4080120160200140.58168.90169.05167.42166.76

Liquid-DSP

Threads: 16 - Buffer Length: 256 - Filter Length: 32

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 32defgh120M240M360M480M600M5493900004569800004581400004578200004574200001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 2 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 2 - Buffer Length: 256 - Filter Length: 57defgh20M40M60M80M100M105630000880380008812000088109000880420001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 4 - Buffer Length: 256 - Filter Length: 32

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 4 - Buffer Length: 256 - Filter Length: 32defgh30M60M90M120M150M1365000001138300001143600001145500001143900001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamdefgh30609012015094.62113.46113.24113.02113.20

Liquid-DSP

Threads: 1 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 512defgh3M6M9M12M15M12652000105530001056300010576000105670001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.6Encoder Mode: Preset 12 - Input: Bosphorus 1080pdefgh110220330440550419.85490.98503.08490.15485.591. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Liquid-DSP

Threads: 8 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 8 - Buffer Length: 256 - Filter Length: 57defgh70M140M210M280M350M3312000002768900002781400002798400002772500001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 1 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 57defgh11M22M33M44M55M52765000441130004414400044187000441830001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamdefgh4080120160200139.61166.16166.52165.51164.66

Liquid-DSP

Threads: 16 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 512defgh40M80M120M160M200M1955100001643500001665000001651800001653900001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 4 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 4 - Buffer Length: 256 - Filter Length: 57defgh40M80M120M160M200M1742800001509300001465100001510100001553600001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 8 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 8 - Buffer Length: 256 - Filter Length: 512defgh20M40M60M80M100M96449000817150008234300083090000827490001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 32 - Buffer Length: 256 - Filter Length: 32

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 32defgh200M400M600M800M1000M10738000009160200009136400009145700009118700001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 32 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 512defgh80M160M240M320M400M3874600003304900003300900003312400003292100001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamdefgh61218243021.0924.7624.6524.7924.68

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.6Encoder Mode: Preset 12 - Input: Bosphorus 4Kdefgh4080120160200199.52169.89183.47189.16194.861. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Liquid-DSP

Threads: 64 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 57defgh400M800M1200M1600M2000M177860000020663000002081700000207660000020720000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 32 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 57defgh300M600M900M1200M1500M123450000010711000001055200000105730000010650000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamdefgh163248648061.8171.9071.9871.8271.54

Stress-NG

Test: Atomic

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Atomicdefgh50100150200250236.99205.09204.56204.44203.491. (CXX) g++ options: -O2 -std=gnu99 -lc

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamdefgh163248648062.1072.0571.9871.7671.58

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.6Encoder Mode: Preset 4 - Input: Bosphorus 1080pdefgh4812162014.9713.1913.4513.5812.911. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 12 - Input: Bosphorus 4Kefgh4080120160200169.93196.32179.41187.681. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamdefgh112233445542.8349.4249.2648.8848.51

Stress-NG

Test: System V Message Passing

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: System V Message Passingdefgh1.7M3.4M5.1M6.8M8.5M6851573.207717311.247746308.697729966.177761412.611. (CXX) g++ options: -O2 -std=gnu99 -lc

Liquid-DSP

Threads: 64 - Buffer Length: 256 - Filter Length: 32

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 32defgh400M800M1200M1600M2000M204560000018271000001827900000182760000018221000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.6Encoder Mode: Preset 4 - Input: Bosphorus 4Kdefgh1.13692.27383.41074.54765.68455.0534.5804.6464.6154.5931. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.6Encoder Mode: Preset 13 - Input: Bosphorus 1080pdefgh130260390520650545.20594.84588.81600.23581.071. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OSPRay

Benchmark: particle_volume/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/pathtracer/real_timedefgh4080120160200176.61161.20160.91161.17160.87

Stress-NG

Test: Cloning

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Cloningdefgh300600900120015001170.311161.561158.861139.871209.531. (CXX) g++ options: -O2 -std=gnu99 -lc

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 12 - Input: Bosphorus 1080pefgh110220330440550495.83483.01511.80507.021. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.6Encoder Mode: Preset 8 - Input: Bosphorus 4Kdefgh2040608010072.3573.6271.7175.1573.251. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 13 - Input: Bosphorus 4Kefgh4080120160200195.36202.49203.01197.031. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 8 - Input: Bosphorus 4Kefgh2040608010093.2893.6692.6494.831. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamdefgh2468107.12287.27597.24537.21117.1163

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamdefgh306090120150140.20137.36137.94138.59140.44

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamdefgh2468107.11027.26727.22337.20267.1792

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamdefgh306090120150140.46137.53138.36138.76139.21

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 4 - Input: Bosphorus 4Kefgh0.94591.89182.83773.78364.72954.1354.1794.1244.2041. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 4 - Input: Bosphorus 1080pefgh36912159.7319.8739.8319.9011. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.6Encoder Mode: Preset 8 - Input: Bosphorus 1080pdefgh306090120150136.07133.87134.06134.88134.381. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 8 - Input: Bosphorus 1080pefgh306090120150123.52124.81125.22124.701. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 13 - Input: Bosphorus 1080pefgh130260390520650602.21602.99599.57600.761. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Kripke

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.6d80M160M240M320M400M3720720001. (CXX) g++ options: -O3 -fopenmp -ldl

Dragonflydb

Clients Per Thread: 50 - Set To Get Ratio: 1:100

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 50 - Set To Get Ratio: 1:100d4M8M12M16M20M17583489.381. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Dragonflydb

Clients Per Thread: 20 - Set To Get Ratio: 1:100

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 20 - Set To Get Ratio: 1:100d3M6M9M12M15M14250093.711. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Dragonflydb

Clients Per Thread: 10 - Set To Get Ratio: 1:100

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:100d3M6M9M12M15M11860591.651. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Dragonflydb

Clients Per Thread: 50 - Set To Get Ratio: 1:10

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 50 - Set To Get Ratio: 1:10d3M6M9M12M15M15253621.531. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Dragonflydb

Clients Per Thread: 20 - Set To Get Ratio: 1:10

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 20 - Set To Get Ratio: 1:10d3M6M9M12M15M15179164.861. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Dragonflydb

Clients Per Thread: 10 - Set To Get Ratio: 1:10

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:10d3M6M9M12M15M11686474.261. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

VVenC

Video Input: Bosphorus 1080p - Video Preset: Faster

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: Fasterd81624324033.571. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

VVenC

Video Input: Bosphorus 1080p - Video Preset: Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: Fastd51015202519.171. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

VVenC

Video Input: Bosphorus 4K - Video Preset: Faster

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: Fasterd369121512.681. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

VVenC

Video Input: Bosphorus 4K - Video Preset: Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: Fastd2468106.7681. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

nekRS

Input: TurboPipe Periodic

OpenBenchmarking.orgflops/rank, More Is BetternekRS 23.0Input: TurboPipe Periodicd1600M3200M4800M6400M8000M74704900001. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi

nekRS

Input: Kershaw

OpenBenchmarking.orgflops/rank, More Is BetternekRS 23.0Input: Kershawd2000M4000M6000M8000M10000M115209000001. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi

SPECFEM3D

Model: Water-layered Halfspace

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Water-layered Halfspaced81624324034.821. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi

SPECFEM3D

Model: Homogeneous Halfspace

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Homogeneous Halfspaced51015202518.851. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi

SPECFEM3D

Model: Tomographic Model

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Tomographic Modeld4812162014.881. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi

SPECFEM3D

Model: Layered Halfspace

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Layered Halfspaced91827364538.491. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi

SPECFEM3D

Model: Mount St. Helens

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Mount St. Helensd4812162014.511. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi

Remhos

Test: Sample Remap Example

OpenBenchmarking.orgSeconds, Fewer Is BetterRemhos 1.0Test: Sample Remap Exampled51015202520.901. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi

Laghos

Test: Sedov Blast Wave, ube_922_hex.mesh

OpenBenchmarking.orgMajor Kernels Total Rate, More Is BetterLaghos 3.1Test: Sedov Blast Wave, ube_922_hex.meshd60120180240300263.851. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi

Laghos

Test: Triple Point Problem

OpenBenchmarking.orgMajor Kernels Total Rate, More Is BetterLaghos 3.1Test: Triple Point Problemd4080120160200195.401. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi

Phoronix Test Suite v10.8.5