deepspaarse 17

AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG STRIX X670E-E GAMING WIFI (1905 BIOS) and NVIDIA GeForce RTX 3080 10GB on Ubuntu 23.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2403151-PTS-DEEPSPAA58&sor&gru.

deepspaarse 17ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen ResolutionabcdeAMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads)ASUS ROG STRIX X670E-E GAMING WIFI (1905 BIOS)AMD Device 14d82 x 16GB DRAM-6000MT/s G Skill F5-6000J3038F16G2000GB Samsung SSD 980 PRO 2TB + Western Digital WD_BLACK SN850X 2000GBNVIDIA GeForce RTX 3080 10GBNVIDIA GA102 HD AudioDELL U2723QEIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 23.106.7.0-060700-generic (x86_64)GNOME Shell 45.2X Server 1.21.1.7NVIDIA 550.54.144.6.0OpenCL 3.0 CUDA 12.4.89GCC 13.2.0ext43840x2160OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseProcessor Details- Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601206Python Details- Python 3.11.6Security Details- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

deepspaarse 17deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamabcde21.598618.8124929.8526300.8741280.6164195.29052379.95131437.55234.09597.6108279.4430194.4294126.339999.0032191.7023117.664337.652231.5733430.4254112.865521.509718.5981369.726953.14968.59253.320628.49285.11493.35180.69371900.4795131.376028.61595.137863.268110.095941.70728.4942212.447931.658818.57388.8521371.570253.761021.250518.6562928.1657301.2353280.4277195.96012376.57191438.2714.10987.6089280.4549195.4038126.676399.497192.506116.349237.775931.6614431.8114112.64921.473418.5403376.363953.59458.60793.316828.50515.09763.35590.69321894.2203131.40928.50765.11263.122710.04641.538.5902211.751231.570618.51388.8696370.827553.929821.279918.6913927.609300.1138281.0267195.50052385.7691444.83334.08537.606280.98196.3357127.025199.4073192.6076116.563937.763931.6577430.8886112.252321.315318.6145375.865953.4948.61283.328728.4585.10953.34250.68991905.4156131.458728.45595.08862.946610.054641.52448.5743211.81931.574318.55398.9004374.077553.714521.244518.7156920.2774301.7005280.4486196.02372381.27161420.74454.07917.5982280.5104196.3727126.411299.4984192.3054115.256637.715631.7017430.6637112.569121.452318.6535376.522453.42478.68173.311328.51455.09633.34880.70191908.6078131.595728.50835.087163.260810.04641.58198.6715212.090431.530818.56388.8748371.94853.602421.311918.6648926.3913301.1689280.5353195.74732359.66051433.24264.09627.6006282.4848195.9355126.725899.1040190.7916117.207937.605731.5591429.1529112.534421.424718.6168374.965353.56948.62443.317628.50615.10303.38000.69571900.5641131.549428.30705.098163.096610.085741.91838.5269212.710331.673818.62948.8780372.492353.7068OpenBenchmarking.org

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamaecbd510152025SE +/- 0.10, N = 3SE +/- 0.03, N = 321.6021.3121.2821.2521.24

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamadceb510152025SE +/- 0.03, N = 3SE +/- 0.02, N = 318.8118.7218.6918.6618.66

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 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabced2004006008001000SE +/- 1.67, N = 3SE +/- 1.13, N = 3929.85928.17927.61926.39920.28

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 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamdbeac70140210280350SE +/- 1.34, N = 3SE +/- 0.77, N = 3301.70301.24301.17300.87300.11

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamcaedb60120180240300SE +/- 0.32, N = 3SE +/- 0.54, N = 3281.03280.62280.54280.45280.43

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamdbeca4080120160200SE +/- 0.46, N = 3SE +/- 0.13, N = 3196.02195.96195.75195.50195.29

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamcdabe5001000150020002500SE +/- 2.33, N = 3SE +/- 13.77, N = 32385.772381.272379.952376.572359.66

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamcbaed30060090012001500SE +/- 2.00, N = 3SE +/- 6.10, N = 31444.831438.271437.551433.241420.74

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Streambeacd0.92471.84942.77413.69884.6235SE +/- 0.0043, N = 3SE +/- 0.0014, N = 34.10984.09624.09594.08534.0791

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Streamabced246810SE +/- 0.0050, N = 3SE +/- 0.0028, N = 37.61087.60897.60607.60067.5982

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamecdba60120180240300SE +/- 0.79, N = 3SE +/- 0.35, N = 3282.48280.98280.51280.45279.44

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamdceba4080120160200SE +/- 0.48, N = 3SE +/- 0.40, N = 3196.37196.34195.94195.40194.43

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamcebda306090120150SE +/- 0.88, N = 3SE +/- 0.41, N = 3127.03126.73126.68126.41126.34

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamdbcea20406080100SE +/- 0.14, N = 3SE +/- 0.04, N = 399.5099.5099.4199.1099.00

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamcbdae4080120160200SE +/- 0.07, N = 3SE +/- 0.41, N = 3192.61192.51192.31191.70190.79

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamaecbd306090120150SE +/- 0.36, N = 3SE +/- 0.10, N = 3117.66117.21116.56116.35115.26

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streambcdae918273645SE +/- 0.04, N = 3SE +/- 0.02, N = 337.7837.7637.7237.6537.61

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamdbcae714212835SE +/- 0.01, N = 3SE +/- 0.02, N = 331.7031.6631.6631.5731.56

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streambcdae90180270360450SE +/- 0.23, N = 3SE +/- 0.70, N = 3431.81430.89430.66430.43429.15

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabdec306090120150SE +/- 0.54, N = 3SE +/- 0.18, N = 3112.87112.65112.57112.53112.25

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabdec510152025SE +/- 0.08, N = 3SE +/- 0.08, N = 321.5121.4721.4521.4221.32

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamdecab510152025SE +/- 0.03, N = 3SE +/- 0.01, N = 318.6518.6218.6118.6018.54

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamaecbd80160240320400SE +/- 1.41, N = 3SE +/- 0.28, N = 3369.73374.97375.87376.36376.52

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamadceb1224364860SE +/- 0.08, N = 3SE +/- 0.06, N = 353.1553.4253.4953.5753.59

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 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabced246810SE +/- 0.0153, N = 3SE +/- 0.0104, N = 38.59258.60798.61288.62448.6817

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 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamdbeac0.7491.4982.2472.9963.745SE +/- 0.0148, N = 3SE +/- 0.0086, N = 33.31133.31683.31763.32063.3287

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamcabed714212835SE +/- 0.03, N = 3SE +/- 0.05, N = 328.4628.4928.5128.5128.51

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamdbeca1.15092.30183.45274.60365.7545SE +/- 0.0121, N = 3SE +/- 0.0035, N = 35.09635.09765.10305.10955.1149

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamcdabe0.76051.5212.28153.0423.8025SE +/- 0.0036, N = 3SE +/- 0.0197, N = 33.34253.34883.35183.35593.3800

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamcbaed0.15790.31580.47370.63160.7895SE +/- 0.0010, N = 3SE +/- 0.0030, N = 30.68990.69320.69370.69570.7019

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Streambaecd400800120016002000SE +/- 0.71, N = 3SE +/- 1.74, N = 31894.221900.481900.561905.421908.61

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Streamabced306090120150SE +/- 0.09, N = 3SE +/- 0.05, N = 3131.38131.41131.46131.55131.60

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamecbda714212835SE +/- 0.08, N = 3SE +/- 0.04, N = 328.3128.4628.5128.5128.62

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamdceba1.1562.3123.4684.6245.78SE +/- 0.0126, N = 3SE +/- 0.0107, N = 35.08715.08805.09815.11205.1378

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamcebda1428425670SE +/- 0.43, N = 3SE +/- 0.21, N = 362.9563.1063.1263.2663.27

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streambdcea3691215SE +/- 0.01, N = 3SE +/- 0.00, N = 310.0510.0510.0510.0910.10

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamcbdae1020304050SE +/- 0.02, N = 3SE +/- 0.09, N = 341.5241.5341.5841.7141.92

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamaecbd246810SE +/- 0.0262, N = 3SE +/- 0.0075, N = 38.49428.52698.57438.59028.6715

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streambcdae50100150200250SE +/- 0.21, N = 3SE +/- 0.13, N = 3211.75211.82212.09212.45212.71

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamdbcae714212835SE +/- 0.01, N = 3SE +/- 0.02, N = 331.5331.5731.5731.6631.67

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streambcdae510152025SE +/- 0.01, N = 3SE +/- 0.03, N = 318.5118.5518.5618.5718.63

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabdec246810SE +/- 0.0421, N = 3SE +/- 0.0141, N = 38.85218.86968.87488.87808.9004

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streambadec80160240320400SE +/- 1.38, N = 3SE +/- 1.05, N = 3370.83371.57371.95372.49374.08

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamdecab1224364860SE +/- 0.08, N = 3SE +/- 0.02, N = 353.6053.7153.7153.7653.93


Phoronix Test Suite v10.8.5