ds

AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS) and NVIDIA NV174 8GB on Ubuntu 23.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2312110-PTS-DS58174320
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

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

Graph Settings

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

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
December 11 2023
  1 Hour, 39 Minutes
b
December 11 2023
  1 Hour, 39 Minutes
c
December 12 2023
  1 Hour, 39 Minutes
d
December 12 2023
  1 Hour, 39 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 39 Minutes

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


dsOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads)ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS)AMD Device 14d832GB2000GB Samsung SSD 980 PRO 2TB + 4001GB Western Digital WD_BLACK SN850X 4000GBNVIDIA NV174 8GBNVIDIA GA104 HD AudioDELL U2723QEIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 23.106.7.0-060700rc2daily20231127-generic (x86_64)GNOME Shell 45.1X Server 1.21.1.7 + Waylandnouveau4.3 Mesa 24.0~git2311260600.945288~oibaf~m (git-945288f 2023-11-26 mantic-oibaf-ppa)GCC 13.2.0 + LLVM 16.0.6ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionDs PerformanceSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203- Python 3.11.6- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + 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

abcdResult OverviewPhoronix Test Suite100%100%101%101%Neural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseC.D.Y.C.S.I - A.M.SC.D.Y.C.S.I - A.M.SR.5.S.I - A.M.SR.5.S.I - A.M.SR.5.S.I - S.S.SR.5.S.I - S.S.SN.T.C.D.m - S.S.SN.T.C.D.m - S.S.SR.5.B - S.S.SR.5.B - S.S.SC.S.9.P.Y.P - A.M.SC.S.9.P.Y.P - A.M.SC.D.Y.C - A.M.SC.D.Y.C - A.M.SN.T.C.B.b.u.S.S.I - S.S.SN.T.C.B.b.u.S.S.I - S.S.SB.L.N.Q.A.S.I - S.S.SB.L.N.Q.A - S.S.SB.L.N.Q.A.S.I - S.S.SN.D.C.o.b.u.o.I - A.M.SB.L.N.Q.A - S.S.SN.T.C.B.b.u.S.S.I - A.M.SN.T.C.B.b.u.S.S.I - A.M.SN.D.C.o.b.u.o.I - A.M.SN.T.C.B.b.u.c - A.M.SC.D.Y.C - S.S.SC.D.Y.C - S.S.SN.T.C.B.b.u.c - A.M.SC.C.R.5.I - A.M.SC.C.R.5.I - S.S.SC.C.R.5.I - S.S.SC.C.R.5.I - A.M.SB.L.N.Q.A.S.I - A.M.SR.5.B - A.M.SR.5.B - A.M.SB.L.N.Q.A.S.I - A.M.SN.T.C.D.m - A.M.SN.T.C.D.m - A.M.SN.T.C.B.b.u.c - S.S.SN.T.C.B.b.u.c - S.S.SB.L.N.Q.A - A.M.SC.D.Y.C.S.I - S.S.SN.D.C.o.b.u.o.I - S.S.SC.D.Y.C.S.I - S.S.SN.D.C.o.b.u.o.I - S.S.SB.L.N.Q.A - A.M.SC.S.9.P.Y.P - S.S.SC.S.9.P.Y.P - S.S.S

dsdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-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 - Asynchronous Multi-Streamdeepsparse: 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, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-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 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-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 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamabcd22.7389350.749219.568551.0955983.31268.1243299.90923.3312296.037827.0091197.07985.06702314.22723.44711295.80780.7695127.712662.6288101.86619.807629.3517272.166521.127947.3214296.032227.0107198.89675.0217133.537659.8641103.16659.6870203.966639.2065116.36738.588438.9835204.857232.388830.8613462.418617.2878110.62289.030722.7592349.975719.541751.165622.6899351.555919.539151.1690988.29818.0835301.51413.3138295.521027.0574198.47795.03202315.52403.44421295.23100.7698127.246262.8602101.76729.818029.3894271.914321.140047.2956295.760627.0344198.45075.0331133.170760.0283103.16359.6883203.489339.2941116.58168.572938.8700205.599832.418930.8326462.680217.2779110.03149.080222.7193351.507619.529251.197522.7000351.401119.545451.1551986.67698.0963301.17383.3173295.728527.0386198.24795.03822317.25553.44201308.76700.7620127.466262.7323101.88419.806829.3969271.778021.130247.3165295.236627.0809198.76535.0250132.025160.5733103.31689.6736203.918539.2164116.71368.563139.0428204.575532.402230.8484461.534417.3189110.05509.077022.6850351.443119.530851.193222.6176352.483419.567851.0971987.40918.0908301.64843.3119295.335527.0742198.36205.03562293.24803.47801299.09090.7672128.016962.4691101.48029.845329.3591272.152721.241047.0684295.573127.0539198.96795.0198132.593360.2946103.23289.6809203.619339.2783117.25718.523439.1305204.220532.405430.8462462.407417.2882110.49569.041422.7096351.407919.509751.2514OpenBenchmarking.org

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabcd510152025SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 322.7422.6922.7022.62

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabcd80160240320400SE +/- 0.16, N = 3SE +/- 0.09, N = 3SE +/- 0.75, N = 3SE +/- 0.20, N = 3350.75351.56351.40352.48

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabcd510152025SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 319.5719.5419.5519.57

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabcd1224364860SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 351.1051.1751.1651.10

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd2004006008001000SE +/- 0.48, N = 3SE +/- 0.99, N = 3SE +/- 1.16, N = 3SE +/- 1.44, N = 3983.31988.30986.68987.41

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd246810SE +/- 0.0039, N = 3SE +/- 0.0081, N = 3SE +/- 0.0093, N = 3SE +/- 0.0118, N = 38.12438.08358.09638.0908

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabcd70140210280350SE +/- 0.35, N = 3SE +/- 0.53, N = 3SE +/- 1.04, N = 3SE +/- 0.32, N = 3299.91301.51301.17301.65

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabcd0.74951.4992.24852.9983.7475SE +/- 0.0038, N = 3SE +/- 0.0056, N = 3SE +/- 0.0115, N = 3SE +/- 0.0036, N = 33.33123.31383.31733.3119

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabcd60120180240300SE +/- 0.11, N = 3SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 3296.04295.52295.73295.34

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabcd612182430SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 327.0127.0627.0427.07

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabcd4080120160200SE +/- 0.82, N = 3SE +/- 0.91, N = 3SE +/- 0.03, N = 3SE +/- 0.35, N = 3197.08198.48198.25198.36

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabcd1.14012.28023.42034.56045.7005SE +/- 0.0211, N = 3SE +/- 0.0228, N = 3SE +/- 0.0010, N = 3SE +/- 0.0087, N = 35.06705.03205.03825.0356

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd5001000150020002500SE +/- 1.66, N = 3SE +/- 6.99, N = 3SE +/- 4.26, N = 3SE +/- 8.04, N = 32314.232315.522317.262293.25

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd0.78261.56522.34783.13043.913SE +/- 0.0021, N = 3SE +/- 0.0106, N = 3SE +/- 0.0064, N = 3SE +/- 0.0122, N = 33.44713.44423.44203.4780

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabcd30060090012001500SE +/- 10.93, N = 3SE +/- 7.10, N = 3SE +/- 1.41, N = 3SE +/- 0.19, N = 31295.811295.231308.771299.09

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabcd0.17320.34640.51960.69280.866SE +/- 0.0065, N = 3SE +/- 0.0041, N = 3SE +/- 0.0008, N = 3SE +/- 0.0001, N = 30.76950.76980.76200.7672

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabcd306090120150SE +/- 0.61, N = 3SE +/- 0.56, N = 3SE +/- 0.72, N = 3SE +/- 0.24, N = 3127.71127.25127.47128.02

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabcd1428425670SE +/- 0.30, N = 3SE +/- 0.28, N = 3SE +/- 0.37, N = 3SE +/- 0.12, N = 362.6362.8662.7362.47

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabcd20406080100SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.19, N = 3101.87101.77101.88101.48

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabcd3691215SE +/- 0.0059, N = 3SE +/- 0.0053, N = 3SE +/- 0.0035, N = 3SE +/- 0.0182, N = 39.80769.81809.80689.8453

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamabcd714212835SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 329.3529.3929.4029.36

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamabcd60120180240300SE +/- 0.01, N = 3SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3272.17271.91271.78272.15

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamabcd510152025SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 321.1321.1421.1321.24

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamabcd1122334455SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 347.3247.3047.3247.07

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabcd60120180240300SE +/- 0.22, N = 3SE +/- 0.22, N = 3SE +/- 0.26, N = 3SE +/- 0.38, N = 3296.03295.76295.24295.57

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabcd612182430SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 327.0127.0327.0827.05

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcd4080120160200SE +/- 0.11, N = 3SE +/- 0.31, N = 3SE +/- 0.17, N = 3SE +/- 0.45, N = 3198.90198.45198.77198.97

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcd1.13242.26483.39724.52965.662SE +/- 0.0028, N = 3SE +/- 0.0078, N = 3SE +/- 0.0044, N = 3SE +/- 0.0116, N = 35.02175.03315.02505.0198

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd306090120150SE +/- 0.30, N = 3SE +/- 0.59, N = 3SE +/- 0.45, N = 3SE +/- 0.43, N = 3133.54133.17132.03132.59

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd1428425670SE +/- 0.13, N = 3SE +/- 0.27, N = 3SE +/- 0.21, N = 3SE +/- 0.21, N = 359.8660.0360.5760.29

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabcd20406080100SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.14, N = 3103.17103.16103.32103.23

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabcd3691215SE +/- 0.0055, N = 3SE +/- 0.0056, N = 3SE +/- 0.0004, N = 3SE +/- 0.0125, N = 39.68709.68839.67369.6809

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabcd4080120160200SE +/- 0.15, N = 3SE +/- 0.06, N = 3SE +/- 0.24, N = 3SE +/- 0.23, N = 3203.97203.49203.92203.62

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabcd918273645SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 339.2139.2939.2239.28

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabcd306090120150SE +/- 0.35, N = 3SE +/- 0.80, N = 3SE +/- 0.84, N = 3SE +/- 0.43, N = 3116.37116.58116.71117.26

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabcd246810SE +/- 0.0256, N = 3SE +/- 0.0593, N = 3SE +/- 0.0624, N = 3SE +/- 0.0316, N = 38.58848.57298.56318.5234

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabcd918273645SE +/- 0.08, N = 3SE +/- 0.36, N = 3SE +/- 0.07, N = 3SE +/- 0.13, N = 338.9838.8739.0439.13

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabcd50100150200250SE +/- 0.47, N = 3SE +/- 1.77, N = 3SE +/- 0.32, N = 3SE +/- 0.62, N = 3204.86205.60204.58204.22

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabcd816243240SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 332.3932.4232.4032.41

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabcd714212835SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 330.8630.8330.8530.85

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd100200300400500SE +/- 0.23, N = 3SE +/- 0.43, N = 3SE +/- 0.34, N = 3SE +/- 0.35, N = 3462.42462.68461.53462.41

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd48121620SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 317.2917.2817.3217.29

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabcd20406080100SE +/- 0.42, N = 3SE +/- 0.94, N = 3SE +/- 0.22, N = 3SE +/- 0.78, N = 3110.62110.03110.06110.50

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabcd3691215SE +/- 0.0337, N = 3SE +/- 0.0759, N = 3SE +/- 0.0179, N = 3SE +/- 0.0640, N = 39.03079.08029.07709.0414

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcd510152025SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 322.7622.7222.6922.71

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcd80160240320400SE +/- 1.12, N = 3SE +/- 0.23, N = 3SE +/- 0.11, N = 3SE +/- 0.17, N = 3349.98351.51351.44351.41

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabcd510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 319.5419.5319.5319.51

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabcd1224364860SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 351.1751.2051.1951.25

48 Results Shown

Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  ResNet-50, Baseline - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  ResNet-50, Baseline - Synchronous Single-Stream:
    items/sec
    ms/batch
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  ResNet-50, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO - Synchronous Single-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    items/sec
    ms/batch