deepsparse tr

AMD Ryzen Threadripper 3990X 64-Core testing with a Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS) and AMD Radeon RX 5700 8GB on Ubuntu 22.10 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 2301232-NE-DEEPSPARS10
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

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
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
a
January 23 2023
  1 Hour, 57 Minutes
b
January 23 2023
  30 Minutes
c
January 23 2023
  31 Minutes
Invert Hiding All Results Option
  59 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):


deepsparse trOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads)Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS)AMD Starship/Matisse128GBSamsung SSD 970 EVO Plus 500GBAMD Radeon RX 5700 8GB (1750/875MHz)AMD Navi 10 HDMI AudioDELL P2415QIntel I211 + Intel Wi-Fi 6 AX200Ubuntu 22.106.1.0-rc8-phx-mglru (x86_64)GNOME Shell 43.0X Server 1.21.1.4 + Wayland4.6 Mesa 22.2.1 (LLVM 15.0.2 DRM 3.49)1.3.224GCC 12.2.0 + LLVM 15.0.2ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionDeepsparse Tr BenchmarksSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301055- Python 3.10.7- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + 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 STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcResult OverviewPhoronix Test Suite100%101%103%104%105%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 DeepSparseN.S.A.8.P.Q.B.B.U - A.M.SN.S.A.8.P.Q.B.B.U - A.M.SN.S.A.8.P.Q.B.B.U - S.S.SN.S.A.8.P.Q.B.B.U - S.S.SC.D.Y.C - S.S.SC.D.Y.C - S.S.SN.T.C.D.m - S.S.SN.T.C.D.m - S.S.SN.T.C.B.b.u.c - S.S.SN.T.C.B.b.u.c - S.S.SN.D.C.o.b.u.o.I - A.M.SN.Q.A.B.b.u.S.1.P - S.S.SN.D.C.o.b.u.o.I - A.M.SN.Q.A.B.b.u.S.1.P - S.S.SN.T.C.B.b.u.S - S.S.SN.T.C.B.b.u.S - S.S.SN.T.C.D.m - A.M.SN.T.C.D.m - A.M.SC.C.R.5.I - S.S.SC.C.R.5.I - S.S.SN.T.C.B.b.u.S - A.M.SN.T.C.B.b.u.S - A.M.SN.D.C.o.b.u.o.I - S.S.SN.D.C.o.b.u.o.I - S.S.SC.S.9.P.Y.P - A.M.SN.Q.A.B.b.u.S.1.P - A.M.SN.T.C.B.b.u.c - A.M.SC.D.Y.C - A.M.SC.D.Y.C - A.M.SN.T.C.B.b.u.c - A.M.SN.Q.A.B.b.u.S.1.P - A.M.SC.S.9.P.Y.P - A.M.SC.C.R.5.I - A.M.SC.S.9.P.Y.P - S.S.SC.S.9.P.Y.P - S.S.SC.C.R.5.I - A.M.S

deepsparse trdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-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 Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamabc121.5987263.2698360.554588.5450728.338543.5414911.394134.8860943.821233.4855224.9088142.213248.013120.826021.084347.418932.729430.546773.155413.668074.591013.404954.620418.3022114.4637279.345417.275057.862215.692163.6711185.7590171.822710.563794.582077.1694414.4296117.8674271.2283359.244988.7699725.262943.8726916.599734.4957941.514533.6307222.2642143.933247.350621.114220.110949.701332.865530.418273.431513.616472.154813.857454.549318.3262112.5672284.141716.62760.113616.439960.7788185.9302171.553610.508495.083876.9125415.6349115.7776276.2048358.030789.0653724.518443.7343929.829634.2097937.817433.6845222.6035143.71447.081221.234820.126249.662832.246631.002572.609113.770772.848613.725454.450518.3593112.8945283.320516.798559.498116.048162.2604184.7932172.62210.672493.623577.1478414.552OpenBenchmarking.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.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamabc306090120150SE +/- 1.25, N = 15121.60117.87115.78
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamabc20406080100Min: 112.54 / Avg: 121.6 / Max: 130.25

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamabc60120180240300SE +/- 2.74, N = 15263.27271.23276.20
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamabc50100150200250Min: 245.17 / Avg: 263.27 / Max: 283.83

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamabc80160240320400SE +/- 1.72, N = 3360.55359.24358.03
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamabc60120180240300Min: 358.6 / Avg: 360.55 / Max: 363.98

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamabc20406080100SE +/- 0.36, N = 388.5588.7789.07
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamabc20406080100Min: 87.86 / Avg: 88.55 / Max: 89.06

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabc160320480640800SE +/- 0.38, N = 3728.34725.26724.52
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabc130260390520650Min: 727.61 / Avg: 728.34 / Max: 728.89

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabc1020304050SE +/- 0.05, N = 343.5443.8743.73
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabc918273645Min: 43.46 / Avg: 43.54 / Max: 43.64

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabc2004006008001000SE +/- 8.05, N = 3911.39916.60929.83
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabc160320480640800Min: 902.4 / Avg: 911.39 / Max: 927.46

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabc816243240SE +/- 0.38, N = 334.8934.5034.21
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabc714212835Min: 34.13 / Avg: 34.89 / Max: 35.34

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabc2004006008001000SE +/- 1.04, N = 3943.82941.51937.82
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabc170340510680850Min: 942.36 / Avg: 943.82 / Max: 945.82

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabc816243240SE +/- 0.05, N = 333.4933.6333.68
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabc714212835Min: 33.42 / Avg: 33.49 / Max: 33.59

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamabc50100150200250SE +/- 0.04, N = 3224.91222.26222.60
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamabc4080120160200Min: 224.84 / Avg: 224.91 / Max: 224.98

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamabc306090120150SE +/- 0.04, N = 3142.21143.93143.71
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamabc306090120150Min: 142.16 / Avg: 142.21 / Max: 142.28

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamabc1122334455SE +/- 0.42, N = 348.0147.3547.08
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamabc1020304050Min: 47.26 / Avg: 48.01 / Max: 48.69

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamabc510152025SE +/- 0.18, N = 320.8321.1121.23
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamabc510152025Min: 20.53 / Avg: 20.83 / Max: 21.16

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamabc510152025SE +/- 0.22, N = 321.0820.1120.13
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamabc510152025Min: 20.78 / Avg: 21.08 / Max: 21.52

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamabc1122334455SE +/- 0.50, N = 347.4249.7049.66
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamabc1020304050Min: 46.45 / Avg: 47.42 / Max: 48.09

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamabc816243240SE +/- 0.13, N = 332.7332.8732.25
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamabc714212835Min: 32.56 / Avg: 32.73 / Max: 32.98

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamabc714212835SE +/- 0.12, N = 330.5530.4231.00
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamabc714212835Min: 30.31 / Avg: 30.55 / Max: 30.7

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabc1632486480SE +/- 0.18, N = 373.1673.4372.61
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabc1428425670Min: 72.82 / Avg: 73.16 / Max: 73.44

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabc48121620SE +/- 0.03, N = 313.6713.6213.77
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabc48121620Min: 13.61 / Avg: 13.67 / Max: 13.73

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabc20406080100SE +/- 0.09, N = 374.5972.1572.85
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabc1428425670Min: 74.5 / Avg: 74.59 / Max: 74.78

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabc48121620SE +/- 0.02, N = 313.4013.8613.73
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabc48121620Min: 13.37 / Avg: 13.4 / Max: 13.42

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabc1224364860SE +/- 0.03, N = 354.6254.5554.45
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabc1122334455Min: 54.59 / Avg: 54.62 / Max: 54.68

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabc510152025SE +/- 0.01, N = 318.3018.3318.36
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabc510152025Min: 18.28 / Avg: 18.3 / Max: 18.31

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabc306090120150SE +/- 0.20, N = 3114.46112.57112.89
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabc20406080100Min: 114.23 / Avg: 114.46 / Max: 114.86

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabc60120180240300SE +/- 0.58, N = 3279.35284.14283.32
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabc50100150200250Min: 278.19 / Avg: 279.35 / Max: 280.02

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabc48121620SE +/- 0.10, N = 317.2816.6316.80
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabc48121620Min: 17.1 / Avg: 17.28 / Max: 17.45

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabc1326395265SE +/- 0.34, N = 357.8660.1159.50
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabc1224364860Min: 57.28 / Avg: 57.86 / Max: 58.46

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabc48121620SE +/- 0.03, N = 315.6916.4416.05
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabc48121620Min: 15.64 / Avg: 15.69 / Max: 15.73

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabc1428425670SE +/- 0.11, N = 363.6760.7862.26
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabc1224364860Min: 63.51 / Avg: 63.67 / Max: 63.89

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabc4080120160200SE +/- 0.12, N = 3185.76185.93184.79
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabc306090120150Min: 185.51 / Avg: 185.76 / Max: 185.92

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabc4080120160200SE +/- 0.14, N = 3171.82171.55172.62
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabc306090120150Min: 171.62 / Avg: 171.82 / Max: 172.1

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabc3691215SE +/- 0.02, N = 310.5610.5110.67
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabc3691215Min: 10.53 / Avg: 10.56 / Max: 10.58

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabc20406080100SE +/- 0.14, N = 394.5895.0893.62
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabc20406080100Min: 94.4 / Avg: 94.58 / Max: 94.87

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabc20406080100SE +/- 0.02, N = 377.1776.9177.15
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabc1530456075Min: 77.14 / Avg: 77.17 / Max: 77.19

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabc90180270360450SE +/- 0.08, N = 3414.43415.63414.55
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabc70140210280350Min: 414.33 / Avg: 414.43 / Max: 414.59

36 Results Shown

Neural Magic DeepSparse:
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Detection, YOLOv5s COCO - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    ms/batch
    items/sec