sdfa

AMD Ryzen Threadripper 3990X 64-Core testing with a Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS) and AMD Radeon RX 5700 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 2312122-PTS-SDFA911983
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

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
Performance Per
Dollar
Date
Run
  Test
  Duration
a
December 11 2023
  22 Hours, 44 Minutes
b
December 12 2023
  7 Hours, 14 Minutes
c
December 12 2023
  21 Hours, 52 Minutes
d
December 12 2023
  21 Hours, 47 Minutes
Invert Hiding All Results Option
  18 Hours, 24 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):


sdfaOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads)Gigabyte TRX40 AORUS PRO WIFI (F6 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 23.106.5.0-13-generic (x86_64)GNOME Shell 45.0X Server + Wayland4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54)GCC 13.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionSdfa BenchmarksSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x830107a- OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)- 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: Mitigation of untrained return thunk; SMT enabled with STIBP protection + 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 Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcdResult OverviewPhoronix Test Suite100%108%116%125%133%Neural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseApache Spark TPC-HNeural 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 DeepSparseApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HApache Spark TPC-HR.5.S.I - S.S.SR.5.S.I - S.S.SC.S.9.P.Y.P - S.S.SC.S.9.P.Y.P - S.S.SB.L.N.Q.A - S.S.SB.L.N.Q.A - S.S.S10 - G.M.O.A.QN.D.C.o.b.u.o.I - A.M.SN.D.C.o.b.u.o.I - A.M.SN.T.C.D.m - S.S.SN.T.C.D.m - S.S.SC.D.Y.C - A.M.SC.D.Y.C - A.M.SN.D.C.o.b.u.o.I - S.S.SN.D.C.o.b.u.o.I - S.S.SR.5.S.I - A.M.SR.5.S.I - A.M.SN.T.C.B.b.u.S.S.I - S.S.SN.T.C.B.b.u.S.S.I - S.S.SR.5.B - S.S.SR.5.B - S.S.S1 - Q011 - Q021 - Q031 - Q041 - Q051 - Q061 - Q071 - Q081 - Q091 - Q101 - Q111 - Q121 - Q131 - Q141 - Q151 - Q161 - Q171 - Q181 - Q191 - Q201 - Q211 - Q2210 - Q0410 - Q0510 - Q0610 - Q0810 - Q0910 - Q1110 - Q1310 - Q1510 - Q1610 - Q1810 - Q1910 - Q2250 - Q0350 - Q0550 - Q1150 - Q1350 - Q1650 - Q22

sdfadeepsparse: 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-Streamspark-tpch: 1 - Geometric Mean Of All Queriesspark-tpch: 10 - Geometric Mean Of All Queriesspark-tpch: 50 - Geometric Mean Of All Queriesspark-tpch: 1 - Q01spark-tpch: 1 - Q02spark-tpch: 1 - Q03spark-tpch: 1 - Q04spark-tpch: 1 - Q05spark-tpch: 1 - Q06spark-tpch: 1 - Q07spark-tpch: 1 - Q08spark-tpch: 1 - Q09spark-tpch: 1 - Q10spark-tpch: 1 - Q11spark-tpch: 1 - Q12spark-tpch: 1 - Q13spark-tpch: 1 - Q14spark-tpch: 1 - Q15spark-tpch: 1 - Q16spark-tpch: 1 - Q17spark-tpch: 1 - Q18spark-tpch: 1 - Q19spark-tpch: 1 - Q20spark-tpch: 1 - Q21spark-tpch: 1 - Q22spark-tpch: 10 - Q01spark-tpch: 10 - Q02spark-tpch: 10 - Q03spark-tpch: 10 - Q04spark-tpch: 10 - Q05spark-tpch: 10 - Q06spark-tpch: 10 - Q07spark-tpch: 10 - Q08spark-tpch: 10 - Q09spark-tpch: 10 - Q10spark-tpch: 10 - Q11spark-tpch: 10 - Q12spark-tpch: 10 - Q13spark-tpch: 10 - Q14spark-tpch: 10 - Q15spark-tpch: 10 - Q16spark-tpch: 10 - Q17spark-tpch: 10 - Q18spark-tpch: 10 - Q19spark-tpch: 10 - Q20spark-tpch: 10 - Q21spark-tpch: 10 - Q22spark-tpch: 50 - Q01spark-tpch: 50 - Q02spark-tpch: 50 - Q03spark-tpch: 50 - Q04spark-tpch: 50 - Q05spark-tpch: 50 - Q06spark-tpch: 50 - Q07spark-tpch: 50 - Q08spark-tpch: 50 - Q09spark-tpch: 50 - Q10spark-tpch: 50 - Q11spark-tpch: 50 - Q12spark-tpch: 50 - Q13spark-tpch: 50 - Q14spark-tpch: 50 - Q15spark-tpch: 50 - Q16spark-tpch: 50 - Q17spark-tpch: 50 - Q18spark-tpch: 50 - Q19spark-tpch: 50 - Q20spark-tpch: 50 - Q21spark-tpch: 50 - Q22abcd37.9294836.917213.898771.9375980.449732.6019129.70417.7066441.440772.4193103.56439.64622555.423212.4868627.75391.5897201.9130158.154486.376911.561149.2180649.934811.308888.4675449.307971.1719106.44329.3853215.8297147.962091.143210.9635336.191795.015156.790217.597843.1906736.773917.074558.5511503.413263.477064.707215.451037.7351841.425914.075171.03902.203287348.1709066727.975628234.695118432.199165113.158902592.960263913.461568060.758707523.162965002.290912694.400907402.837899391.308498562.149872691.400586641.832315361.994915871.427312912.661922224.003722491.028470382.755551767.395054701.085022848.678337424.8509952210.244067198.6368297012.476073584.4013136210.6311874410.9939940814.8994369510.265551884.549316258.034650014.457083075.796152755.837094314.3205062612.4504474014.862232537.216275388.8416096429.314933783.5358621326.0223490410.4835224236.6144994130.5848776541.1654268920.3811728235.6305478438.3594220546.8971544935.926039389.0623906530.4303925912.3371191025.4870529223.0454743710.5865411855.6091779162.5085741724.7187226630.70769501130.8656412810.6748638239.3833806.392814.402969.4174993.603732.1567131.1677.6192450.806270.9424106.92959.34242635.572912.1095599.18631.6656206.9627154.303588.16511.327949.3328648.52411.605786.1505448.760371.2672106.53879.377212.7552150.225989.801811.1265337.082194.881859.008216.935543.8384726.250417.991255.5621508.590262.811264.398515.52237.9456837.458114.307869.87842.245314157.8939945527.786828934.730920792.207261323.23912433.092572213.37768650.732237643.303481342.327807664.515100483.079596281.364477992.02941991.458663231.781570552.174607751.439398532.722641944.04589511.17394592.587625987.703692440.988863238.701518064.8849501610.321226128.7080907812.918885234.6216292410.53174410.6704559314.180296910.184454924.267613418.108592994.036980155.828408725.680895334.1559176412.4410772314.876805316.04250248.8766384128.798635483.4011077925.9903545410.4503164336.0291671830.2687091843.2500114420.2972335835.3421478337.9715690646.3175430336.272079478.6932077430.4071655312.1311054225.3969287922.8892459910.5323028655.2799911561.955020925.0755310130.53813362131.4552612310.5269079237.7845841.343513.881372.0273988.490532.3392132.10477.5689445.162371.8091106.03339.42152548.377112.5199591.25701.6887199.2162160.278087.930611.357649.0805649.755011.838784.4587452.040170.7399107.10429.3277216.3914147.488991.156510.9619337.781394.678957.179317.477943.0454737.977716.986558.8526506.133063.129564.115415.592637.9380837.141814.104870.89892.237059118.1114257528.112194134.840341092.278467663.345568972.944285953.524186530.710825563.184302172.357799214.329672183.029143571.289742672.040395381.399916811.838365992.143637741.494487602.585270723.993240671.208379112.752848237.461975891.058803248.666814484.9289708110.264451038.5045766812.663379354.3003606810.6200927110.8527135914.8189811710.419712074.389634298.171160384.097770065.861774135.810214364.1757297512.4186039016.114520396.543281558.9121713629.033676783.6996615826.0016663910.5609486937.0584462530.2234160139.7004280120.3408381135.4553070137.8074277247.1084391336.821423858.7526063930.8858286513.1364854225.4562212622.9463895210.8244365155.3342908262.2995541924.8944753030.78961944131.4217529310.6366717038.7188820.120813.902071.9192989.058932.3108134.39757.4402441.394172.4572103.97919.60842543.113812.5483620.24121.6090201.9444158.106587.465411.417249.1687650.693111.742385.1572450.059871.0506104.29309.5802215.2909148.282789.591811.1539335.096895.445856.859917.576143.0569737.852417.087858.5011504.842063.296564.084215.600137.4534845.443813.999771.41652.223564468.2456727328.123942264.846229872.275128683.154473222.858560403.309953690.742623983.253300432.225297374.558725043.142105901.291904692.069544161.392255511.832191392.277157311.539288202.577730503.869211360.994358202.747976627.407735511.061138478.732316974.7943743010.152245528.3395834012.656619074.3671096210.7454160010.8172769514.9209750510.358723004.480574608.094197754.613405865.735224725.855655994.3460126012.4005835914.911290498.027953478.8245258328.908061353.5968260726.1190382710.4435723635.9920043930.5570793138.9946009320.3820470235.4003842738.3807525746.9971860235.928248099.0176893930.0418027213.6845792125.4237861623.0023676610.9140424755.4218126962.7336400325.0289204930.51781400131.0061238610.26505438OpenBenchmarking.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-Streamdcba918273645SE +/- 0.36, N = 3SE +/- 0.38, N = 6SE +/- 0.52, N = 338.7237.7839.3837.93

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamdcba2004006008001000SE +/- 7.99, N = 3SE +/- 8.13, N = 6SE +/- 12.88, N = 3820.12841.34806.39836.92

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamdcba48121620SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 313.9013.8814.4013.90

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamdcba1632486480SE +/- 0.18, N = 3SE +/- 0.25, N = 3SE +/- 0.30, N = 371.9272.0369.4271.94

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamdcba2004006008001000SE +/- 1.17, N = 3SE +/- 1.16, N = 3SE +/- 3.44, N = 3989.06988.49993.60980.45

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamdcba816243240SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 332.3132.3432.1632.60

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamdcba306090120150SE +/- 1.48, N = 5SE +/- 1.51, N = 4SE +/- 0.69, N = 3134.40132.10131.17129.70

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamdcba246810SE +/- 0.0842, N = 5SE +/- 0.0865, N = 4SE +/- 0.0410, N = 37.44027.56897.61927.7066

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamdcba100200300400500SE +/- 1.15, N = 3SE +/- 1.47, N = 3SE +/- 2.10, N = 3441.39445.16450.81441.44

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamdcba1632486480SE +/- 0.19, N = 3SE +/- 0.24, N = 3SE +/- 0.35, N = 372.4671.8170.9472.42

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamdcba20406080100SE +/- 0.81, N = 3SE +/- 0.15, N = 3SE +/- 0.53, N = 3103.98106.03106.93103.56

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamdcba3691215SE +/- 0.0758, N = 3SE +/- 0.0132, N = 3SE +/- 0.0493, N = 39.60849.42159.34249.6462

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamdcba6001200180024003000SE +/- 15.60, N = 3SE +/- 12.01, N = 3SE +/- 14.52, N = 32543.112548.382635.572555.42

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamdcba3691215SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 312.5512.5212.1112.49

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamdcba140280420560700SE +/- 1.41, N = 3SE +/- 8.33, N = 3SE +/- 2.01, N = 3620.24591.26599.19627.75

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamdcba0.380.761.141.521.9SE +/- 0.0037, N = 3SE +/- 0.0240, N = 3SE +/- 0.0051, N = 31.60901.68871.66561.5897

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamdcba50100150200250SE +/- 1.27, N = 3SE +/- 1.60, N = 3SE +/- 1.28, N = 3201.94199.22206.96201.91

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamdcba4080120160200SE +/- 1.02, N = 3SE +/- 1.36, N = 3SE +/- 0.94, N = 3158.11160.28154.30158.15

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamdcba20406080100SE +/- 0.19, N = 3SE +/- 0.32, N = 3SE +/- 0.58, N = 387.4787.9388.1786.38

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamdcba3691215SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 311.4211.3611.3311.56

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamdcba1122334455SE +/- 0.10, N = 3SE +/- 0.26, N = 3SE +/- 0.03, N = 349.1749.0849.3349.22

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamdcba140280420560700SE +/- 1.27, N = 3SE +/- 1.51, N = 3SE +/- 0.29, N = 3650.69649.76648.52649.93

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamdcba3691215SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 1511.7411.8411.6111.31

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamdcba20406080100SE +/- 0.61, N = 3SE +/- 0.42, N = 3SE +/- 0.60, N = 1585.1684.4686.1588.47

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamdcba100200300400500SE +/- 1.54, N = 3SE +/- 0.60, N = 3SE +/- 1.01, N = 3450.06452.04448.76449.31

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamdcba1632486480SE +/- 0.25, N = 3SE +/- 0.10, N = 3SE +/- 0.17, N = 371.0570.7471.2771.17

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamdcba20406080100SE +/- 1.00, N = 3SE +/- 0.34, N = 3SE +/- 0.16, N = 3104.29107.10106.54106.44

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamdcba3691215SE +/- 0.0916, N = 3SE +/- 0.0294, N = 3SE +/- 0.0142, N = 39.58029.32779.37709.3853

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamdcba50100150200250SE +/- 0.09, N = 3SE +/- 0.14, N = 3SE +/- 0.62, N = 3215.29216.39212.76215.83

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamdcba306090120150SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.45, N = 3148.28147.49150.23147.96

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamdcba20406080100SE +/- 0.36, N = 3SE +/- 0.17, N = 3SE +/- 0.36, N = 389.5991.1689.8091.14

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamdcba3691215SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 311.1510.9611.1310.96

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamdcba70140210280350SE +/- 1.00, N = 3SE +/- 0.44, N = 3SE +/- 0.53, N = 3335.10337.78337.08336.19

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamdcba20406080100SE +/- 0.28, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 395.4594.6894.8895.02

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamdcba1326395265SE +/- 0.19, N = 3SE +/- 0.19, N = 3SE +/- 0.15, N = 356.8657.1859.0156.79

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamdcba48121620SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 317.5817.4816.9417.60

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamdcba1020304050SE +/- 0.06, N = 3SE +/- 0.28, N = 3SE +/- 0.30, N = 343.0643.0543.8443.19

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamdcba160320480640800SE +/- 2.01, N = 3SE +/- 4.42, N = 3SE +/- 6.44, N = 3737.85737.98726.25736.77

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamdcba48121620SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 317.0916.9917.9917.07

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamdcba1326395265SE +/- 0.11, N = 3SE +/- 0.30, N = 3SE +/- 0.38, N = 358.5058.8555.5658.55

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamdcba110220330440550SE +/- 0.62, N = 3SE +/- 0.45, N = 3SE +/- 0.37, N = 3504.84506.13508.59503.41

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamdcba1428425670SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 363.3063.1362.8163.48

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamdcba1428425670SE +/- 0.57, N = 3SE +/- 0.51, N = 3SE +/- 0.66, N = 364.0864.1264.4064.71

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamdcba48121620SE +/- 0.14, N = 3SE +/- 0.12, N = 3SE +/- 0.16, N = 315.6015.5915.5215.45

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamdcba918273645SE +/- 0.10, N = 3SE +/- 0.25, N = 3SE +/- 0.10, N = 337.4537.9437.9537.74

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamdcba2004006008001000SE +/- 2.60, N = 3SE +/- 6.31, N = 3SE +/- 2.31, N = 3845.44837.14837.46841.43

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamdcba48121620SE +/- 0.03, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 314.0014.1014.3114.08

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamdcba1632486480SE +/- 0.16, N = 3SE +/- 0.72, N = 3SE +/- 0.43, N = 371.4270.9069.8871.04

Apache Spark TPC-H

This is a benchmark of Apache Spark using TPC-H data-set. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmarks the Apache Spark in a single-system configuration using spark-submit. The test makes use of https://github.com/ssavvides/tpch-spark/ for facilitating the TPC-H benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 1 - Geometric Mean Of All Queriesdcba0.50521.01041.51562.02082.526SE +/- 0.02256519, N = 3SE +/- 0.00573499, N = 3SE +/- 0.02461970, N = 42.223564462.237059112.245314152.20328734MIN: 0.97 / MAX: 7.7MIN: 1.05 / MAX: 7.66MIN: 0.99 / MAX: 7.7MIN: 0.99 / MAX: 7.56

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 10 - Geometric Mean Of All Queriesdcba246810SE +/- 0.01945474, N = 3SE +/- 0.05385571, N = 3SE +/- 0.00516651, N = 38.245672738.111425757.893994558.17090667MIN: 3.57 / MAX: 29.28MIN: 3.43 / MAX: 29.17MIN: 3.4 / MAX: 28.8MIN: 3.42 / MAX: 29.75

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark TPC-H 3.5Scale Factor: 50 - Geometric Mean Of All Queriesdcba714212835SE +/- 0.15, N = 3SE +/- 0.14, N = 3SE +/- 0.09, N = 328.1228.1127.7927.98MIN: 8.73 / MAX: 132.42MIN: 8.58 / MAX: 132.82MIN: 8.69 / MAX: 131.46MIN: 8.84 / MAX: 131.32

Scale Factor: 100

a: The test quit with a non-zero exit status. E: ./spark-tpch: line 6: echo: write error: No space left on device

b: The test quit with a non-zero exit status. E: ./spark-tpch: line 6: echo: write error: No space left on device

c: The test quit with a non-zero exit status. E: ./spark-tpch: line 6: echo: write error: No space left on device

d: The test quit with a non-zero exit status. E: ./spark-tpch: line 6: echo: write error: No space left on device

51 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
Apache Spark TPC-H:
  1 - Geometric Mean Of All Queries
  10 - Geometric Mean Of All Queries
  50 - Geometric Mean Of All Queries