a

Benchmarks for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2312143-NE-A8154652071
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

Limit displaying results to tests within:

BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
Fortran Tests 2 Tests
HPC - High Performance Computing 3 Tests
LAPACK (Linear Algebra Pack) Tests 2 Tests
OpenMPI Tests 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
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 12 2023
  6 Hours, 14 Minutes
b
December 12 2023
  6 Hours, 8 Minutes
c
December 12 2023
  5 Hours, 57 Minutes
d
December 13 2023
  6 Hours, 19 Minutes
Invert Hiding All Results Option
  6 Hours, 9 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):


aOpenBenchmarking.orgPhoronix Test Suite2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads)Quanta Cloud S6Q-MB-MPS (3B05.TEL4P1 BIOS)Intel Device 1bce1008GB3201GB Micron_7450_MTFDKCB3T2TFSASPEED2 x Intel X710 for 10GBASE-TUbuntu 23.106.5.0-13-generic (x86_64)GCC 13.2.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionA BenchmarksSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x21000161 - 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: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected - d: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v

abcdResult OverviewPhoronix Test Suite100%100%101%101%102%NWChemNeural Magic DeepSparseWRF

adeepsparse: 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-Streamnwchem: C240 Buckyballwrf: conus 2.5kmabcd133.5159475.696431.194532.06134554.979614.0362238.65234.20831829.964434.9169338.95622.949211228.66255.68521030.31810.9681828.038477.1758190.84205.2382156.0563407.277729.942133.40221832.792734.8681339.04162.9484854.052574.8177194.24765.14851231.204951.9301199.69305.0073183.4966347.663734.962028.58761880.768833.980896.430010.3634133.6023475.126531.695431.582117445566.729133.7189474.185231.233632.03684563.509714.0081237.04604.22951824.375935.0063337.67992.960211169.85175.71401027.51170.9706828.653277.0924190.03995.2617155.7222408.626330.389132.89891817.993935.1423338.85832.9500852.945574.9435193.59725.16591231.293951.9273199.33805.0196180.3157353.688935.106528.47011875.903534.081596.379010.3695133.8239474.368731.533231.73031730.75600.976133.4843475.680431.630031.65014563.427814.0090230.76404.34361827.978034.9683338.55362.953011163.65935.71651043.28040.9556828.446277.1235189.81755.2651155.7677408.969930.294432.99841834.477134.8217338.21922.9555854.252174.7945193.08725.18021231.273651.9192199.33235.0179177.1512359.891935.005728.55211879.838833.993996.547410.3507133.6004475.349731.720231.56181757.35583.112133.0079477.610832.893630.42224556.023314.0315240.23364.16041837.497734.7567338.14662.957311221.13575.69081032.24100.9667825.084177.4573190.13765.2589155.6020408.163829.523133.86351819.686135.1013339.36712.9455850.892675.0848193.81865.16141226.796052.0706196.78745.0808181.2029352.223534.998728.55861865.019334.250895.698110.4501133.5969475.446433.054030.289117485617.197OpenBenchmarking.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-Streamabcd306090120150SE +/- 0.15, N = 3SE +/- 0.13, N = 3SE +/- 0.16, N = 3SE +/- 0.11, N = 3133.52133.72133.48133.01

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabcd100200300400500SE +/- 0.61, N = 3SE +/- 0.47, N = 3SE +/- 0.52, N = 3SE +/- 0.44, N = 3475.70474.19475.68477.61

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabcd816243240SE +/- 0.38, N = 4SE +/- 0.25, N = 15SE +/- 0.32, N = 15SE +/- 0.26, N = 1531.1931.2331.6332.89

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabcd714212835SE +/- 0.40, N = 4SE +/- 0.27, N = 15SE +/- 0.32, N = 15SE +/- 0.25, N = 1532.0632.0431.6530.42

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd10002000300040005000SE +/- 49.40, N = 5SE +/- 40.39, N = 7SE +/- 43.60, N = 6SE +/- 42.83, N = 64554.984563.514563.434556.02

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd48121620SE +/- 0.16, N = 5SE +/- 0.13, N = 7SE +/- 0.14, N = 6SE +/- 0.14, N = 614.0414.0114.0114.03

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabcd50100150200250SE +/- 4.61, N = 15SE +/- 3.82, N = 15SE +/- 3.66, N = 15SE +/- 3.16, N = 3238.65237.05230.76240.23

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabcd0.97731.95462.93193.90924.8865SE +/- 0.0821, N = 15SE +/- 0.0666, N = 15SE +/- 0.0661, N = 15SE +/- 0.0540, N = 34.20834.22954.34364.1604

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabcd400800120016002000SE +/- 4.85, N = 3SE +/- 13.19, N = 3SE +/- 17.94, N = 3SE +/- 14.66, N = 31829.961824.381827.981837.50

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabcd816243240SE +/- 0.08, N = 3SE +/- 0.25, N = 3SE +/- 0.35, N = 3SE +/- 0.29, N = 334.9235.0134.9734.76

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabcd70140210280350SE +/- 2.76, N = 9SE +/- 3.44, N = 6SE +/- 2.56, N = 12SE +/- 2.94, N = 12338.96337.68338.55338.15

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabcd0.6661.3321.9982.6643.33SE +/- 0.0255, N = 9SE +/- 0.0315, N = 6SE +/- 0.0242, N = 12SE +/- 0.0282, N = 122.94922.96022.95302.9573

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd2K4K6K8K10KSE +/- 71.77, N = 13SE +/- 89.80, N = 9SE +/- 101.43, N = 7SE +/- 77.36, N = 1211228.6611169.8511163.6611221.14

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd1.28622.57243.85865.14486.431SE +/- 0.0393, N = 13SE +/- 0.0484, N = 9SE +/- 0.0544, N = 7SE +/- 0.0425, N = 125.68525.71405.71655.6908

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabcd2004006008001000SE +/- 11.12, N = 4SE +/- 9.47, N = 3SE +/- 5.37, N = 3SE +/- 9.64, N = 71030.321027.511043.281032.24

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabcd0.21840.43680.65520.87361.092SE +/- 0.0105, N = 4SE +/- 0.0090, N = 3SE +/- 0.0048, N = 3SE +/- 0.0094, N = 70.96810.97060.95560.9667

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabcd2004006008001000SE +/- 7.51, N = 3SE +/- 6.37, N = 3SE +/- 6.81, N = 3SE +/- 9.22, N = 3828.04828.65828.45825.08

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabcd20406080100SE +/- 0.70, N = 3SE +/- 0.63, N = 3SE +/- 0.64, N = 3SE +/- 0.87, N = 377.1877.0977.1277.46

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabcd4080120160200SE +/- 1.29, N = 12SE +/- 1.73, N = 12SE +/- 1.69, N = 7SE +/- 1.52, N = 12190.84190.04189.82190.14

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabcd1.18462.36923.55384.73845.923SE +/- 0.0382, N = 12SE +/- 0.0526, N = 12SE +/- 0.0492, N = 7SE +/- 0.0457, N = 125.23825.26175.26515.2589

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamabcd306090120150SE +/- 0.66, N = 3SE +/- 0.66, N = 3SE +/- 1.19, N = 3SE +/- 1.10, N = 3156.06155.72155.77155.60

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamabcd90180270360450SE +/- 1.62, N = 3SE +/- 1.91, N = 3SE +/- 2.55, N = 3SE +/- 2.06, N = 3407.28408.63408.97408.16

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamabcd714212835SE +/- 0.30, N = 6SE +/- 0.27, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 329.9430.3930.2929.52

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamabcd816243240SE +/- 0.34, N = 6SE +/- 0.30, N = 3SE +/- 0.16, N = 3SE +/- 0.12, N = 333.4032.9033.0033.86

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabcd400800120016002000SE +/- 22.80, N = 3SE +/- 7.71, N = 3SE +/- 5.61, N = 3SE +/- 21.20, N = 31832.791817.991834.481819.69

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabcd816243240SE +/- 0.43, N = 3SE +/- 0.14, N = 3SE +/- 0.11, N = 3SE +/- 0.39, N = 334.8735.1434.8235.10

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcd70140210280350SE +/- 2.66, N = 10SE +/- 2.82, N = 9SE +/- 3.30, N = 6SE +/- 2.24, N = 12339.04338.86338.22339.37

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcd0.6651.331.9952.663.325SE +/- 0.0247, N = 10SE +/- 0.0260, N = 9SE +/- 0.0300, N = 6SE +/- 0.0208, N = 122.94842.95002.95552.9455

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd2004006008001000SE +/- 8.70, N = 3SE +/- 10.26, N = 3SE +/- 9.10, N = 3SE +/- 10.96, N = 3854.05852.95854.25850.89

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd20406080100SE +/- 0.77, N = 3SE +/- 0.92, N = 3SE +/- 0.80, N = 3SE +/- 0.97, N = 374.8274.9474.7975.08

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabcd4080120160200SE +/- 1.36, N = 12SE +/- 1.53, N = 13SE +/- 1.70, N = 12SE +/- 1.62, N = 12194.25193.60193.09193.82

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabcd1.16552.3313.49654.6625.8275SE +/- 0.0389, N = 12SE +/- 0.0445, N = 13SE +/- 0.0500, N = 12SE +/- 0.0471, N = 125.14855.16595.18025.1614

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabcd30060090012001500SE +/- 14.83, N = 3SE +/- 14.60, N = 4SE +/- 13.91, N = 3SE +/- 17.38, N = 31231.201231.291231.271226.80

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabcd1224364860SE +/- 0.63, N = 3SE +/- 0.60, N = 4SE +/- 0.62, N = 3SE +/- 0.70, N = 351.9351.9351.9252.07

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabcd4080120160200SE +/- 1.45, N = 12SE +/- 2.05, N = 12SE +/- 1.76, N = 12SE +/- 1.69, N = 8199.69199.34199.33196.79

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabcd1.14322.28643.42964.57285.716SE +/- 0.0391, N = 12SE +/- 0.0573, N = 12SE +/- 0.0484, N = 12SE +/- 0.0457, N = 85.00735.01965.01795.0808

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabcd4080120160200SE +/- 1.57, N = 8SE +/- 2.09, N = 3SE +/- 1.83, N = 3SE +/- 1.48, N = 9183.50180.32177.15181.20

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabcd80160240320400SE +/- 3.00, N = 8SE +/- 4.19, N = 3SE +/- 3.47, N = 3SE +/- 2.84, N = 9347.66353.69359.89352.22

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabcd816243240SE +/- 0.33, N = 7SE +/- 0.34, N = 6SE +/- 0.35, N = 6SE +/- 0.23, N = 1234.9635.1135.0135.00

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabcd714212835SE +/- 0.28, N = 7SE +/- 0.29, N = 6SE +/- 0.29, N = 6SE +/- 0.20, N = 1228.5928.4728.5528.56

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd400800120016002000SE +/- 21.42, N = 3SE +/- 26.46, N = 3SE +/- 21.19, N = 3SE +/- 21.54, N = 31880.771875.901879.841865.02

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd816243240SE +/- 0.38, N = 3SE +/- 0.48, N = 3SE +/- 0.38, N = 3SE +/- 0.40, N = 333.9834.0833.9934.25

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabcd20406080100SE +/- 0.11, N = 3SE +/- 0.30, N = 3SE +/- 0.16, N = 3SE +/- 0.72, N = 1096.4396.3896.5595.70

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabcd3691215SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 1010.3610.3710.3510.45

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcd306090120150SE +/- 0.13, N = 3SE +/- 0.14, N = 3SE +/- 0.19, N = 3SE +/- 0.26, N = 3133.60133.82133.60133.60

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcd100200300400500SE +/- 0.32, N = 3SE +/- 0.39, N = 3SE +/- 0.55, N = 3SE +/- 0.75, N = 3475.13474.37475.35475.45

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabcd816243240SE +/- 0.31, N = 15SE +/- 0.25, N = 15SE +/- 0.33, N = 15SE +/- 0.33, N = 1531.7031.5331.7233.05

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabcd714212835SE +/- 0.31, N = 15SE +/- 0.25, N = 15SE +/- 0.32, N = 15SE +/- 0.31, N = 1531.5831.7331.5630.29

NWChem

NWChem is an open-source high performance computational chemistry package. Per NWChem's documentation, "NWChem aims to provide its users with computational chemistry tools that are scalable both in their ability to treat large scientific computational chemistry problems efficiently, and in their use of available parallel computing resources from high-performance parallel supercomputers to conventional workstation clusters." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNWChem 7.0.2Input: C240 Buckyballabcd4008001200160020001744.01730.71757.31748.01. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lcomex -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2

WRF

WRF, the Weather Research and Forecasting Model, is a "next-generation mesoscale numerical weather prediction system designed for both atmospheric research and operational forecasting applications. It features two dynamical cores, a data assimilation system, and a software architecture supporting parallel computation and system extensibility." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWRF 4.2.2Input: conus 2.5kmabcd120024003600480060005566.735600.985583.115617.201. (F9X) gfortran options: -O2 -ftree-vectorize -funroll-loops -ffree-form -fconvert=big-endian -frecord-marker=4 -fallow-invalid-boz -lesmf_time -lwrfio_nf -lnetcdff -lnetcdf -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

50 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
NWChem
WRF