xeon emr

2 x INTEL XEON PLATINUM 8592+ testing with a Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS) and ASPEED 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 2403172-NE-XEONEMR4990
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

Limit displaying results to tests within:

C/C++ Compiler Tests 2 Tests
CPU Massive 5 Tests
Creator Workloads 2 Tests
Multi-Core 5 Tests
Server CPU Tests 3 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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
a
March 17
  40 Minutes
b
March 17
  41 Minutes
c
March 17
  40 Minutes
d
March 17
  41 Minutes
Invert Hiding All Results Option
  40 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):


xeon emrOpenBenchmarking.orgPhoronix Test Suite2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads)Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS)Intel Device 1bce1008GB3201GB Micron_7450_MTFDKCC3T2TFSASPEED2 x Intel X710 for 10GBASE-TUbuntu 23.106.6.0-rc5-phx-patched (x86_64)GNOME Shell 45.0X Server 1.21.1.7GCC 13.2.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionXeon Emr BenchmarksSystem Logs- Transparent Huge Pages: madvise- --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 - Scaling Governor: intel_pstate performance (EPP: 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

abcdResult OverviewPhoronix Test Suite100%102%105%107%110%srsRAN ProjectStockfishParallel BZIP2 CompressionPrimesieveSVT-AV1Timed Linux Kernel CompilationNeural Magic DeepSparseGoogle Draco

xeon emrsrsran: PDSCH Processor Benchmark, Throughput Totaldeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamdeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamstockfish: Chess Benchmarksvt-av1: Preset 12 - Bosphorus 1080psrsran: PDSCH Processor Benchmark, Throughput Threadsvt-av1: Preset 13 - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 4 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Kprimesieve: 1e12deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamsvt-av1: Preset 4 - Bosphorus 1080pdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamdraco: Church Facadecompress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compressionsvt-av1: Preset 8 - Bosphorus 1080pdraco: Lionbuild-linux-kernel: defconfigsvt-av1: Preset 13 - Bosphorus 4Kbuild-linux-kernel: allmodconfigdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - 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, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamprimesieve: 1e13deepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-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: 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-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamabcd43297.43.102816509.1382212133268457.741755.6643.52572.867.75172.7182.2130.93941060.95229.9739100.208435.829227.883622.03368.887414.500148371.249184152.48406026.074168.799181.564137.9486461.3828199.06685.0199197.61335.0581800.714635.499834.056929.354551.65961238.0561342.281425.0332.91881789.6958351.868735.7151181.78532.9085343.45875.446311719.0071138.30513.91874590.22733.2778304.7581460.732329.248634.18331904.078373.9698864.347433.571850572.12.967617153.2257207635904439.119728.7640.89273.7137.531168.2982.1630.92321079.571910.023399.709635.85127.866622.16169.879114.293747931.235156152.788404126.364167.052183.153137.2758462.5178198.34485.0378195.87175.1031788.797835.730334.123329.294851.51311241.5488342.900824.9752.91351792.6939350.377835.6661182.10962.9192342.20845.444511722.5863137.790913.89244598.8813.2774304.7953461.216729.208434.22971902.914573.9961863.669233.594252220.42.950617224.3584221316167441.419755.3620.86572.8277.541169.912.1590.93561065.96659.8997100.953635.194328.385222.39269.641614.340847651.235287153.098409226.042168.2182.434136.559465.457200.28184.9896195.83255.10371803.232235.454333.989629.411551.84221233.705341.444125.0772.92571781.8907349.803235.8738182.8092.9173342.44215.454411702.1757137.970513.87134605.99163.2761304.8963461.993229.276834.15031902.175874.0382863.853833.591349150.33.213716021.351214224198442.336756627.5971.5117.586169.3872.1630.94491055.182210.121698.746735.765427.930922.2469.94514.280948201.252094154.5405926.131168.292181.284137.823460.9087198.37895.0371197.00815.07341794.846235.613733.891329.49551.70721236.9478343.534924.9252.9081789.8075350.44335.7107182.55242.9035344.04695.467511674.2462137.965713.92234589.14833.2877303.8422462.028429.236434.19681902.928174.0261863.925733.5967OpenBenchmarking.org

srsRAN Project

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240219Test: PDSCH Processor Benchmark, Throughput Totalcbda11K22K33K44K55K52220.450572.149150.346252.51. (CXX) g++ options: -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -O3 -fno-trapping-math -fno-math-errno -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Streamdabc0.72311.44622.16932.89243.61553.21373.10282.96762.9506

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Streamdabc4K8K12K16K20K16021.3516509.1417153.2317224.36

Stockfish

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess Benchmarkcdab50M100M150M200M250M2213161672142241982121332682076359041. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 1080padcb100200300400500457.74442.34441.42439.121. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

srsRAN Project

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240219Test: PDSCH Processor Benchmark, Throughput Threaddacb160320480640800756.0755.6755.3728.71. (CXX) g++ options: -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -O3 -fno-trapping-math -fno-math-errno -ldl

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 1080pabdc140280420560700643.53640.89627.59620.871. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4Kbacd163248648073.7172.8672.8371.511. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4Kadcb2468107.7507.5867.5417.5311. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4Kacdb4080120160200172.72169.91169.39168.301. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e12cbda0.49790.99581.49371.99162.48952.1592.1632.1632.2131. (CXX) g++ options: -O3

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streambcad0.21260.42520.63780.85041.0630.92320.93560.93940.9449

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streambcad20040060080010001079.571065.971060.951055.18

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamcabd36912159.89979.973910.023310.1216

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamcabd20406080100100.95100.2199.7198.75

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streambadc81624324035.8535.8335.7735.19

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streambadc71421283527.8727.8827.9328.39

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 1080pcdba51015202522.3922.2422.1622.031. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Streamacbd163248648068.8969.6469.8869.95

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Streamacbd4812162014.5014.3414.2914.28

Google Draco

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Church Facadecbda1000200030004000500047654793482048371. (CXX) g++ options: -O3

Parallel BZIP2 Compression

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img Compressionbcad0.28170.56340.84511.12681.40851.2351561.2352871.2491841.2520941. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 1080pdcba306090120150154.50153.10152.79152.481. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Google Draco

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Lionbdac900180027003600450040414059406040921. (CXX) g++ options: -O3

Timed Linux Kernel Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigcadb61218243026.0426.0726.1326.36

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4Kadcb4080120160200168.80168.29168.20167.051. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Timed Linux Kernel Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigdacb4080120160200181.28181.56182.43183.15

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamadbc306090120150137.95137.82137.28136.56

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamdabc100200300400500460.91461.38462.52465.46

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamcadb4080120160200200.28199.07198.38198.34

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamcadb1.13352.2673.40054.5345.66754.98965.01995.03715.0378

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamadbc4080120160200197.61197.01195.87195.83

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamadbc1.14832.29663.44494.59325.74155.05805.07345.10305.1037

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamcadb4008001200160020001803.231800.711794.851788.80

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamcadb81624324035.4535.5035.6135.73

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streambacd81624324034.1234.0633.9933.89

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streambacd71421283529.2929.3529.4129.50

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streambadc122436486051.5151.6651.7151.84

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streambadc300600900120015001241.551238.061236.951233.71

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamdbac70140210280350343.53342.90342.28341.44

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e13dbac61218243024.9324.9825.0325.081. (CXX) g++ options: -O3

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamdbac0.65831.31661.97492.63323.29152.90802.91352.91882.9257

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streambdac4008001200160020001792.691789.811789.701781.89

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamcbda80160240320400349.80350.38350.44351.87

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streambdac81624324035.6735.7135.7235.87

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamcdba4080120160200182.81182.55182.11181.79

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamdacb0.65681.31361.97042.62723.2842.90352.90852.91732.9192

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamdacb70140210280350344.05343.46342.44342.21

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streambacd1.23022.46043.69064.92086.1515.44455.44635.45445.4675

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streambacd3K6K9K12K15K11722.5911719.0111702.1811674.25

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamacdb306090120150138.31137.97137.97137.79

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamcbad4812162013.8713.8913.9213.92

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamcbad100020003000400050004605.994598.884590.234589.15

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamcbad0.73971.47942.21912.95883.69853.27613.27743.27783.2877

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamcbad70140210280350304.90304.80304.76303.84

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcd100200300400500460.73461.22461.99462.03

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streambdac71421283529.2129.2429.2529.28

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streambdac81624324034.2334.2034.1834.15

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamadbc4008001200160020001904.081902.931902.911902.18

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabdc163248648073.9774.0074.0374.04

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamadcb2004006008001000864.35863.93863.85863.67

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamacbd81624324033.5733.5933.5933.60

62 Results Shown

srsRAN Project
Neural Magic DeepSparse:
  Llama2 Chat 7b Quantized - Asynchronous Multi-Stream:
    items/sec
    ms/batch
Stockfish
SVT-AV1
srsRAN Project
SVT-AV1:
  Preset 13 - Bosphorus 1080p
  Preset 8 - Bosphorus 4K
  Preset 4 - Bosphorus 4K
  Preset 12 - Bosphorus 4K
Primesieve
Neural Magic DeepSparse:
  ResNet-50, Sparse INT8 - Synchronous Single-Stream:
    ms/batch
    items/sec
  BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream:
    items/sec
    ms/batch
SVT-AV1
Neural Magic DeepSparse:
  Llama2 Chat 7b Quantized - Synchronous Single-Stream:
    ms/batch
    items/sec
Google Draco
Parallel BZIP2 Compression
SVT-AV1
Google Draco
Timed Linux Kernel Compilation
SVT-AV1
Timed Linux Kernel Compilation
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - 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, DistilBERT mnli - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  ResNet-50, Baseline - Synchronous Single-Stream:
    items/sec
Primesieve
Neural Magic DeepSparse:
  ResNet-50, Baseline - Synchronous Single-Stream
  ResNet-50, Baseline - Asynchronous Multi-Stream
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream
  ResNet-50, Baseline - Asynchronous Multi-Stream
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream