net

INTEL XEON PLATINUM 8592+ testing with a Quanta Cloud 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 2312187-NE-NET50813920
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:

CPU Massive 2 Tests
HPC - High Performance Computing 2 Tests
Machine Learning 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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
a
December 18 2023
  3 Hours, 20 Minutes
b
December 18 2023
  3 Hours, 20 Minutes
c
December 18 2023
  3 Hours, 16 Minutes
Invert Hiding All Results Option
  3 Hours, 19 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):


netOpenBenchmarking.orgPhoronix Test SuiteINTEL XEON PLATINUM 8592+ @ 3.90GHz (64 Cores / 128 Threads)Quanta Cloud S6Q-MB-MPS (3B05.TEL4P1 BIOS)Intel Device 1bce512GB3201GB Micron_7450_MTFDKCC3T2TFS + 0GB Virtual HDisk0 + 0GB Virtual HDisk2 + 0GB Virtual HDisk1 + 0GB Virtual HDisk3ASPEEDUbuntu 23.106.6.0-rc5-phx-patched (x86_64)GNOME Shell 45.0X Server 1.21.1.7GCC 13.2.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionNet 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- a: OpenJDK Runtime Environment (build 11.0.20+8-post-Ubuntu-1ubuntu1)- 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

abcResult OverviewPhoronix Test Suite100%101%101%102%102%LeelaChessZeroSVT-AV1Neural Magic DeepSparseXmrig

netlczero: BLASlczero: Eigenxmrig: KawPow - 1Mxmrig: Monero - 1Mxmrig: Wownero - 1Mxmrig: GhostRider - 1Mxmrig: CryptoNight-Heavy - 1Mxmrig: CryptoNight-Femto UPX2 - 1Msvt-av1: Preset 4 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Ksvt-av1: Preset 4 - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 1080psvt-av1: Preset 12 - Bosphorus 1080psvt-av1: Preset 13 - Bosphorus 1080pdeepsparse: 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-Streamabc6779639936.240329.643088.36862.940394.940425.97.15675.139228.874227.28520.770139.811545.910632.45971.9864442.311934.474929.00162323.979913.7504210.96384.7354934.652434.2126286.88823.48255706.69645.5953701.79151.4200436.522673.2660164.93936.057786.3024370.728731.224632.0197933.007434.2750290.01333.4452452.195170.7373166.65675.9970641.104749.8955186.02575.372996.1343332.806335.102328.4611938.066134.072567.869414.727672.0462442.221034.609228.88906780540344.740153.242998.76857.840282.240080.47.16875.737229.514229.55620.587141.977543.725636.90971.6759443.397134.482628.99532324.736213.7462210.81004.7386928.446234.4463290.28263.44175717.51855.5844705.82681.4123436.328673.2935164.89686.058986.2914370.776131.146532.0999934.522434.2173288.68493.4609452.164170.7412166.51236.0023637.609250.1708188.53765.300595.6329334.315334.617428.8654937.577534.090568.176014.661272.0875441.477634.625028.87566881740242.540072.243080.46820.840286.640331.17.15174.926228.518229.07520.492141.873546.877637.33771.9685442.752534.237729.20302322.580313.7597209.60954.7654939.536334.0380287.34693.47675704.95305.5965701.70611.4205435.493273.4267163.97186.092286.1709371.295731.187532.0585940.219834.0080289.80813.4473450.491871.0046166.30506.0096637.417550.1864188.23245.309296.8521330.335233.724629.6799937.863034.079267.580214.789871.7827443.158234.452629.0205OpenBenchmarking.org

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.30Backend: BLASabc1530456075SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 36767681. (CXX) g++ options: -flto -pthread

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.30Backend: Eigenabc2004006008001000SE +/- 21.82, N = 9SE +/- 11.08, N = 9SE +/- 32.94, N = 67968058171. (CXX) g++ options: -flto -pthread

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: KawPow - Hash Count: 1Macb9K18K27K36K45KSE +/- 185.86, N = 3SE +/- 102.95, N = 3SE +/- 97.76, N = 339936.240242.540344.71. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Monero - Hash Count: 1Mcba9K18K27K36K45KSE +/- 234.22, N = 3SE +/- 234.97, N = 3SE +/- 106.27, N = 340072.240153.240329.61. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Wownero - Hash Count: 1Mbca9K18K27K36K45KSE +/- 81.91, N = 3SE +/- 104.95, N = 3SE +/- 76.66, N = 342998.743080.443088.31. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1Mcba15003000450060007500SE +/- 18.86, N = 3SE +/- 29.78, N = 3SE +/- 5.37, N = 36820.86857.86862.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Heavy - Hash Count: 1Mbca9K18K27K36K45KSE +/- 64.66, N = 3SE +/- 169.87, N = 3SE +/- 42.10, N = 340282.240286.640394.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Femto UPX2 - Hash Count: 1Mbca9K18K27K36K45KSE +/- 72.11, N = 3SE +/- 88.91, N = 3SE +/- 55.21, N = 340080.440331.140425.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4Kcab246810SE +/- 0.071, N = 3SE +/- 0.022, N = 3SE +/- 0.025, N = 37.1517.1567.1681. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4Kcab20406080100SE +/- 0.15, N = 3SE +/- 0.38, N = 3SE +/- 0.27, N = 374.9375.1475.741. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4Kcab50100150200250SE +/- 1.46, N = 3SE +/- 0.42, N = 3SE +/- 1.07, N = 3228.52228.87229.511. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4Kacb50100150200250SE +/- 2.23, N = 3SE +/- 0.19, N = 3SE +/- 0.75, N = 3227.29229.08229.561. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 1080pcba510152025SE +/- 0.25, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 320.4920.5920.771. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 1080pacb306090120150SE +/- 0.16, N = 3SE +/- 1.86, N = 3SE +/- 1.29, N = 7139.81141.87141.981. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 1080pbac120240360480600SE +/- 3.52, N = 3SE +/- 4.95, N = 3SE +/- 4.85, N = 3543.73545.91546.881. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 1080pabc140280420560700SE +/- 3.46, N = 3SE +/- 4.83, N = 3SE +/- 4.46, N = 3632.46636.91637.341. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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-Streambca1632486480SE +/- 0.17, N = 3SE +/- 0.20, N = 3SE +/- 0.16, N = 371.6871.9771.99

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streambca100200300400500SE +/- 0.20, N = 3SE +/- 0.77, N = 3SE +/- 0.57, N = 3443.40442.75442.31

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamcab816243240SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 334.2434.4734.48

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamcab714212835SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 329.2029.0029.00

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamcab5001000150020002500SE +/- 0.54, N = 3SE +/- 2.42, N = 3SE +/- 2.92, N = 32322.582323.982324.74

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamcab48121620SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 313.7613.7513.75

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamcba50100150200250SE +/- 0.49, N = 3SE +/- 0.83, N = 3SE +/- 1.74, N = 3209.61210.81210.96

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamcba1.07222.14443.21664.28885.361SE +/- 0.0109, N = 3SE +/- 0.0188, N = 3SE +/- 0.0394, N = 34.76544.73864.7354

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streambac2004006008001000SE +/- 8.90, N = 3SE +/- 3.60, N = 3SE +/- 0.83, N = 3928.45934.65939.54

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streambac816243240SE +/- 0.33, N = 3SE +/- 0.13, N = 3SE +/- 0.03, N = 334.4534.2134.04

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamacb60120180240300SE +/- 0.98, N = 3SE +/- 1.23, N = 3SE +/- 0.65, N = 3286.89287.35290.28

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamacb0.78361.56722.35083.13443.918SE +/- 0.0119, N = 3SE +/- 0.0147, N = 3SE +/- 0.0077, N = 33.48253.47673.4417

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamcab12002400360048006000SE +/- 16.89, N = 3SE +/- 15.58, N = 3SE +/- 10.52, N = 35704.955706.705717.52

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamcab1.25922.51843.77765.03686.296SE +/- 0.0160, N = 3SE +/- 0.0153, N = 3SE +/- 0.0102, N = 35.59655.59535.5844

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamcab150300450600750SE +/- 0.26, N = 3SE +/- 2.07, N = 3SE +/- 2.96, N = 3701.71701.79705.83

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamcab0.31960.63920.95881.27841.598SE +/- 0.0007, N = 3SE +/- 0.0038, N = 3SE +/- 0.0057, N = 31.42051.42001.4123

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamcba90180270360450SE +/- 0.19, N = 3SE +/- 0.34, N = 3SE +/- 0.33, N = 3435.49436.33436.52

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamcba1632486480SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 373.4373.2973.27

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamcba4080120160200SE +/- 0.23, N = 3SE +/- 0.12, N = 3SE +/- 0.67, N = 3163.97164.90164.94

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamcba246810SE +/- 0.0081, N = 3SE +/- 0.0043, N = 3SE +/- 0.0247, N = 36.09226.05896.0577

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamcba20406080100SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.14, N = 386.1786.2986.30

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamcba80160240320400SE +/- 0.22, N = 3SE +/- 0.36, N = 3SE +/- 0.59, N = 3371.30370.78370.73

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streambca714212835SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 331.1531.1931.22

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streambca714212835SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 332.1032.0632.02

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabc2004006008001000SE +/- 3.85, N = 3SE +/- 4.66, N = 3SE +/- 0.19, N = 3933.01934.52940.22

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabc816243240SE +/- 0.14, N = 3SE +/- 0.17, N = 3SE +/- 0.01, N = 334.2834.2234.01

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streambca60120180240300SE +/- 0.99, N = 3SE +/- 0.98, N = 3SE +/- 1.63, N = 3288.68289.81290.01

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streambca0.77871.55742.33613.11483.8935SE +/- 0.0119, N = 3SE +/- 0.0117, N = 3SE +/- 0.0193, N = 33.46093.44733.4452

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamcba100200300400500SE +/- 0.54, N = 3SE +/- 0.02, N = 3SE +/- 0.30, N = 3450.49452.16452.20

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamcba1632486480SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 371.0070.7470.74

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamcba4080120160200SE +/- 0.19, N = 3SE +/- 0.25, N = 3SE +/- 0.33, N = 3166.31166.51166.66

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamcba246810SE +/- 0.0069, N = 3SE +/- 0.0087, N = 3SE +/- 0.0119, N = 36.00966.00235.9970

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamcba140280420560700SE +/- 2.11, N = 3SE +/- 1.94, N = 3SE +/- 0.45, N = 3637.42637.61641.10

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamcba1122334455SE +/- 0.17, N = 3SE +/- 0.15, N = 3SE +/- 0.03, N = 350.1950.1749.90

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamacb4080120160200SE +/- 1.59, N = 3SE +/- 0.41, N = 3SE +/- 0.69, N = 3186.03188.23188.54

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamacb1.20892.41783.62674.83566.0445SE +/- 0.0459, N = 3SE +/- 0.0116, N = 3SE +/- 0.0193, N = 35.37295.30925.3005

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streambac20406080100SE +/- 0.27, N = 3SE +/- 0.29, N = 3SE +/- 0.08, N = 395.6396.1396.85

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streambac70140210280350SE +/- 0.71, N = 3SE +/- 1.00, N = 3SE +/- 0.28, N = 3334.32332.81330.34

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamcba816243240SE +/- 0.38, N = 15SE +/- 0.35, N = 3SE +/- 0.16, N = 333.7234.6235.10

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamcba714212835SE +/- 0.34, N = 15SE +/- 0.29, N = 3SE +/- 0.12, N = 329.6828.8728.46

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streambca2004006008001000SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.34, N = 3937.58937.86938.07

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streambca816243240SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 334.0934.0834.07

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamcab1530456075SE +/- 0.11, N = 3SE +/- 0.27, N = 3SE +/- 0.12, N = 367.5867.8768.18

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamcab48121620SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 314.7914.7314.66

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamcab1632486480SE +/- 0.07, N = 3SE +/- 0.17, N = 3SE +/- 0.04, N = 371.7872.0572.09

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamcab100200300400500SE +/- 0.25, N = 3SE +/- 0.73, N = 3SE +/- 0.59, N = 3443.16442.22441.48

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamcab816243240SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 334.4534.6134.63

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamcab714212835SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 329.0228.8928.88

64 Results Shown

LeelaChessZero:
  BLAS
  Eigen
Xmrig:
  KawPow - 1M
  Monero - 1M
  Wownero - 1M
  GhostRider - 1M
  CryptoNight-Heavy - 1M
  CryptoNight-Femto UPX2 - 1M
SVT-AV1:
  Preset 4 - Bosphorus 4K
  Preset 8 - Bosphorus 4K
  Preset 12 - Bosphorus 4K
  Preset 13 - Bosphorus 4K
  Preset 4 - Bosphorus 1080p
  Preset 8 - Bosphorus 1080p
  Preset 12 - Bosphorus 1080p
  Preset 13 - Bosphorus 1080p
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