8490h 1s

Intel Xeon Platinum 8490H testing with a Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) and ASPEED on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2307296-NE-8490H1S1663&sro&grt.

8490h 1sProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionabcdeIntel Xeon Platinum 8490H @ 3.50GHz (60 Cores / 120 Threads)Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS)Intel Device 1bce512GB3 x 3841GB Micron_9300_MTFDHAL3T8TDPASPEED4 x Intel E810-C for QSFPUbuntu 22.045.15.0-47-generic (x86_64)GNOME Shell 42.4X Server 1.21.1.31.2.204GCC 11.2.0ext41024x768OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --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,brig,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-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/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 Processor Details- Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0 Java Details- OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu122.04)Python Details- Python 3.10.6Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

8490h 1scassandra: Writesblender: BMW27 - CPU-Onlyblender: Classroom - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Barbershop - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlybrl-cad: VGR Performance Metriccryptopp: All Algorithmscryptopp: Keyed Algorithmscryptopp: Unkeyed Algorithmsdragonflydb: 10 - 1:5dragonflydb: 10 - 1:10dragonflydb: 10 - 1:100deepsparse: 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: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - 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 Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - 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-Streammemtier-benchmark: Redis - 50 - 1:1memtier-benchmark: Redis - 50 - 1:5memtier-benchmark: Redis - 100 - 1:1memtier-benchmark: Redis - 100 - 1:5memtier-benchmark: Redis - 50 - 1:10memtier-benchmark: Redis - 100 - 1:10memtier-benchmark: Redis - 500 - 1:10abcde13469425.7468.9335.75272.9188.738259171663.920955595.365201452.34373414247982.4514662941.4214338166.1556.1193534.501435.491128.17021905.980815.703208.95614.7834648.317546.2475180.1415.5454192.5033155.801386.9311.4928780.499638.4127272.79913.66085672.79935.268759.48471.3144346.938886.4291184.38675.418262.575479.12521.164747.2403780.398238.3944267.99433.7271348.530486.0393183.63325.4431475.718163.0065121.88648.198975.6034396.73439.942725.0015868.497534.4904117.22668.5248218.1115137.508461.647216.214557.076525.138535.76427.95522462536.662613416.652503378.332627400.982646929.552929613.1713493225.6369.1635.26273.1488.582360214476834.1014292262.5214432034.2157.7892517.163435.361328.27351891.056515.8316209.10214.7802644.049546.5440179.68165.5592191.9935156.210987.158211.4653782.040038.3371270.22953.69615678.51525.2627746.70731.3371347.655286.2508185.74535.378661.5956486.185121.161147.2504781.302438.3727270.85363.6871348.720685.9332183.92685.4340487.464661.5102123.67818.080475.8818395.209939.958324.9917869.470234.4634114.61478.7193224.1648133.77961.891316.150457.5702520.869535.719927.98972470315.912546591.862630752.032710324.972544897.582583878.2912170825.6970.0335.03272.6488.8382041014235868.6114204640.2514307949.0357.9253517.837535.622328.06591891.32715.8257208.42834.7956649.297746.1781178.71895.5886191.6104156.461586.78611.5118780.529438.4104268.1463.72485677.0355.2632758.33591.3167348.011786.1641184.19665.423961.4143488.245521.087147.4151780.331238.4054271.62293.677347.591786.2759183.8195.4372487.176461.546124.62248.01975.613396.682839.931825.0071870.756734.4193116.34838.5903220.4888135.998461.608816.224157.9918516.041835.855527.8842377430.142516320.692460387.752554516.652508415.592611551.5914093425.7569.1635.16272.4188.1881280614750102.5214205235.7114571297.7758.2508511.418635.592528.09011890.570515.838209.65554.7675648.386446.2436180.43865.5358190.8181157.175687.340111.4418780.314138.422270.34813.69385665.46995.2743759.42531.3146346.560686.5253184.93195.40262.1748482.435421.061347.4732778.762938.4911271.77973.6743347.512886.2939184.0475.4307485.715461.6935123.45438.094575.5523396.993639.869825.0454871.205234.4017117.22358.5255229.4472130.515361.828316.166658.2129514.898235.756927.96072383147.072452685.992493158.972549066.222487096.512593991.113784925.7169.2535.5272.4488.0982297714392511.7914390358.9914492478.3657.2121520.223935.094428.4881905.149115.7168205.24284.8699633.445547.3169177.01055.642191.4971156.556285.15911.7345783.19838.2796266.34443.74995679.78055.2615709.15491.4076347.760486.1663181.19935.513461.0696488.234720.73648.2186782.543938.312264.30623.7788348.139286.1261181.12895.5183488.249461.4194120.44098.297375.7124396.165139.736825.132870.666434.4226113.24198.8247217.7184137.761461.845816.161457.5236519.268635.881627.86372414601.072444450.112474272.952541163.682540848.352755166.14OpenBenchmarking.org

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.1.3Test: Writesabcde30K60K90K120K150K134694134932121708140934137849

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: BMW27 - Compute: CPU-Onlyabcde61218243025.7425.6325.6925.7525.71

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Classroom - Compute: CPU-Onlyabcde163248648068.9369.1670.0369.1669.25

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Fishy Cat - Compute: CPU-Onlyabcde81624324035.7535.2635.0335.1635.50

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Barbershop - Compute: CPU-Onlyabcde60120180240300272.91273.14272.64272.41272.44

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Pabellon Barcelona - Compute: CPU-Onlyabcde2040608010088.7388.5088.8388.1888.09

BRL-CAD

VGR Performance Metric

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.36VGR Performance Metricabcde200K400K600K800K1000K8259178236028204108128068229771. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6

Crypto++

Test: All Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.8Test: All Algorithmsa4008001200160020001663.921. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

Crypto++

Test: Keyed Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.8Test: Keyed Algorithmsa130260390520650595.371. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

Crypto++

Test: Unkeyed Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.8Test: Unkeyed Algorithmsa100200300400500452.341. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

Dragonflydb

Clients Per Thread: 10 - Set To Get Ratio: 1:5

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:5abcde3M6M9M12M15MSE +/- 71046.49, N = 314247982.4514476834.1014235868.6114750102.5214392511.791. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Dragonflydb

Clients Per Thread: 10 - Set To Get Ratio: 1:10

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:10abcde3M6M9M12M15MSE +/- 31999.75, N = 314662941.4214292262.5214204640.2514205235.7114390358.991. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Dragonflydb

Clients Per Thread: 10 - Set To Get Ratio: 1:100

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:100abcde3M6M9M12M15MSE +/- 145332.09, N = 314338166.1514432034.2114307949.0314571297.7714492478.361. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabcde1326395265SE +/- 0.18, N = 356.1257.7957.9358.2557.21

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabcde120240360480600SE +/- 1.23, N = 3534.50517.16517.84511.42520.22

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabcde816243240SE +/- 0.07, N = 335.4935.3635.6235.5935.09

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabcde714212835SE +/- 0.05, N = 328.1728.2728.0728.0928.49

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcde400800120016002000SE +/- 1.24, N = 31905.981891.061891.331890.571905.15

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcde48121620SE +/- 0.01, N = 315.7015.8315.8315.8415.72

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabcde50100150200250SE +/- 0.71, N = 3208.96209.10208.43209.66205.24

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabcde1.09572.19143.28714.38285.4785SE +/- 0.0162, N = 34.78344.78024.79564.76754.8699

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamabcde140280420560700SE +/- 5.86, N = 3648.32644.05649.30648.39633.45

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamabcde1122334455SE +/- 0.41, N = 346.2546.5446.1846.2447.32

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamabcde4080120160200SE +/- 0.21, N = 3180.14179.68178.72180.44177.01

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamabcde1.26952.5393.80855.0786.3475SE +/- 0.0064, N = 35.54545.55925.58865.53585.6420

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamabcde4080120160200SE +/- 0.10, N = 3192.50191.99191.61190.82191.50

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamabcde306090120150SE +/- 0.08, N = 3155.80156.21156.46157.18156.56

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamabcde20406080100SE +/- 0.09, N = 386.9387.1686.7987.3485.16

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamabcde3691215SE +/- 0.01, N = 311.4911.4711.5111.4411.73

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabcde2004006008001000SE +/- 0.80, N = 3780.50782.04780.53780.31783.20

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabcde918273645SE +/- 0.04, N = 338.4138.3438.4138.4238.28

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabcde60120180240300SE +/- 0.64, N = 3272.80270.23268.15270.35266.34

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabcde0.84371.68742.53113.37484.2185SE +/- 0.0089, N = 33.66083.69613.72483.69383.7499

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcde12002400360048006000SE +/- 3.30, N = 35672.805678.525677.045665.475679.78

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcde1.18672.37343.56014.74685.9335SE +/- 0.0032, N = 35.26805.26275.26325.27435.2615

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabcde160320480640800SE +/- 0.65, N = 3759.48746.71758.34759.43709.15

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabcde0.31670.63340.95011.26681.5835SE +/- 0.0011, N = 31.31441.33711.31671.31461.4076

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabcde80160240320400SE +/- 0.33, N = 3346.94347.66348.01346.56347.76

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabcde20406080100SE +/- 0.08, N = 386.4386.2586.1686.5386.17

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabcde4080120160200SE +/- 0.69, N = 3184.39185.75184.20184.93181.20

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabcde1.24052.4813.72154.9626.2025SE +/- 0.0199, N = 35.41825.37865.42395.40205.5134

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamabcde1428425670SE +/- 0.44, N = 362.5861.6061.4162.1761.07

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamabcde110220330440550SE +/- 2.68, N = 3479.13486.19488.25482.44488.23

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamabcde510152025SE +/- 0.07, N = 321.1621.1621.0921.0620.74

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamabcde1122334455SE +/- 0.16, N = 347.2447.2547.4247.4748.22

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabcde2004006008001000SE +/- 0.42, N = 3780.40781.30780.33778.76782.54

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabcde918273645SE +/- 0.02, N = 338.3938.3738.4138.4938.31

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcde60120180240300SE +/- 0.45, N = 3267.99270.85271.62271.78264.31

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcde0.85021.70042.55063.40084.251SE +/- 0.0060, N = 33.72713.68713.67703.67433.7788

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcde80160240320400SE +/- 0.57, N = 3348.53348.72347.59347.51348.14

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcde20406080100SE +/- 0.14, N = 386.0485.9386.2886.2986.13

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabcde4080120160200SE +/- 0.31, N = 3183.63183.93183.82184.05181.13

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabcde1.24162.48323.72484.96646.208SE +/- 0.0092, N = 35.44315.43405.43725.43075.5183

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabcde110220330440550SE +/- 0.85, N = 3475.72487.46487.18485.72488.25

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabcde1428425670SE +/- 0.11, N = 363.0161.5161.5561.6961.42

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabcde306090120150SE +/- 0.43, N = 3121.89123.68124.62123.45120.44

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabcde246810SE +/- 0.0280, N = 38.19898.08048.01908.09458.2973

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabcde20406080100SE +/- 0.23, N = 375.6075.8875.6175.5575.71

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabcde90180270360450SE +/- 1.22, N = 3396.73395.21396.68396.99396.17

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabcde918273645SE +/- 0.01, N = 339.9439.9639.9339.8739.74

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabcde612182430SE +/- 0.00, N = 325.0024.9925.0125.0525.13

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcde2004006008001000SE +/- 0.53, N = 3868.50869.47870.76871.21870.67

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcde816243240SE +/- 0.02, N = 334.4934.4634.4234.4034.42

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabcde306090120150117.23114.61116.35117.22113.24

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabcde2468108.52488.71938.59038.52558.8247

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamabcde50100150200250218.11224.16220.49229.45217.72

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamabcde306090120150137.51133.78136.00130.52137.76

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamabcde142842567061.6561.8961.6161.8361.85

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamabcde4812162016.2116.1516.2216.1716.16

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcde132639526557.0857.5757.9958.2157.52

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcde110220330440550525.14520.87516.04514.90519.27

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabcde81624324035.7635.7235.8635.7635.88

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabcde71421283527.9627.9927.8827.9627.86

Redis 7.0.12 + memtier_benchmark

Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:1

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:1abcde500K1000K1500K2000K2500K2462536.662470315.912377430.142383147.072414601.071. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Redis 7.0.12 + memtier_benchmark

Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:5

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:5abcde600K1200K1800K2400K3000K2613416.652546591.862516320.692452685.992444450.111. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Redis 7.0.12 + memtier_benchmark

Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:1

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:1abcde600K1200K1800K2400K3000K2503378.332630752.032460387.752493158.972474272.951. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Redis 7.0.12 + memtier_benchmark

Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5abcde600K1200K1800K2400K3000K2627400.982710324.972554516.652549066.222541163.681. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Redis 7.0.12 + memtier_benchmark

Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10abcde600K1200K1800K2400K3000K2646929.552544897.582508415.592487096.512540848.351. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Redis 7.0.12 + memtier_benchmark

Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10abcde600K1200K1800K2400K3000K2929613.172583878.292611551.592593991.102755166.141. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre


Phoronix Test Suite v10.8.5