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&sor&grr.

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 1sbrl-cad: VGR Performance Metriccryptopp: All Algorithmscryptopp: Keyed Algorithmsblender: Barbershop - CPU-Onlycryptopp: Unkeyed Algorithmsdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamcassandra: Writesdeepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdragonflydb: 10 - 1:5dragonflydb: 10 - 1:100dragonflydb: 10 - 1:10blender: Pabellon Barcelona - CPU-Onlydeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, 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: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - 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 Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streammemtier-benchmark: Redis - 100 - 1:10memtier-benchmark: Redis - 100 - 1:5memtier-benchmark: Redis - 100 - 1:1blender: Classroom - CPU-Onlydeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streammemtier-benchmark: Redis - 50 - 1:5memtier-benchmark: Redis - 50 - 1:10memtier-benchmark: Redis - 50 - 1:1deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - 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: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-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: 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 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 Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, 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: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-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: 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: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - 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 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamblender: Fishy Cat - CPU-Onlyblender: BMW27 - CPU-Onlydragonflydb: 20 - 1:100abcde8259171663.920955595.365201272.91452.343734479.12562.57513469447.240321.16478.5248117.226614247982.4514338166.1514662941.4288.7334.4904868.49754.7834208.9561396.73475.603415.7031905.9808534.501456.11932929613.172627400.982503378.3368.93155.8013192.50332613416.652646929.552462536.6628.170235.491146.2475648.317525.001539.942711.492886.935.5454180.14163.0065475.71818.1989121.88645.4182184.38671.3144759.484738.4127780.49963.6608272.799186.4291346.938886.0393348.53045.4431183.633238.3944780.39823.7271267.99435.2685672.7993137.5084218.1115525.138557.07616.214561.647227.955235.76435.7525.74823602273.14486.185161.595613493247.250421.16118.7193114.614714476834.1014432034.2114292262.5288.534.4634869.47024.7802209.1021395.209975.881815.83161891.0565517.163457.78922583878.292710324.972630752.0369.16156.2109191.99352546591.862544897.582470315.9128.273535.361346.5440644.049524.991739.958311.465387.15825.5592179.681661.5102487.46468.0804123.67815.3786185.74531.3371746.707338.3371782.04003.6961270.229586.2508347.655285.9332348.72065.4340183.926838.3727781.30243.6871270.85365.26275678.5152133.779224.1648520.869557.570216.150461.891327.989735.719935.2625.63820410272.64488.245561.414312170847.415121.08718.5903116.348314235868.6114307949.0314204640.2588.8334.4193870.75674.7956208.4283396.682875.61315.82571891.327517.837557.92532611551.592554516.652460387.7570.03156.4615191.61042516320.692508415.592377430.1428.065935.622346.1781649.297725.007139.931811.511886.7865.5886178.718961.546487.17648.019124.62245.4239184.19661.3167758.335938.4104780.52943.7248268.14686.1641348.011786.2759347.59175.4372183.81938.4054780.33123.677271.62295.26325677.035135.9984220.4888516.041857.991816.224161.608827.88435.855535.0325.69812806272.41482.435462.174814093447.473221.06138.5255117.223514750102.5214571297.7714205235.7188.1834.4017871.20524.7675209.6555396.993675.552315.8381890.5705511.418658.25082593991.12549066.222493158.9769.16157.1756190.81812452685.992487096.512383147.0728.090135.592546.2436648.386425.045439.869811.441887.34015.5358180.438661.6935485.71548.0945123.45435.402184.93191.3146759.425338.422780.31413.6938270.348186.5253346.560686.2939347.51285.4307184.04738.4911778.76293.6743271.77975.27435665.4699130.5153229.4472514.898258.212916.166661.828327.960735.756935.1625.75822977272.44488.234761.069613784948.218620.7368.8247113.241914392511.7914492478.3614390358.9988.0934.4226870.66644.8699205.2428396.165175.712415.71681905.1491520.223957.21212755166.142541163.682474272.9569.25156.5562191.49712444450.112540848.352414601.0728.48835.094447.3169633.445525.13239.736811.734585.1595.642177.010561.4194488.24948.2973120.44095.5134181.19931.4076709.154938.2796783.1983.7499266.344486.1663347.760486.1261348.13925.5183181.128938.312782.54393.7788264.30625.26155679.7805137.7614217.7184519.268657.523616.161461.845827.863735.881635.525.71OpenBenchmarking.org

BRL-CAD

VGR Performance Metric

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.36VGR Performance Metricabecd200K400K600K800K1000K8259178236028229778204108128061. (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

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Barbershop - Compute: CPU-Onlydecab60120180240300272.41272.44272.64272.91273.14

Crypto++

Test: Unkeyed Algorithms

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

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-Streamadbec110220330440550SE +/- 2.68, N = 3479.13482.44486.19488.23488.25

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-Streamadbce1428425670SE +/- 0.44, N = 362.5862.1761.6061.4161.07

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.1.3Test: Writesdebac30K60K90K120K150K140934137849134932134694121708

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: 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, 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-Streamadcbe2468108.52488.52558.59038.71938.8247

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-Streamadcbe306090120150117.23117.22116.35114.61113.24

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: 1:5dbeac3M6M9M12M15MSE +/- 71046.49, N = 314750102.5214476834.1014392511.7914247982.4514235868.611. (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: 1:100debac3M6M9M12M15MSE +/- 145332.09, N = 314571297.7714492478.3614432034.2114338166.1514307949.031. (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: 1:10aebdc3M6M9M12M15MSE +/- 31999.75, N = 314662941.4214390358.9914292262.5214205235.7114204640.251. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Pabellon Barcelona - Compute: CPU-Onlyedbac2040608010088.0988.1888.5088.7388.83

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-Streamdceba816243240SE +/- 0.02, N = 334.4034.4234.4234.4634.49

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-Streamdceba2004006008001000SE +/- 0.53, N = 3871.21870.76870.67869.47868.50

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-Streamdbace1.09572.19143.28714.38285.4785SE +/- 0.0162, N = 34.76754.78024.78344.79564.8699

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-Streamdbace50100150200250SE +/- 0.71, N = 3209.66209.10208.96208.43205.24

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-Streambecad90180270360450SE +/- 1.22, N = 3395.21396.17396.68396.73396.99

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-Streambecad20406080100SE +/- 0.23, N = 375.8875.7175.6175.6075.55

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-Streamaecbd48121620SE +/- 0.01, N = 315.7015.7215.8315.8315.84

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-Streamaecbd400800120016002000SE +/- 1.24, N = 31905.981905.151891.331891.061890.57

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-Streamdbcea120240360480600SE +/- 1.23, N = 3511.42517.16517.84520.22534.50

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-Streamdcbea1326395265SE +/- 0.18, N = 358.2557.9357.7957.2156.12

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: 1:10aecdb600K1200K1800K2400K3000K2929613.172755166.142611551.592593991.102583878.291. (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: 1:5bacde600K1200K1800K2400K3000K2710324.972627400.982554516.652549066.222541163.681. (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: 1:1badec600K1200K1800K2400K3000K2630752.032503378.332493158.972474272.952460387.751. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Classroom - Compute: CPU-Onlyabdec163248648068.9369.1669.1669.2570.03

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-Streamabced306090120150SE +/- 0.08, N = 3155.80156.21156.46156.56157.18

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-Streamabced4080120160200SE +/- 0.10, N = 3192.50191.99191.61191.50190.82

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: 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: 1:10abecd600K1200K1800K2400K3000K2646929.552544897.582540848.352508415.592487096.511. (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: 1:1

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:1baedc500K1000K1500K2000K2500K2470315.912462536.662414601.072383147.072377430.141. (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: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamcdabe714212835SE +/- 0.05, N = 328.0728.0928.1728.2728.49

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-Streamcdabe816243240SE +/- 0.07, N = 335.6235.5935.4935.3635.09

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-Streamcdabe1122334455SE +/- 0.41, N = 346.1846.2446.2546.5447.32

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-Streamcdabe140280420560700SE +/- 5.86, N = 3649.30648.39648.32644.05633.45

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-Streambacde612182430SE +/- 0.00, N = 324.9925.0025.0125.0525.13

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-Streambacde918273645SE +/- 0.01, N = 339.9639.9439.9339.8739.74

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-Streamdbace3691215SE +/- 0.01, N = 311.4411.4711.4911.5111.73

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-Streamdbace20406080100SE +/- 0.09, N = 387.3487.1686.9386.7985.16

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-Streamdabce1.26952.5393.80855.0786.3475SE +/- 0.0064, N = 35.53585.54545.55925.58865.6420

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-Streamdabce4080120160200SE +/- 0.21, N = 3180.44180.14179.68178.72177.01

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-Streamebcda1428425670SE +/- 0.11, N = 361.4261.5161.5561.6963.01

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-Streamebcda110220330440550SE +/- 0.85, N = 3488.25487.46487.18485.72475.72

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-Streamcbdae246810SE +/- 0.0280, N = 38.01908.08048.09458.19898.2973

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-Streamcbdae306090120150SE +/- 0.43, N = 3124.62123.68123.45121.89120.44

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-Streambdace1.24052.4813.72154.9626.2025SE +/- 0.0199, N = 35.37865.40205.41825.42395.5134

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-Streambdace4080120160200SE +/- 0.69, N = 3185.75184.93184.39184.20181.20

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-Streamadcbe0.31670.63340.95011.26681.5835SE +/- 0.0011, N = 31.31441.31461.31671.33711.4076

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-Streamadcbe160320480640800SE +/- 0.65, N = 3759.48759.43758.34746.71709.15

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-Streamebcad918273645SE +/- 0.04, N = 338.2838.3438.4138.4138.42

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-Streamebcad2004006008001000SE +/- 0.80, N = 3783.20782.04780.53780.50780.31

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-Streamadbce0.84371.68742.53113.37484.2185SE +/- 0.0089, N = 33.66083.69383.69613.72483.7499

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-Streamadbce60120180240300SE +/- 0.64, N = 3272.80270.35270.23268.15266.34

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-Streamcebad20406080100SE +/- 0.08, N = 386.1686.1786.2586.4386.53

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-Streamcebad80160240320400SE +/- 0.33, N = 3348.01347.76347.66346.94346.56

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-Streambaecd20406080100SE +/- 0.14, N = 385.9386.0486.1386.2886.29

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-Streambaecd80160240320400SE +/- 0.57, N = 3348.72348.53348.14347.59347.51

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-Streamdbcae1.24162.48323.72484.96646.208SE +/- 0.0092, N = 35.43075.43405.43725.44315.5183

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-Streamdbcae4080120160200SE +/- 0.31, N = 3184.05183.93183.82183.63181.13

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-Streamebacd918273645SE +/- 0.02, N = 338.3138.3738.3938.4138.49

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-Streamebacd2004006008001000SE +/- 0.42, N = 3782.54781.30780.40780.33778.76

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-Streamdcbae0.85021.70042.55063.40084.251SE +/- 0.0060, N = 33.67433.67703.68713.72713.7788

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-Streamdcbae60120180240300SE +/- 0.45, N = 3271.78271.62270.85267.99264.31

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-Streamebcad1.18672.37343.56014.74685.9335SE +/- 0.0032, N = 35.26155.26275.26325.26805.2743

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-Streamebcad12002400360048006000SE +/- 3.30, N = 35679.785678.525677.045672.805665.47

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-Streamdbcae306090120150130.52133.78136.00137.51137.76

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-Streamdbcae50100150200250229.45224.16220.49218.11217.72

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-Streamdceba110220330440550514.90516.04519.27520.87525.14

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-Streamdcbea132639526558.2157.9957.5757.5257.08

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-Streambedac4812162016.1516.1616.1716.2116.22

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-Streambedac142842567061.8961.8561.8361.6561.61

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-Streamecadb71421283527.8627.8827.9627.9627.99

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-Streamecadb81624324035.8835.8635.7635.7635.72

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Fishy Cat - Compute: CPU-Onlycdbea81624324035.0335.1635.2635.5035.75

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: BMW27 - Compute: CPU-Onlybcead61218243025.6325.6925.7125.7425.75

Phoronix Test Suite v10.8.4