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.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2307296-NE-8490H1S1663
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

CPU Massive 2 Tests
Creator Workloads 2 Tests
Database Test Suite 3 Tests
Multi-Core 2 Tests
Server 3 Tests
Common Workstation Benchmarks 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
July 28 2023
  1 Hour, 52 Minutes
b
July 28 2023
  2 Hours, 53 Minutes
c
July 28 2023
  1 Hour, 26 Minutes
d
July 28 2023
  1 Hour, 25 Minutes
e
July 29 2023
  1 Hour, 25 Minutes
Invert Hiding All Results Option
  1 Hour, 48 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):


8490h 1sOpenBenchmarking.orgPhoronix Test SuiteIntel 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 11.2.0ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen Resolution8490h 1s PerformanceSystem 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,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 - Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0 - OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu122.04)- Python 3.10.6- 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

abcdeResult OverviewPhoronix Test Suite100%104%108%112%116%Apache CassandraRedis 7.0.12 + memtier_benchmarkDragonflydbBRL-CADNeural Magic DeepSparseBlender

8490h 1scassandra: Writesmemtier-benchmark: Redis - 100 - 1:10deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streammemtier-benchmark: Redis - 100 - 1:1memtier-benchmark: Redis - 50 - 1:5memtier-benchmark: Redis - 100 - 1:5memtier-benchmark: Redis - 50 - 1:10deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streammemtier-benchmark: Redis - 50 - 1:1deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdragonflydb: 10 - 1:5deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdragonflydb: 10 - 1:10deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - 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: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - 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: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-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: BERT-Large, NLP Question Answering - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamblender: Fishy Cat - CPU-Onlydeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - 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: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdragonflydb: 10 - 1:100brl-cad: VGR Performance Metricdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamblender: Classroom - CPU-Onlydeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - 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 Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamblender: Pabellon Barcelona - CPU-Onlydeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamblender: BMW27 - CPU-Onlydeepsparse: CV Classification, ResNet-50 ImageNet - 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-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamblender: Barbershop - CPU-Onlydeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamcryptopp: Unkeyed Algorithmscryptopp: Keyed Algorithmscryptopp: All Algorithmsdragonflydb: 20 - 1:5abcde1346942929613.17759.48471.31442503378.332613416.652627400.982646929.55137.5084218.1115534.50142462536.6656.119314247982.45117.22668.5248121.88648.198914662941.423.7271267.9943475.718163.006586.9311.4928184.38675.4182648.317546.247562.5753.6608272.7991208.95614.783447.240321.164735.7557.076525.1385180.1415.5454479.12514338166.158259175.4431183.633268.9335.491128.1702192.5033155.801315.70388.731905.980825.001539.9427780.398225.7438.394461.647216.214535.76427.9552396.73475.603486.039386.4291346.938838.4127780.4996348.5304868.4975272.9134.49045672.79935.268452.343734595.3652011663.9209551349322583878.29746.70731.33712630752.032546591.862710324.972544897.58133.779224.1648517.16342470315.9157.789214476834.10114.61478.7193123.67818.080414292262.523.6871270.8536487.464661.510287.158211.4653185.74535.3786644.049546.544061.59563.6961270.2295209.10214.780247.250421.161135.2657.5702520.8695179.68165.5592486.185114432034.218236025.4340183.926869.1635.361328.2735191.9935156.210915.831688.51891.056524.991739.9583781.302425.6338.372761.891316.150435.719927.9897395.209975.881885.933286.2508347.655238.3371782.0400348.7206869.4702273.1434.46345678.51525.26271217082611551.59758.33591.31672460387.752516320.692554516.652508415.59135.9984220.4888517.83752377430.1457.925314235868.61116.34838.5903124.62248.01914204640.253.677271.6229487.176461.54686.78611.5118184.19665.4239649.297746.178161.41433.7248268.146208.42834.795647.415121.087135.0357.9918516.0418178.71895.5886488.245514307949.038204105.4372183.81970.0335.622328.0659191.6104156.461515.825788.831891.32725.007139.9318780.331225.6938.405461.608816.224135.855527.884396.682875.61386.275986.1641348.011738.4104780.5294347.5917870.7567272.6434.41935677.0355.26321409342593991.1759.42531.31462493158.972452685.992549066.222487096.51130.5153229.4472511.41862383147.0758.250814750102.52117.22358.5255123.45438.094514205235.713.6743271.7797485.715461.693587.340111.4418184.93195.402648.386446.243662.17483.6938270.3481209.65554.767547.473221.061335.1658.2129514.8982180.43865.5358482.435414571297.778128065.4307184.04769.1635.592528.0901190.8181157.175615.83888.181890.570525.045439.8698778.762925.7538.491161.828316.166635.756927.9607396.993675.552386.293986.5253346.560638.422780.3141347.5128871.2052272.4134.40175665.46995.27431378492755166.14709.15491.40762474272.952444450.112541163.682540848.35137.7614217.7184520.22392414601.0757.212114392511.79113.24198.8247120.44098.297314390358.993.7788264.3062488.249461.419485.15911.7345181.19935.5134633.445547.316961.06963.7499266.3444205.24284.869948.218620.73635.557.5236519.2686177.01055.642488.234714492478.368229775.5183181.128969.2535.094428.488191.4971156.556215.716888.091905.149125.13239.7368782.543925.7138.31261.845816.161435.881627.8637396.165175.712486.126186.1663347.760438.2796783.198348.1392870.6664272.4434.42265679.78055.2615OpenBenchmarking.org

Apache Cassandra

This is a benchmark of the Apache Cassandra NoSQL database management system making use of cassandra-stress. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.1.3Test: Writescabed30K60K90K120K150K121708134694134932137849140934

Redis 7.0.12 + memtier_benchmark

Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10bdcea600K1200K1800K2400K3000K2583878.292593991.102611551.592755166.142929613.171. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamebcda160320480640800SE +/- 0.65, N = 3709.15746.71758.34759.43759.48
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamebcda130260390520650Min: 745.81 / Avg: 746.71 / Max: 747.97

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamebcda0.31670.63340.95011.26681.5835SE +/- 0.0011, N = 31.40761.33711.31671.31461.3144
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamebcda246810Min: 1.33 / Avg: 1.34 / Max: 1.34

Redis 7.0.12 + memtier_benchmark

Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:1cedab600K1200K1800K2400K3000K2460387.752474272.952493158.972503378.332630752.031. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:5edcba600K1200K1800K2400K3000K2444450.112452685.992516320.692546591.862613416.651. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5edcab600K1200K1800K2400K3000K2541163.682549066.222554516.652627400.982710324.971. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10dceba600K1200K1800K2400K3000K2487096.512508415.592540848.352544897.582646929.551. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streameacbd306090120150137.76137.51136.00133.78130.52

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streameacbd50100150200250217.72218.11220.49224.16229.45

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamaecbd120240360480600SE +/- 1.23, N = 3534.50520.22517.84517.16511.42
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamaecbd90180270360450Min: 514.94 / Avg: 517.16 / Max: 519.2

Redis 7.0.12 + memtier_benchmark

Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:1cdeab500K1000K1500K2000K2500K2377430.142383147.072414601.072462536.662470315.911. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamaebcd1326395265SE +/- 0.18, N = 356.1257.2157.7957.9358.25
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamaebcd1224364860Min: 57.59 / Avg: 57.79 / Max: 58.15

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:5caebd3M6M9M12M15MSE +/- 71046.49, N = 314235868.6114247982.4514392511.7914476834.1014750102.521. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:5caebd3M6M9M12M15MMin: 14334901.06 / Avg: 14476834.1 / Max: 14553637.611. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamebcda306090120150113.24114.61116.35117.22117.23

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamebcda2468108.82478.71938.59038.52558.5248

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streameadbc306090120150SE +/- 0.43, N = 3120.44121.89123.45123.68124.62
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streameadbc20406080100Min: 122.98 / Avg: 123.68 / Max: 124.46

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streameadbc246810SE +/- 0.0280, N = 38.29738.19898.09458.08048.0190
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streameadbc3691215Min: 8.03 / Avg: 8.08 / Max: 8.13

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:10cdbea3M6M9M12M15MSE +/- 31999.75, N = 314204640.2514205235.7114292262.5214390358.9914662941.421. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:10cdbea3M6M9M12M15MMin: 14236827.92 / Avg: 14292262.52 / Max: 14347678.311. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streameabcd0.85021.70042.55063.40084.251SE +/- 0.0060, N = 33.77883.72713.68713.67703.6743
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streameabcd246810Min: 3.68 / Avg: 3.69 / Max: 3.7

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streameabcd60120180240300SE +/- 0.45, N = 3264.31267.99270.85271.62271.78
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streameabcd50100150200250Min: 269.96 / Avg: 270.85 / Max: 271.34

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamadcbe110220330440550SE +/- 0.85, N = 3475.72485.72487.18487.46488.25
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamadcbe90180270360450Min: 486.55 / Avg: 487.46 / Max: 489.16

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamadcbe1428425670SE +/- 0.11, N = 363.0161.6961.5561.5161.42
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamadcbe1224364860Min: 61.29 / Avg: 61.51 / Max: 61.62

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamecabd20406080100SE +/- 0.09, N = 385.1686.7986.9387.1687.34
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamecabd20406080100Min: 87.06 / Avg: 87.16 / Max: 87.33

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamecabd3691215SE +/- 0.01, N = 311.7311.5111.4911.4711.44
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamecabd3691215Min: 11.44 / Avg: 11.47 / Max: 11.48

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamecadb4080120160200SE +/- 0.69, N = 3181.20184.20184.39184.93185.75
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamecadb306090120150Min: 184.82 / Avg: 185.75 / Max: 187.09

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamecadb1.24052.4813.72154.9626.2025SE +/- 0.0199, N = 35.51345.42395.41825.40205.3786
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamecadb246810Min: 5.34 / Avg: 5.38 / Max: 5.41

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamebadc140280420560700SE +/- 5.86, N = 3633.45644.05648.32648.39649.30
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamebadc110220330440550Min: 632.36 / Avg: 644.05 / Max: 650.63

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamebadc1122334455SE +/- 0.41, N = 347.3246.5446.2546.2446.18
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamebadc1020304050Min: 46.08 / Avg: 46.54 / Max: 47.36

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamecbda1428425670SE +/- 0.44, N = 361.0761.4161.6062.1762.58
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamecbda1224364860Min: 60.77 / Avg: 61.6 / Max: 62.25

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamecbda0.84371.68742.53113.37484.2185SE +/- 0.0089, N = 33.74993.72483.69613.69383.6608
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamecbda246810Min: 3.68 / Avg: 3.7 / Max: 3.71

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamecbda60120180240300SE +/- 0.64, N = 3266.34268.15270.23270.35272.80
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamecbda50100150200250Min: 269.2 / Avg: 270.23 / Max: 271.4

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamecabd50100150200250SE +/- 0.71, N = 3205.24208.43208.96209.10209.66
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamecabd4080120160200Min: 207.85 / Avg: 209.1 / Max: 210.31

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamecabd1.09572.19143.28714.38285.4785SE +/- 0.0162, N = 34.86994.79564.78344.78024.7675
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamecabd246810Min: 4.75 / Avg: 4.78 / Max: 4.81

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamedcba1122334455SE +/- 0.16, N = 348.2247.4747.4247.2547.24
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamedcba1020304050Min: 46.98 / Avg: 47.25 / Max: 47.53

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamedcba510152025SE +/- 0.07, N = 320.7421.0621.0921.1621.16
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamedcba510152025Min: 21.04 / Avg: 21.16 / Max: 21.28

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Fishy Cat - Compute: CPU-Onlyaebdc81624324035.7535.5035.2635.1635.03

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamaebcd132639526557.0857.5257.5757.9958.21

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabecd110220330440550525.14520.87519.27516.04514.90

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamecbad4080120160200SE +/- 0.21, N = 3177.01178.72179.68180.14180.44
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamecbad306090120150Min: 179.42 / Avg: 179.68 / Max: 180.1

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamecbad1.26952.5393.80855.0786.3475SE +/- 0.0064, N = 35.64205.58865.55925.54545.5358
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamecbad246810Min: 5.55 / Avg: 5.56 / Max: 5.57

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamcebda110220330440550SE +/- 2.68, N = 3488.25488.23486.19482.44479.13
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamcebda90180270360450Min: 481.82 / Avg: 486.19 / Max: 491.07

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:100cabed3M6M9M12M15MSE +/- 145332.09, N = 314307949.0314338166.1514432034.2114492478.3614571297.771. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:100cabed3M6M9M12M15MMin: 14179386.08 / Avg: 14432034.21 / Max: 14682820.881. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

BRL-CAD

BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.36VGR Performance Metricdceba200K400K600K800K1000K8128068204108229778236028259171. (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

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streameacbd1.24162.48323.72484.96646.208SE +/- 0.0092, N = 35.51835.44315.43725.43405.4307
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streameacbd246810Min: 5.42 / Avg: 5.43 / Max: 5.45

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streameacbd4080120160200SE +/- 0.31, N = 3181.13183.63183.82183.93184.05
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streameacbd306090120150Min: 183.53 / Avg: 183.93 / Max: 184.55

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Classroom - Compute: CPU-Onlycedba163248648070.0369.2569.1669.1668.93

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamebadc816243240SE +/- 0.07, N = 335.0935.3635.4935.5935.62
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamebadc816243240Min: 35.25 / Avg: 35.36 / Max: 35.48

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamebadc714212835SE +/- 0.05, N = 328.4928.2728.1728.0928.07
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamebadc612182430Min: 28.18 / Avg: 28.27 / Max: 28.37

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamdecba4080120160200SE +/- 0.10, N = 3190.82191.50191.61191.99192.50
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamdecba4080120160200Min: 191.86 / Avg: 191.99 / Max: 192.19

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamdecba306090120150SE +/- 0.08, N = 3157.18156.56156.46156.21155.80
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamdecba306090120150Min: 156.06 / Avg: 156.21 / Max: 156.31

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamdbcea48121620SE +/- 0.01, N = 315.8415.8315.8315.7215.70
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamdbcea48121620Min: 15.81 / Avg: 15.83 / Max: 15.84

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Pabellon Barcelona - Compute: CPU-Onlycabde2040608010088.8388.7388.5088.1888.09

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamdbcea400800120016002000SE +/- 1.24, N = 31890.571891.061891.331905.151905.98
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamdbcea30060090012001500Min: 1889.29 / Avg: 1891.06 / Max: 1893.44

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamedcab612182430SE +/- 0.00, N = 325.1325.0525.0125.0024.99
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamedcab612182430Min: 24.98 / Avg: 24.99 / Max: 25

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamedcab918273645SE +/- 0.01, N = 339.7439.8739.9339.9439.96
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamedcab816243240Min: 39.95 / Avg: 39.96 / Max: 39.97

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamdcabe2004006008001000SE +/- 0.42, N = 3778.76780.33780.40781.30782.54
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamdcabe140280420560700Min: 780.57 / Avg: 781.3 / Max: 782.03

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: BMW27 - Compute: CPU-Onlydaecb61218243025.7525.7425.7125.6925.63

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamdcabe918273645SE +/- 0.02, N = 338.4938.4138.3938.3738.31
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamdcabe816243240Min: 38.34 / Avg: 38.37 / Max: 38.41

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamcadeb142842567061.6161.6561.8361.8561.89

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamcadeb4812162016.2216.2116.1716.1616.15

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streambdace81624324035.7235.7635.7635.8635.88

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streambdace71421283527.9927.9627.9627.8827.86

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamdaceb90180270360450SE +/- 1.22, N = 3396.99396.73396.68396.17395.21
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamdaceb70140210280350Min: 392.84 / Avg: 395.21 / Max: 396.89

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamdaceb20406080100SE +/- 0.23, N = 375.5575.6075.6175.7175.88
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamdaceb1530456075Min: 75.57 / Avg: 75.88 / Max: 76.32

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamdceab20406080100SE +/- 0.14, N = 386.2986.2886.1386.0485.93
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamdceab1632486480Min: 85.67 / Avg: 85.93 / Max: 86.12

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamdabec20406080100SE +/- 0.08, N = 386.5386.4386.2586.1786.16
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamdabec1632486480Min: 86.12 / Avg: 86.25 / Max: 86.4

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamdabec80160240320400SE +/- 0.33, N = 3346.56346.94347.66347.76348.01
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamdabec60120180240300Min: 347.05 / Avg: 347.66 / Max: 348.17

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamdacbe918273645SE +/- 0.04, N = 338.4238.4138.4138.3438.28
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamdacbe816243240Min: 38.26 / Avg: 38.34 / Max: 38.39

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamdacbe2004006008001000SE +/- 0.80, N = 3780.31780.50780.53782.04783.20
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamdacbe140280420560700Min: 780.91 / Avg: 782.04 / Max: 783.58

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamdceab80160240320400SE +/- 0.57, N = 3347.51347.59348.14348.53348.72
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamdceab60120180240300Min: 348.1 / Avg: 348.72 / Max: 349.87

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabecd2004006008001000SE +/- 0.53, N = 3868.50869.47870.67870.76871.21
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabecd150300450600750Min: 868.66 / Avg: 869.47 / Max: 870.48

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Barbershop - Compute: CPU-Onlybaced60120180240300273.14272.91272.64272.44272.41

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabecd816243240SE +/- 0.02, N = 334.4934.4634.4234.4234.40
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabecd714212835Min: 34.43 / Avg: 34.46 / Max: 34.5

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamdacbe12002400360048006000SE +/- 3.30, N = 35665.475672.805677.045678.525679.78
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamdacbe10002000300040005000Min: 5674.66 / Avg: 5678.52 / Max: 5685.09

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamdacbe1.18672.37343.56014.74685.9335SE +/- 0.0032, N = 35.27435.26805.26325.26275.2615
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamdacbe246810Min: 5.26 / Avg: 5.26 / Max: 5.27

Crypto++

Crypto++ is a C++ class library of cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

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

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

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

Redis 7.0.12 + memtier_benchmark

Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:10

a: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

b: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

c: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

d: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

e: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:5

a: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

b: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

c: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

d: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

e: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

Protocol: Redis - Clients: 500 - Set To Get Ratio: 1:1

a: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

b: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

c: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

d: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

e: The test run did not produce a result. E: error: failed to prepare thread 56 for test.

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

Clients Per Thread: 20 - Set To Get Ratio: 1:100

a: The test run did not produce a result. E: Connection error: Connection refused

b: The test run did not produce a result. E: Connection error: Connection reset by peer

c: The test run did not produce a result. E: Connection error: Connection reset by peer

d: The test run did not produce a result. E: Connection error: Connection refused

e: The test run did not produce a result. E: Connection error: Connection reset by peer

Clients Per Thread: 20 - Set To Get Ratio: 1:10

a: The test run did not produce a result. E: Connection error: Connection reset by peer

b: The test run did not produce a result. E: Connection error: Connection reset by peer

c: The test run did not produce a result. E: Connection error: Connection reset by peer

d: The test run did not produce a result. E: Connection error: Connection refused

e: The test run did not produce a result. E: Connection error: Connection reset by peer

Clients Per Thread: 20 - Set To Get Ratio: 1:5

a: The test run did not produce a result. E: Connection error: Connection reset by peer

b: The test run did not produce a result. E: Connection error: Connection reset by peer

c: The test run did not produce a result. E: Connection error: Connection reset by peer

d: The test run did not produce a result. E: Connection error: Connection reset by peer

e: The test run did not produce a result. E: Connection error: Connection reset by peer

79 Results Shown

Apache Cassandra
Redis 7.0.12 + memtier_benchmark
Neural Magic DeepSparse:
  ResNet-50, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
Redis 7.0.12 + memtier_benchmark:
  Redis - 100 - 1:1
  Redis - 50 - 1:5
  Redis - 100 - 1:5
  Redis - 50 - 1:10
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    ms/batch
Redis 7.0.12 + memtier_benchmark
Neural Magic DeepSparse
Dragonflydb
Neural Magic DeepSparse:
  BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    items/sec
    ms/batch
Dragonflydb
Neural Magic DeepSparse:
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering - Asynchronous Multi-Stream:
    items/sec
  ResNet-50, Baseline - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering - Synchronous Single-Stream:
    ms/batch
    items/sec
Blender
Neural Magic DeepSparse:
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream:
    items/sec
    ms/batch
  BERT-Large, NLP Question Answering - Asynchronous Multi-Stream:
    ms/batch
Dragonflydb
BRL-CAD
Neural Magic DeepSparse:
  CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream:
    ms/batch
    items/sec
Blender
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
Blender
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream
Blender
Neural Magic DeepSparse:
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream
  NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream
  NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream
  ResNet-50, Baseline - Asynchronous Multi-Stream
  ResNet-50, Baseline - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream
Blender
Neural Magic DeepSparse:
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream
Crypto++:
  Unkeyed Algorithms
  Keyed Algorithms
  All Algorithms