new tests

Intel Core i9-13900K testing with a ASUS PRIME Z790-P WIFI (0602 BIOS) and AMD Radeon RX 6700 XT 12GB on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2301230-PTS-NEWTESTS60&rdt&grr.

new testsProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionabcdIntel Core i9-13900K @ 4.00GHz (24 Cores / 32 Threads)ASUS PRIME Z790-P WIFI (0602 BIOS)Intel Device 7a2732GB1000GB Western Digital WDS100T1X0E-00AFY0AMD Radeon RX 6700 XT 12GB (2855/1000MHz)Realtek ALC897ASUS VP28UIntel Device 7a70Ubuntu 22.046.0.0-060000-generic (x86_64)GNOME Shell 42.4X Server 1.21.1.3 + Wayland4.6 Mesa 22.3.0-devel (git-8945375 2022-10-04 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48)1.3.230GCC 11.2.0ext43840x2160OpenBenchmarking.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 powersave (EPP: balance_performance) - CPU Microcode: 0x10e - Thermald 2.4.9Python 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 + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

new testskeydb: HMSET - 900keydb: HMSET - 500keydb: HMSET - 100keydb: LPUSH - 500keydb: LPUSH - 100keydb: SET - 900keydb: SADD - 900keydb: LPOP - 500keydb: LPOP - 100keydb: LPOP - 900keydb: SADD - 500keydb: GET - 500keydb: HMSET - 50deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - 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 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamkeydb: LPUSH - 900keydb: SADD - 100deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamkeydb: SET - 100keydb: SET - 500deepsparse: 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 Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - 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 - 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: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamkeydb: GET - 100keydb: GET - 900keydb: LPUSH - 50deepsparse: 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 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamkeydb: SET - 50deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamkeydb: LPOP - 50keydb: SADD - 50keydb: GET - 50abcd405828.74540612.07811193.33972928.701079455.031227964.691318361.981541362.821548101.631572282.981369793.361493932.89770419.02693.753417.0977694.203017.0593160.484274.6763913352.581301147.20531.490822.45831277181.121242079.00191.405962.472759.3747201.885865.998415.151023.574942.412465.847115.186181.6431146.836255.795017.91981526251.211563299.291885806.5610.300797.026622.511444.4092118.9735100.595611.871284.213954.4516220.22422051262.0314.728367.85277.9509125.70402355768.582240005.252301457.08385409.94575162.19838926.19932940.251009102.121200999.251402721.251142413.251082813.621132092.51365262.251558846.38827088.81697.459117.0299693.696117.2641161.855373.963988728.51326330.25530.176422.5721180776.881314786.12192.559862.032559.0448202.872166.007915.148823.575742.410765.782615.200881.6896146.763855.631317.972314822281582378.621849522.7510.345996.600422.542744.3471117.1808102.185411.854184.335453.7491223.11232074172.3814.60768.41137.8702126.99192032602.882210042.52203905.25373870.94544525.88858045.061020158.311053252.51209599.381331770.751166752.251133555.511714541294096.251476886.75822828.56696.458617.1322695.233417.0024159.44375.2056967361.251443334.75528.695522.48291105998.881188354.12191.387362.433559.1069202.741466.033115.143123.475342.592266.111915.124780.4175148.978556.088717.82571488316.621527463.751964096.2510.229997.697122.61644.2034118.6662100.92211.814784.615553.8481222.58162007790.2514.646668.22687.8877126.713220147482215133.752258764405919.94514398.03762636.94925805.941161008.621305926.381264958.121101928.381110666.751168661.121296243.381553518.62781066.94693.884517.2573693.832917.2405161.020274.4384934195.311235605.25523.944922.87711296008.251307531.38189.932162.936858.8037203.720265.974815.156423.5742.420665.890715.175881.7629146.707955.8517.9021484384.381510802.121816596.3810.298897.045622.526144.3803117.9462101.580811.802884.703554.3784220.6292013693.1214.433569.23087.8787126.84822016942.2521865572273450.75OpenBenchmarking.org

KeyDB

Test: HMSET - Parallel Connections: 900

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: HMSET - Parallel Connections: 900abcd90K180K270K360K450KSE +/- 8190.09, N = 12405828.74385409.94373870.94405919.941. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: HMSET - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: HMSET - Parallel Connections: 500abcd120K240K360K480K600KSE +/- 11687.20, N = 15540612.07575162.19544525.88514398.031. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: HMSET - Parallel Connections: 100

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: HMSET - Parallel Connections: 100abcd200K400K600K800K1000KSE +/- 7152.65, N = 15811193.33838926.19858045.06762636.941. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: LPUSH - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: LPUSH - Parallel Connections: 500abcd200K400K600K800K1000KSE +/- 11803.30, N = 15972928.70932940.251020158.31925805.941. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: LPUSH - Parallel Connections: 100

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: LPUSH - Parallel Connections: 100abcd200K400K600K800K1000KSE +/- 19016.70, N = 151079455.031009102.121053252.501161008.621. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: SET - Parallel Connections: 900

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: SET - Parallel Connections: 900abcd300K600K900K1200K1500KSE +/- 10170.24, N = 151227964.691200999.251209599.381305926.381. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: SADD - Parallel Connections: 900

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: SADD - Parallel Connections: 900abcd300K600K900K1200K1500KSE +/- 13077.27, N = 151318361.981402721.251331770.751264958.121. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: LPOP - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: LPOP - Parallel Connections: 500abcd300K600K900K1200K1500KSE +/- 15335.07, N = 151541362.821142413.251166752.251101928.381. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: LPOP - Parallel Connections: 100

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: LPOP - Parallel Connections: 100abcd300K600K900K1200K1500KSE +/- 18631.04, N = 151548101.631082813.621133555.501110666.751. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: LPOP - Parallel Connections: 900

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: LPOP - Parallel Connections: 900abcd300K600K900K1200K1500KSE +/- 21774.31, N = 151572282.981132092.501171454.001168661.121. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: SADD - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: SADD - Parallel Connections: 500abcd300K600K900K1200K1500KSE +/- 20006.28, N = 121369793.361365262.251294096.251296243.381. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: GET - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: GET - Parallel Connections: 500abcd300K600K900K1200K1500KSE +/- 21838.17, N = 121493932.891558846.381476886.751553518.621. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: HMSET - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: HMSET - Parallel Connections: 50abcd200K400K600K800K1000KSE +/- 10277.06, N = 3770419.02827088.81822828.56781066.941. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabcd150300450600750SE +/- 1.58, N = 3693.75697.46696.46693.88

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabcd48121620SE +/- 0.09, N = 317.1017.0317.1317.26

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcd150300450600750SE +/- 2.02, N = 3694.20693.70695.23693.83

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcd48121620SE +/- 0.06, N = 317.0617.2617.0017.24

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamabcd4080120160200SE +/- 0.25, N = 3160.48161.86159.44161.02

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamabcd20406080100SE +/- 0.11, N = 374.6873.9675.2174.44

KeyDB

Test: LPUSH - Parallel Connections: 900

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: LPUSH - Parallel Connections: 900abcd200K400K600K800K1000KSE +/- 7796.97, N = 3913352.58988728.50967361.25934195.311. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: SADD - Parallel Connections: 100

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: SADD - Parallel Connections: 100abcd300K600K900K1200K1500KSE +/- 13610.75, N = 51301147.201326330.251443334.751235605.251. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabcd110220330440550SE +/- 0.36, N = 3531.49530.18528.70523.94

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabcd510152025SE +/- 0.04, N = 322.4622.5722.4822.88

KeyDB

Test: SET - Parallel Connections: 100

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: SET - Parallel Connections: 100abcd300K600K900K1200K1500KSE +/- 6390.36, N = 31277181.121180776.881105998.881296008.251. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: SET - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: SET - Parallel Connections: 500abcd300K600K900K1200K1500KSE +/- 7859.44, N = 31242079.001314786.121188354.121307531.381. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

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 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamabcd4080120160200SE +/- 0.42, N = 3191.41192.56191.39189.93

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 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamabcd1428425670SE +/- 0.15, N = 362.4762.0362.4362.94

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 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamabcd1326395265SE +/- 0.65, N = 359.3759.0459.1158.80

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 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamabcd4080120160200SE +/- 2.21, N = 3201.89202.87202.74203.72

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabcd1530456075SE +/- 0.08, N = 366.0066.0166.0365.97

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabcd48121620SE +/- 0.02, N = 315.1515.1515.1415.16

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamabcd612182430SE +/- 0.04, N = 323.5723.5823.4823.57

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamabcd1020304050SE +/- 0.08, N = 342.4142.4142.5942.42

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabcd1530456075SE +/- 0.18, N = 365.8565.7866.1165.89

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabcd48121620SE +/- 0.04, N = 315.1915.2015.1215.18

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabcd20406080100SE +/- 0.08, N = 381.6481.6980.4281.76

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabcd306090120150SE +/- 0.16, N = 3146.84146.76148.98146.71

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabcd1326395265SE +/- 0.14, N = 355.8055.6356.0955.85

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabcd48121620SE +/- 0.04, N = 317.9217.9717.8317.90

KeyDB

Test: GET - Parallel Connections: 100

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: GET - Parallel Connections: 100abcd300K600K900K1200K1500KSE +/- 12834.74, N = 31526251.211482228.001488316.621484384.381. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: GET - Parallel Connections: 900

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: GET - Parallel Connections: 900abcd300K600K900K1200K1500KSE +/- 20017.86, N = 31563299.291582378.621527463.751510802.121. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: LPUSH - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: LPUSH - Parallel Connections: 50abcd400K800K1200K1600K2000KSE +/- 22045.54, N = 41885806.561849522.751964096.251816596.381. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

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 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamabcd3691215SE +/- 0.02, N = 310.3010.3510.2310.30

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 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamabcd20406080100SE +/- 0.18, N = 397.0396.6097.7097.05

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 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamabcd510152025SE +/- 0.04, N = 322.5122.5422.6222.53

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 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamabcd1020304050SE +/- 0.08, N = 344.4144.3544.2044.38

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabcd306090120150SE +/- 0.61, N = 3118.97117.18118.67117.95

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamabcd20406080100SE +/- 0.45, N = 3100.60102.19100.92101.58

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabcd3691215SE +/- 0.03, N = 311.8711.8511.8111.80

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabcd20406080100SE +/- 0.18, N = 384.2184.3484.6284.70

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabcd1224364860SE +/- 0.36, N = 354.4553.7553.8554.38

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabcd50100150200250SE +/- 1.42, N = 3220.22223.11222.58220.63

KeyDB

Test: SET - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: SET - Parallel Connections: 50abcd400K800K1200K1600K2000KSE +/- 22564.98, N = 42051262.032074172.382007790.252013693.121. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabcd48121620SE +/- 0.07, N = 314.7314.6114.6514.43

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamabcd1530456075SE +/- 0.33, N = 367.8568.4168.2369.23

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcd246810SE +/- 0.0210, N = 37.95097.87027.88777.8787

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcd306090120150SE +/- 0.33, N = 3125.70126.99126.71126.85

KeyDB

Test: LPOP - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: LPOP - Parallel Connections: 50abcd500K1000K1500K2000K2500KSE +/- 25251.29, N = 32355768.582032602.882014748.002016942.251. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: SADD - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: SADD - Parallel Connections: 50abcd500K1000K1500K2000K2500KSE +/- 14787.63, N = 32240005.252210042.502215133.752186557.001. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD

KeyDB

Test: GET - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: GET - Parallel Connections: 50abcd500K1000K1500K2000K2500KSE +/- 12561.87, N = 32301457.082203905.252258764.002273450.751. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD


Phoronix Test Suite v10.8.5