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&gru&rdt&rro.

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 testsdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-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 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamkeydb: GET - 50keydb: SET - 50keydb: GET - 100keydb: GET - 500keydb: GET - 900keydb: LPOP - 50keydb: SADD - 50keydb: SET - 100keydb: SET - 500keydb: SET - 900keydb: HMSET - 50keydb: LPOP - 100keydb: LPOP - 500keydb: LPOP - 900keydb: LPUSH - 50keydb: SADD - 100keydb: SADD - 500keydb: SADD - 900keydb: HMSET - 100keydb: HMSET - 500keydb: HMSET - 900keydb: LPUSH - 100keydb: LPUSH - 500keydb: LPUSH - 900deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-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 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamabcd17.097715.1510201.885897.026662.472744.4092100.595667.8527220.2242125.7040146.836284.213922.458317.919874.676342.412417.059315.18612301457.082051262.031526251.211493932.891563299.292355768.582240005.251277181.121242079.001227964.69770419.021548101.631541362.821572282.981885806.561301147.201369793.361318361.98811193.33540612.07405828.741079455.03972928.70913352.58693.753465.998459.374710.3007191.405922.5114118.973514.728354.45167.950981.643111.8712531.490855.7950160.484223.5749694.203065.847117.029915.1488202.872196.600462.032544.3471102.185468.4113223.1123126.9919146.763884.335422.57217.972373.96342.410717.264115.20082203905.252074172.3814822281558846.381582378.622032602.882210042.51180776.881314786.121200999.25827088.811082813.621142413.251132092.51849522.751326330.251365262.251402721.25838926.19575162.19385409.941009102.12932940.25988728.5697.459166.007959.044810.3459192.559822.5427117.180814.60753.74917.870281.689611.8541530.176455.6313161.855323.5757693.696165.782617.132215.1431202.741497.697162.433544.2034100.92268.2268222.5816126.7132148.978584.615522.482917.825775.205642.592217.002415.124722587642007790.251488316.621476886.751527463.7520147482215133.751105998.881188354.121209599.38822828.561133555.51166752.2511714541964096.251443334.751294096.251331770.75858045.06544525.88373870.941053252.51020158.31967361.25696.458666.033159.106910.2299191.387322.616118.666214.646653.84817.887780.417511.8147528.695556.0887159.44323.4753695.233466.111917.257315.1564203.720297.045662.936844.3803101.580869.2308220.629126.8482146.707984.703522.877117.90274.438442.420617.240515.17582273450.752013693.121484384.381553518.621510802.122016942.2521865571296008.251307531.381305926.38781066.941110666.751101928.381168661.121816596.381235605.251296243.381264958.12762636.94514398.03405919.941161008.62925805.94934195.31693.884565.974858.803710.2988189.932122.5261117.946214.433554.37847.878781.762911.8028523.944955.85161.020223.57693.832965.8907OpenBenchmarking.org

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-Streamdcba48121620SE +/- 0.09, N = 317.2617.1317.0317.10

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-Streamdcba48121620SE +/- 0.02, N = 315.1615.1415.1515.15

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-Streamdcba4080120160200SE +/- 2.21, N = 3203.72202.74202.87201.89

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-Streamdcba20406080100SE +/- 0.18, N = 397.0597.7096.6097.03

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-Streamdcba1428425670SE +/- 0.15, N = 362.9462.4362.0362.47

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-Streamdcba1020304050SE +/- 0.08, N = 344.3844.2044.3544.41

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-Streamdcba20406080100SE +/- 0.45, N = 3101.58100.92102.19100.60

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-Streamdcba1530456075SE +/- 0.33, N = 369.2368.2368.4167.85

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-Streamdcba50100150200250SE +/- 1.42, N = 3220.63222.58223.11220.22

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-Streamdcba306090120150SE +/- 0.33, N = 3126.85126.71126.99125.70

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-Streamdcba306090120150SE +/- 0.16, N = 3146.71148.98146.76146.84

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-Streamdcba20406080100SE +/- 0.18, N = 384.7084.6284.3484.21

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-Streamdcba510152025SE +/- 0.04, N = 322.8822.4822.5722.46

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-Streamdcba48121620SE +/- 0.04, N = 317.9017.8317.9717.92

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-Streamdcba20406080100SE +/- 0.11, N = 374.4475.2173.9674.68

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-Streamdcba1020304050SE +/- 0.08, N = 342.4242.5942.4142.41

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-Streamdcba48121620SE +/- 0.06, N = 317.2417.0017.2617.06

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-Streamdcba48121620SE +/- 0.04, N = 315.1815.1215.2015.19

KeyDB

Test: GET - Parallel Connections: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: GET - Parallel Connections: 50dcba500K1000K1500K2000K2500KSE +/- 12561.87, N = 32273450.752258764.002203905.252301457.081. (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: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: SET - Parallel Connections: 50dcba400K800K1200K1600K2000KSE +/- 22564.98, N = 42013693.122007790.252074172.382051262.031. (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: GET - Parallel Connections: 100

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: GET - Parallel Connections: 100dcba300K600K900K1200K1500KSE +/- 12834.74, N = 31484384.381488316.621482228.001526251.211. (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: 500dcba300K600K900K1200K1500KSE +/- 21838.17, N = 121553518.621476886.751558846.381493932.891. (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: 900dcba300K600K900K1200K1500KSE +/- 20017.86, N = 31510802.121527463.751582378.621563299.291. (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: 50

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: LPOP - Parallel Connections: 50dcba500K1000K1500K2000K2500KSE +/- 25251.29, N = 32016942.252014748.002032602.882355768.581. (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: 50dcba500K1000K1500K2000K2500KSE +/- 14787.63, N = 32186557.002215133.752210042.502240005.251. (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: 100

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: SET - Parallel Connections: 100dcba300K600K900K1200K1500KSE +/- 6390.36, N = 31296008.251105998.881180776.881277181.121. (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: SET - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: SET - Parallel Connections: 500dcba300K600K900K1200K1500KSE +/- 7859.44, N = 31307531.381188354.121314786.121242079.001. (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: SET - Parallel Connections: 900

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: SET - Parallel Connections: 900dcba300K600K900K1200K1500KSE +/- 10170.24, N = 151305926.381209599.381200999.251227964.691. (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: 50dcba200K400K600K800K1000KSE +/- 10277.06, N = 3781066.94822828.56827088.81770419.021. (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: 100dcba300K600K900K1200K1500KSE +/- 18631.04, N = 151110666.751133555.501082813.621548101.631. (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: 500dcba300K600K900K1200K1500KSE +/- 15335.07, N = 151101928.381166752.251142413.251541362.821. (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: 900dcba300K600K900K1200K1500KSE +/- 21774.31, N = 151168661.121171454.001132092.501572282.981. (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: 50dcba400K800K1200K1600K2000KSE +/- 22045.54, N = 41816596.381964096.251849522.751885806.561. (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: 100dcba300K600K900K1200K1500KSE +/- 13610.75, N = 51235605.251443334.751326330.251301147.201. (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: 500dcba300K600K900K1200K1500KSE +/- 20006.28, N = 121296243.381294096.251365262.251369793.361. (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: 900dcba300K600K900K1200K1500KSE +/- 13077.27, N = 151264958.121331770.751402721.251318361.981. (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: 100dcba200K400K600K800K1000KSE +/- 7152.65, N = 15762636.94858045.06838926.19811193.331. (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: 500dcba120K240K360K480K600KSE +/- 11687.20, N = 15514398.03544525.88575162.19540612.071. (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: 900

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: HMSET - Parallel Connections: 900dcba90K180K270K360K450KSE +/- 8190.09, N = 12405919.94373870.94385409.94405828.741. (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: 100dcba200K400K600K800K1000KSE +/- 19016.70, N = 151161008.621053252.501009102.121079455.031. (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: LPUSH - Parallel Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: LPUSH - Parallel Connections: 500dcba200K400K600K800K1000KSE +/- 11803.30, N = 15925805.941020158.31932940.25972928.701. (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: 900

OpenBenchmarking.orgRequests Per Second, More Is BetterKeyDB 6.3.2Test: LPUSH - Parallel Connections: 900dcba200K400K600K800K1000KSE +/- 7796.97, N = 3934195.31967361.25988728.50913352.581. (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-Streamdcba150300450600750SE +/- 1.58, N = 3693.88696.46697.46693.75

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-Streamdcba1530456075SE +/- 0.08, N = 365.9766.0366.0166.00

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-Streamdcba1326395265SE +/- 0.65, N = 358.8059.1159.0459.37

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-Streamdcba3691215SE +/- 0.02, N = 310.3010.2310.3510.30

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-Streamdcba4080120160200SE +/- 0.42, N = 3189.93191.39192.56191.41

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-Streamdcba510152025SE +/- 0.04, N = 322.5322.6222.5422.51

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-Streamdcba306090120150SE +/- 0.61, N = 3117.95118.67117.18118.97

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-Streamdcba48121620SE +/- 0.07, N = 314.4314.6514.6114.73

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-Streamdcba1224364860SE +/- 0.36, N = 354.3853.8553.7554.45

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-Streamdcba246810SE +/- 0.0210, N = 37.87877.88777.87027.9509

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-Streamdcba20406080100SE +/- 0.08, N = 381.7680.4281.6981.64

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-Streamdcba3691215SE +/- 0.03, N = 311.8011.8111.8511.87

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-Streamdcba110220330440550SE +/- 0.36, N = 3523.94528.70530.18531.49

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-Streamdcba1326395265SE +/- 0.14, N = 355.8556.0955.6355.80

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-Streamdcba4080120160200SE +/- 0.25, N = 3161.02159.44161.86160.48

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-Streamdcba612182430SE +/- 0.04, N = 323.5723.4823.5823.57

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-Streamdcba150300450600750SE +/- 2.02, N = 3693.83695.23693.70694.20

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-Streamdcba1530456075SE +/- 0.18, N = 365.8966.1165.7865.85

Phoronix Test Suite v10.8.5