fggg

d

HTML result view exported from: https://openbenchmarking.org/result/2403172-NE-FGGG8186960&grs&sor.

fgggProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionabcIntel Core Ultra 7 155HIntel Core Ultra 7 155H @ 4.80GHz (16 Cores / 22 Threads)MTL Swift SFG14-72T Coral_MTH (V1.01 BIOS)Intel Device 7e7f8 x 2GB DRAM-6400MT/s Micron MT62F1G32D2DS-0261024GB Micron_2550_MTFDKBA1T0TGEIntel Arc MTL 8GB (2250MHz)Intel Meteor Lake-P HD AudioIntel Device 7e40Ubuntu 23.106.8.0-060800rc1daily20240126-generic (x86_64)GNOME Shell 45.2X Server 1.21.1.7 + Wayland4.6 Mesa 24.1~git2401200600.ebcab1~oibaf~m (git-ebcab14 2024-01-20 mantic-oibaf-ppa)GCC 13.2.0ext41920x1200OpenBenchmarking.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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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: 0x13 - Thermald 2.5.4Python Details- Python 3.11.6Security Details- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

fgggselenium: SilverBench - Google Chromesvt-av1: Preset 12 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Kstockfish: Chess Benchmarkdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streambuild-linux-kernel: allmodconfigselenium: SilverBench - Firefoxselenium: WASM imageConvolute - Google Chromeselenium: PSPDFKit WASM - Google Chromedeepsparse: 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-Streamselenium: Speedometer 3.0 - Google Chromeselenium: Kraken - Google Chromedeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamselenium: Speedometer 3.0 - Firefoxdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamcompress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compressiondeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamdeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamselenium: Kraken - Firefoxdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamselenium: WASM imageConvolute - Firefoxselenium: WASM collisionDetection - Firefoxdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamprimesieve: 1e13build-linux-kernel: defconfigdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamsvt-av1: Preset 4 - Bosphorus 1080pdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamselenium: PSPDFKit WASM - Firefoxsvt-av1: Preset 13 - Bosphorus 1080pdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamprimesieve: 1e12deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamsvt-av1: Preset 12 - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 1080psvt-av1: Preset 4 - Bosphorus 4Kselenium: WASM collisionDetection - Google Chromesvt-av1: Preset 8 - Bosphorus 4Kdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-StreamabcIntel Core Ultra 7 155H4997485.01284.3851041799522.639944.13312198.954137020.9104119.970350.04149.9143100.722118.2489.13.143316.583114.634.713328.78867.66918489.48742.88562353.99287.004778.0041599.8983.93818.541653.89323.228095.93265.552572.803454.0806361.144143.512.3239128.9833566.571425.197112.03839.66993.564274.78321224.521082434.212155.26396.43975.5873175.71845.6903202.113934.566175.99845.681224.84836.2569192.2847355.61186.3343.351221.4225.7961234.80177.9943125.05096806864.85464.1661057963723.411242.6812018.834145920.29102318.61253.691710.056399.30519.2462.63.0565325.439115.432.945630.33457.29007992.65192.91882313.37156.758575.3695614.61016.004519.007652.575922.4276.495.96425.753772.754955.1778349.939139.05212.1523126.6007574.670124.999812.28139.982890.895876.94251190.15151084433.457157.46536.34975.5932177.55845.6314201.747634.6216176.34185.670224.76136.5825190.558355.15885.8623.375219.625.9021235.58427.986125.17864896279.67484.8451200109724.420740.91632069.486137221.2109819.488951.277610.616694.062718.6463.43.1954311.496514.633.422129.90217.60246293.62562.86842364.7786.755774.664608.21020.227219.395351.525122.6280.794.97225.699373.553454.2522351.481141.98512.524128.6802557.73925.508512.19139.184893.494674.77781217.17891072425.855159.03516.28715.5129178.91185.5888198.934235.1325178.55965.599825.10436.6946190.0904356.15585.493.372220.9925.9441242.95537.9907125.10814422562.42478.9571032738324.731640.40412111.002134721.91102819.168552.131610.155498.3373184873.2294308.078215.232.940930.33727.39983494.09793.01562249.49246.673674.33986291030.840819.205152.029122.3287.592.59585.705975.39153.4604353.136142.412.2097130.4653571.953525.755211.92138.810893.203674.93181218.94121054436.602158.39796.31235.4819179.06725.584198.813735.1396175.87985.685125.03936.6392190.2256359.21185.7263.344220.1225.7551243.60777.9919125.0865OpenBenchmarking.org

Selenium

Benchmark: SilverBench - Browser: Google Chrome

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: SilverBench - Browser: Google ChromebacIntel Core Ultra 7 155H15K30K45K60K75K680684997448962442251. chrome 122.0.6261.128

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4KacbIntel Core Ultra 7 155H2040608010085.0179.6764.8562.421. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4KcaIntel Core Ultra 7 155Hb2040608010084.8584.3978.9664.171. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Stockfish

Chess Benchmark

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess BenchmarkcbaIntel Core Ultra 7 155H3M6M9M12M15M120010971057963710417995103273831. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-StreamabcIntel Core Ultra 7 155H61218243022.6423.4124.4224.73

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-StreamabcIntel Core Ultra 7 155H102030405044.1342.6840.9240.40

Timed Linux Kernel Compilation

Build: allmodconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigbcIntel Core Ultra 7 155Ha50010001500200025002018.832069.492111.002198.95

Selenium

Benchmark: SilverBench - Browser: Firefox

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: SilverBench - Browser: FirefoxbcaIntel Core Ultra 7 155H3006009001200150014591372137013471. firefox 121.0.1

Selenium

Benchmark: WASM imageConvolute - Browser: Google Chrome

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM imageConvolute - Browser: Google ChromebacIntel Core Ultra 7 155H51015202520.2920.9021.2021.911. chrome 122.0.6261.128

Selenium

Benchmark: PSPDFKit WASM - Browser: Google Chrome

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: Google ChromebIntel Core Ultra 7 155Hac200400600800100010231028104110981. chrome 122.0.6261.128

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-StreambIntel Core Ultra 7 155Hca51015202518.6119.1719.4919.97

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-StreambIntel Core Ultra 7 155Hca122436486053.6952.1351.2850.04

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-StreamabIntel Core Ultra 7 155Hc36912159.914310.056310.155410.6166

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-StreamabIntel Core Ultra 7 155Hc20406080100100.7299.3198.3494.06

Selenium

Benchmark: Speedometer 3.0 - Browser: Google Chrome

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Speedometer 3.0 - Browser: Google ChromebcaIntel Core Ultra 7 155H51015202519.218.618.218.01. chrome 122.0.6261.128

Selenium

Benchmark: Kraken - Browser: Google Chrome

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: Kraken - Browser: Google ChromebcIntel Core Ultra 7 155Ha110220330440550462.6463.4487.0489.11. chrome 122.0.6261.128

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-StreambacIntel Core Ultra 7 155H0.72661.45322.17982.90643.6333.05653.14303.19543.2294

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-StreambacIntel Core Ultra 7 155H70140210280350325.44316.58311.50308.08

Selenium

Benchmark: Speedometer 3.0 - Browser: Firefox

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Speedometer 3.0 - Browser: FirefoxbIntel Core Ultra 7 155Hca4812162015.415.214.614.61. firefox 121.0.1

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-StreamIntel Core Ultra 7 155Hbca81624324032.9432.9533.4234.71

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-StreamIntel Core Ultra 7 155Hbca71421283530.3430.3329.9028.79

Parallel BZIP2 Compression

FreeBSD-13.0-RELEASE-amd64-memstick.img Compression

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionbIntel Core Ultra 7 155Hca2468107.2900797.3998347.6024627.6691841. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamabcIntel Core Ultra 7 155H2040608010089.4992.6593.6394.10

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-StreamIntel Core Ultra 7 155Hbac0.67851.3572.03552.7143.39253.01562.91882.88562.8684

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-StreamIntel Core Ultra 7 155Hbac50010001500200025002249.492313.372353.992364.78

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamabcIntel Core Ultra 7 155H2468107.00476.75856.75576.6736

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamabcIntel Core Ultra 7 155H2040608010078.0075.3774.6674.34

Selenium

Benchmark: Kraken - Browser: Firefox

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: Kraken - Browser: FirefoxacbIntel Core Ultra 7 155H140280420560700599.8608.2614.6629.01. firefox 121.0.1

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamabcIntel Core Ultra 7 155H2004006008001000983.941016.001020.231030.84

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamabIntel Core Ultra 7 155Hc51015202518.5419.0119.2119.40

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamabIntel Core Ultra 7 155Hc122436486053.8952.5852.0351.53

Selenium

Benchmark: WASM imageConvolute - Browser: Firefox

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM imageConvolute - Browser: FirefoxIntel Core Ultra 7 155Hbca61218243022.322.422.623.21. firefox 121.0.1

Selenium

Benchmark: WASM collisionDetection - Browser: Firefox

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM collisionDetection - Browser: FirefoxbacIntel Core Ultra 7 155H60120180240300276.4280.0280.7287.51. firefox 121.0.1

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreambacIntel Core Ultra 7 155H2040608010095.9695.9394.9792.60

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreambIntel Core Ultra 7 155Hca1.29462.58923.88385.17846.4735.75375.70595.69935.5525

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreambacIntel Core Ultra 7 155H2040608010072.7572.8073.5575.39

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreambcaIntel Core Ultra 7 155H122436486055.1854.2554.0853.46

Primesieve

Length: 1e13

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e13bcIntel Core Ultra 7 155Ha80160240320400349.94351.48353.14361.141. (CXX) g++ options: -O3

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigbcIntel Core Ultra 7 155Ha306090120150139.05141.99142.40143.50

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreambIntel Core Ultra 7 155Hac369121512.1512.2112.3212.52

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreambcaIntel Core Ultra 7 155H306090120150126.60128.68128.98130.47

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreambIntel Core Ultra 7 155Hac120240360480600574.67571.95566.57557.74

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreambacIntel Core Ultra 7 155H61218243025.0025.2025.5125.76

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 1080pbcaIntel Core Ultra 7 155H369121512.2812.1912.0411.921. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreambacIntel Core Ultra 7 155H91827364539.9839.6739.1838.81

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreambIntel Core Ultra 7 155Hca2040608010090.9093.2093.4993.56

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreambIntel Core Ultra 7 155Hac2040608010076.9474.9374.7874.78

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreambcIntel Core Ultra 7 155Ha300600900120015001190.151217.181218.941224.52

Selenium

Benchmark: PSPDFKit WASM - Browser: Firefox

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: FirefoxIntel Core Ultra 7 155Hcab200400600800100010541072108210841. firefox 121.0.1

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 1080pIntel Core Ultra 7 155Habc90180270360450436.60434.21433.46425.861. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-StreamabIntel Core Ultra 7 155Hc4080120160200155.26157.47158.40159.04

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-StreamabIntel Core Ultra 7 155Hc2468106.43976.34976.31236.2871

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreambacIntel Core Ultra 7 155H1.25852.5173.77555.0346.29255.59325.58735.51295.4819

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamabcIntel Core Ultra 7 155H4080120160200175.72177.56178.91179.07

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamabcIntel Core Ultra 7 155H1.28032.56063.84095.12126.40155.69035.63145.58885.5840

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamabcIntel Core Ultra 7 155H4080120160200202.11201.75198.93198.81

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamabcIntel Core Ultra 7 155H81624324034.5734.6235.1335.14

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamIntel Core Ultra 7 155Habc4080120160200175.88176.00176.34178.56

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamIntel Core Ultra 7 155Habc1.27912.55823.83735.11646.39555.68515.68125.67025.5998

Primesieve

Length: 1e12

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e12baIntel Core Ultra 7 155Hc61218243024.7624.8525.0425.101. (CXX) g++ options: -O3

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamcIntel Core Ultra 7 155Hba81624324036.6936.6436.5836.26

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamcIntel Core Ultra 7 155Hba4080120160200190.09190.23190.56192.28

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 1080pIntel Core Ultra 7 155Hcab80160240320400359.21356.16355.61355.161. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 1080pabIntel Core Ultra 7 155Hc2040608010086.3385.8685.7385.491. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4KbcaIntel Core Ultra 7 155H0.75941.51882.27823.03763.7973.3753.3723.3513.3441. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Selenium

Benchmark: WASM collisionDetection - Browser: Google Chrome

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM collisionDetection - Browser: Google ChromebIntel Core Ultra 7 155Hca50100150200250219.60220.12220.99221.421. chrome 122.0.6261.128

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4KcbaIntel Core Ultra 7 155H61218243025.9425.9025.8025.761. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamabcIntel Core Ultra 7 155H300600900120015001234.801235.581242.961243.61

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-StreamaIntel Core Ultra 7 155Hcb2468107.99437.99197.99077.9860

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-StreamaIntel Core Ultra 7 155Hcb306090120150125.05125.09125.11125.18

Phoronix Test Suite v10.8.4