Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2403172-NE-FGGG8186960 fggg - Phoronix Test Suite fggg d
HTML result view exported from: https://openbenchmarking.org/result/2403172-NE-FGGG8186960&grt&sor .
fggg Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution a b c Intel Core Ultra 7 155H Intel Core Ultra 7 155H @ 4.80GHz (16 Cores / 22 Threads) MTL Swift SFG14-72T Coral_MTH (V1.01 BIOS) Intel Device 7e7f 8 x 2GB DRAM-6400MT/s Micron MT62F1G32D2DS-026 1024GB Micron_2550_MTFDKBA1T0TGE Intel Arc MTL 8GB (2250MHz) Intel Meteor Lake-P HD Audio Intel Device 7e40 Ubuntu 23.10 6.8.0-060800rc1daily20240126-generic (x86_64) GNOME Shell 45.2 X Server 1.21.1.7 + Wayland 4.6 Mesa 24.1~git2401200600.ebcab1~oibaf~m (git-ebcab14 2024-01-20 mantic-oibaf-ppa) GCC 13.2.0 ext4 1920x1200 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler 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 2.5.4 Python Details - Python 3.11.6 Security 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
fggg deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Synchronous Single-Stream deepsparse: ResNet-50, Baseline - Synchronous Single-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream deepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Stream deepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Stream deepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Stream deepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream compress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compression primesieve: 1e12 primesieve: 1e13 selenium: Kraken - Firefox selenium: SilverBench - Firefox selenium: Kraken - Google Chrome selenium: PSPDFKit WASM - Firefox selenium: Speedometer 3.0 - Firefox selenium: SilverBench - Google Chrome selenium: PSPDFKit WASM - Google Chrome selenium: WASM imageConvolute - Firefox selenium: Speedometer 3.0 - Google Chrome selenium: WASM collisionDetection - Firefox selenium: WASM imageConvolute - Google Chrome selenium: WASM collisionDetection - Google Chrome stockfish: Chess Benchmark svt-av1: Preset 4 - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 12 - Bosphorus 4K svt-av1: Preset 13 - Bosphorus 4K svt-av1: Preset 4 - Bosphorus 1080p svt-av1: Preset 8 - Bosphorus 1080p svt-av1: Preset 12 - Bosphorus 1080p svt-av1: Preset 13 - Bosphorus 1080p build-linux-kernel: defconfig build-linux-kernel: allmodconfig a b c Intel Core Ultra 7 155H 5.5525 1224.52 5.6812 175.9984 202.1139 34.566 100.7221 9.9143 74.7832 93.5642 50.0414 19.9703 566.5714 12.3239 316.5831 3.143 2.8856 2353.9928 7.9943 125.0509 78.0041 89.4874 53.893 18.5416 36.2569 192.2847 28.7886 34.7133 54.0806 128.9833 39.669 25.1971 7.0047 983.938 6.4397 155.2639 95.9326 72.8034 44.1331 22.6399 5.5873 1234.8017 5.6903 175.7184 7.669184 24.848 361.144 599.8 1370 489.1 1082 14.6 49974 1041 23.2 18.2 280 20.9 221.42 10417995 3.351 25.796 85.012 84.385 12.038 86.334 355.611 434.212 143.5 2198.954 5.7537 1190.1515 5.6702 176.3418 201.7476 34.6216 99.305 10.0563 76.9425 90.8958 53.6917 18.612 574.6701 12.1523 325.4391 3.0565 2.9188 2313.3715 7.986 125.1786 75.3695 92.6519 52.5759 19.0076 36.5825 190.558 30.3345 32.9456 55.1778 126.6007 39.9828 24.9998 6.7585 1016.0045 6.3497 157.4653 95.9642 72.7549 42.681 23.4112 5.5932 1235.5842 5.6314 177.5584 7.290079 24.761 349.939 614.6 1459 462.6 1084 15.4 68068 1023 22.4 19.2 276.4 20.29 219.6 10579637 3.375 25.902 64.854 64.166 12.281 85.862 355.158 433.457 139.052 2018.834 5.6993 1217.1789 5.5998 178.5596 198.9342 35.1325 94.0627 10.6166 74.7778 93.4946 51.2776 19.4889 557.739 12.524 311.4965 3.1954 2.8684 2364.778 7.9907 125.1081 74.664 93.6256 51.5251 19.3953 36.6946 190.0904 29.9021 33.4221 54.2522 128.6802 39.1848 25.5085 6.7557 1020.2272 6.2871 159.0351 94.9722 73.5534 40.9163 24.4207 5.5129 1242.9553 5.5888 178.9118 7.602462 25.104 351.481 608.2 1372 463.4 1072 14.6 48962 1098 22.6 18.6 280.7 21.2 220.99 12001097 3.372 25.944 79.674 84.845 12.191 85.49 356.155 425.855 141.985 2069.486 5.7059 1218.9412 5.6851 175.8798 198.8137 35.1396 98.3373 10.1554 74.9318 93.2036 52.1316 19.1685 571.9535 12.2097 308.0782 3.2294 3.0156 2249.4924 7.9919 125.0865 74.3398 94.0979 52.0291 19.2051 36.6392 190.2256 30.3372 32.9409 53.4604 130.4653 38.8108 25.7552 6.6736 1030.8408 6.3123 158.3979 92.5958 75.391 40.4041 24.7316 5.4819 1243.6077 5.584 179.0672 7.399834 25.039 353.136 629 1347 487 1054 15.2 44225 1028 22.3 18 287.5 21.91 220.12 10327383 3.344 25.755 62.424 78.957 11.921 85.726 359.211 436.602 142.4 2111.002 OpenBenchmarking.org
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream b Intel Core Ultra 7 155H c a 1.2946 2.5892 3.8838 5.1784 6.473 5.7537 5.7059 5.6993 5.5525
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream b c Intel Core Ultra 7 155H a 300 600 900 1200 1500 1190.15 1217.18 1218.94 1224.52
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream Intel Core Ultra 7 155H a b c 1.2791 2.5582 3.8373 5.1164 6.3955 5.6851 5.6812 5.6702 5.5998
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream Intel Core Ultra 7 155H a b c 40 80 120 160 200 175.88 176.00 176.34 178.56
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c Intel Core Ultra 7 155H 40 80 120 160 200 202.11 201.75 198.93 198.81
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c Intel Core Ultra 7 155H 8 16 24 32 40 34.57 34.62 35.13 35.14
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream a b Intel Core Ultra 7 155H c 20 40 60 80 100 100.72 99.31 98.34 94.06
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream a b Intel Core Ultra 7 155H c 3 6 9 12 15 9.9143 10.0563 10.1554 10.6166
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream b Intel Core Ultra 7 155H a c 20 40 60 80 100 76.94 74.93 74.78 74.78
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream b Intel Core Ultra 7 155H c a 20 40 60 80 100 90.90 93.20 93.49 93.56
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream b Intel Core Ultra 7 155H c a 12 24 36 48 60 53.69 52.13 51.28 50.04
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream b Intel Core Ultra 7 155H c a 5 10 15 20 25 18.61 19.17 19.49 19.97
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream b Intel Core Ultra 7 155H a c 120 240 360 480 600 574.67 571.95 566.57 557.74
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream b Intel Core Ultra 7 155H a c 3 6 9 12 15 12.15 12.21 12.32 12.52
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream b a c Intel Core Ultra 7 155H 70 140 210 280 350 325.44 316.58 311.50 308.08
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream b a c Intel Core Ultra 7 155H 0.7266 1.4532 2.1798 2.9064 3.633 3.0565 3.1430 3.1954 3.2294
Neural Magic DeepSparse Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream Intel Core Ultra 7 155H b a c 0.6785 1.357 2.0355 2.714 3.3925 3.0156 2.9188 2.8856 2.8684
Neural Magic DeepSparse Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream Intel Core Ultra 7 155H b a c 500 1000 1500 2000 2500 2249.49 2313.37 2353.99 2364.78
Neural Magic DeepSparse Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream a Intel Core Ultra 7 155H c b 2 4 6 8 10 7.9943 7.9919 7.9907 7.9860
Neural Magic DeepSparse Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream a Intel Core Ultra 7 155H c b 30 60 90 120 150 125.05 125.09 125.11 125.18
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b c Intel Core Ultra 7 155H 20 40 60 80 100 78.00 75.37 74.66 74.34
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b c Intel Core Ultra 7 155H 20 40 60 80 100 89.49 92.65 93.63 94.10
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b Intel Core Ultra 7 155H c 12 24 36 48 60 53.89 52.58 52.03 51.53
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b Intel Core Ultra 7 155H c 5 10 15 20 25 18.54 19.01 19.21 19.40
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream c Intel Core Ultra 7 155H b a 8 16 24 32 40 36.69 36.64 36.58 36.26
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream c Intel Core Ultra 7 155H b a 40 80 120 160 200 190.09 190.23 190.56 192.28
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream Intel Core Ultra 7 155H b c a 7 14 21 28 35 30.34 30.33 29.90 28.79
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream Intel Core Ultra 7 155H b c a 8 16 24 32 40 32.94 32.95 33.42 34.71
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream b c a Intel Core Ultra 7 155H 12 24 36 48 60 55.18 54.25 54.08 53.46
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream b c a Intel Core Ultra 7 155H 30 60 90 120 150 126.60 128.68 128.98 130.47
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream b a c Intel Core Ultra 7 155H 9 18 27 36 45 39.98 39.67 39.18 38.81
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream b a c Intel Core Ultra 7 155H 6 12 18 24 30 25.00 25.20 25.51 25.76
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b c Intel Core Ultra 7 155H 2 4 6 8 10 7.0047 6.7585 6.7557 6.6736
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b c Intel Core Ultra 7 155H 200 400 600 800 1000 983.94 1016.00 1020.23 1030.84
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a b Intel Core Ultra 7 155H c 2 4 6 8 10 6.4397 6.3497 6.3123 6.2871
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a b Intel Core Ultra 7 155H c 40 80 120 160 200 155.26 157.47 158.40 159.04
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream b a c Intel Core Ultra 7 155H 20 40 60 80 100 95.96 95.93 94.97 92.60
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream b a c Intel Core Ultra 7 155H 20 40 60 80 100 72.75 72.80 73.55 75.39
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream a b c Intel Core Ultra 7 155H 10 20 30 40 50 44.13 42.68 40.92 40.40
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream a b c Intel Core Ultra 7 155H 6 12 18 24 30 22.64 23.41 24.42 24.73
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream b a c Intel Core Ultra 7 155H 1.2585 2.517 3.7755 5.034 6.2925 5.5932 5.5873 5.5129 5.4819
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b c Intel Core Ultra 7 155H 300 600 900 1200 1500 1234.80 1235.58 1242.96 1243.61
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a b c Intel Core Ultra 7 155H 1.2803 2.5606 3.8409 5.1212 6.4015 5.6903 5.6314 5.5888 5.5840
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a b c Intel Core Ultra 7 155H 40 80 120 160 200 175.72 177.56 178.91 179.07
Parallel BZIP2 Compression FreeBSD-13.0-RELEASE-amd64-memstick.img Compression OpenBenchmarking.org Seconds, Fewer Is Better Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression b Intel Core Ultra 7 155H c a 2 4 6 8 10 7.290079 7.399834 7.602462 7.669184 1. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
Primesieve Length: 1e12 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e12 b a Intel Core Ultra 7 155H c 6 12 18 24 30 24.76 24.85 25.04 25.10 1. (CXX) g++ options: -O3
Primesieve Length: 1e13 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e13 b c Intel Core Ultra 7 155H a 80 160 240 320 400 349.94 351.48 353.14 361.14 1. (CXX) g++ options: -O3
Selenium Benchmark: Kraken - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: Kraken - Browser: Firefox a c b Intel Core Ultra 7 155H 140 280 420 560 700 599.8 608.2 614.6 629.0 1. firefox 121.0.1
Selenium Benchmark: SilverBench - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: SilverBench - Browser: Firefox b c a Intel Core Ultra 7 155H 300 600 900 1200 1500 1459 1372 1370 1347 1. firefox 121.0.1
Selenium Benchmark: Kraken - Browser: Google Chrome OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: Kraken - Browser: Google Chrome b c Intel Core Ultra 7 155H a 110 220 330 440 550 462.6 463.4 487.0 489.1 1. chrome 122.0.6261.128
Selenium Benchmark: PSPDFKit WASM - Browser: Firefox OpenBenchmarking.org Score, Fewer Is Better Selenium Benchmark: PSPDFKit WASM - Browser: Firefox Intel Core Ultra 7 155H c a b 200 400 600 800 1000 1054 1072 1082 1084 1. firefox 121.0.1
Selenium Benchmark: Speedometer 3.0 - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Speedometer 3.0 - Browser: Firefox b Intel Core Ultra 7 155H c a 4 8 12 16 20 15.4 15.2 14.6 14.6 1. firefox 121.0.1
Selenium Benchmark: SilverBench - Browser: Google Chrome OpenBenchmarking.org Score, More Is Better Selenium Benchmark: SilverBench - Browser: Google Chrome b a c Intel Core Ultra 7 155H 15K 30K 45K 60K 75K 68068 49974 48962 44225 1. chrome 122.0.6261.128
Selenium Benchmark: PSPDFKit WASM - Browser: Google Chrome OpenBenchmarking.org Score, Fewer Is Better Selenium Benchmark: PSPDFKit WASM - Browser: Google Chrome b Intel Core Ultra 7 155H a c 200 400 600 800 1000 1023 1028 1041 1098 1. chrome 122.0.6261.128
Selenium Benchmark: WASM imageConvolute - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM imageConvolute - Browser: Firefox Intel Core Ultra 7 155H b c a 6 12 18 24 30 22.3 22.4 22.6 23.2 1. firefox 121.0.1
Selenium Benchmark: Speedometer 3.0 - Browser: Google Chrome OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Speedometer 3.0 - Browser: Google Chrome b c a Intel Core Ultra 7 155H 5 10 15 20 25 19.2 18.6 18.2 18.0 1. chrome 122.0.6261.128
Selenium Benchmark: WASM collisionDetection - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM collisionDetection - Browser: Firefox b a c Intel Core Ultra 7 155H 60 120 180 240 300 276.4 280.0 280.7 287.5 1. firefox 121.0.1
Selenium Benchmark: WASM imageConvolute - Browser: Google Chrome OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM imageConvolute - Browser: Google Chrome b a c Intel Core Ultra 7 155H 5 10 15 20 25 20.29 20.90 21.20 21.91 1. chrome 122.0.6261.128
Selenium Benchmark: WASM collisionDetection - Browser: Google Chrome OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM collisionDetection - Browser: Google Chrome b Intel Core Ultra 7 155H c a 50 100 150 200 250 219.60 220.12 220.99 221.42 1. chrome 122.0.6261.128
Stockfish Chess Benchmark OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 16.1 Chess Benchmark c b a Intel Core Ultra 7 155H 3M 6M 9M 12M 15M 12001097 10579637 10417995 10327383 1. (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
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K b c a Intel Core Ultra 7 155H 0.7594 1.5188 2.2782 3.0376 3.797 3.375 3.372 3.351 3.344 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K c b a Intel Core Ultra 7 155H 6 12 18 24 30 25.94 25.90 25.80 25.76 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K a c b Intel Core Ultra 7 155H 20 40 60 80 100 85.01 79.67 64.85 62.42 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K c a Intel Core Ultra 7 155H b 20 40 60 80 100 84.85 84.39 78.96 64.17 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 1080p b c a Intel Core Ultra 7 155H 3 6 9 12 15 12.28 12.19 12.04 11.92 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 1080p a b Intel Core Ultra 7 155H c 20 40 60 80 100 86.33 85.86 85.73 85.49 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Intel Core Ultra 7 155H c a b 80 160 240 320 400 359.21 356.16 355.61 355.16 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Intel Core Ultra 7 155H a b c 90 180 270 360 450 436.60 434.21 433.46 425.86 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: defconfig b c Intel Core Ultra 7 155H a 30 60 90 120 150 139.05 141.99 142.40 143.50
Timed Linux Kernel Compilation Build: allmodconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: allmodconfig b c Intel Core Ultra 7 155H a 500 1000 1500 2000 2500 2018.83 2069.49 2111.00 2198.95
Phoronix Test Suite v10.8.4