xeon emr 2 x INTEL XEON PLATINUM 8592+ testing with a Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2403172-NE-XEONEMR4990&sor&gru .
xeon emr Processor Motherboard Chipset Memory Disk Graphics Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution a b c d 2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads) Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS) Intel Device 1bce 1008GB 3201GB Micron_7450_MTFDKCC3T2TFS ASPEED 2 x Intel X710 for 10GBASE-T Ubuntu 23.10 6.6.0-rc5-phx-patched (x86_64) GNOME Shell 45.0 X Server 1.21.1.7 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 performance (EPP: performance) - CPU Microcode: 0x21000161 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: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
xeon emr 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 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 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: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Synchronous Single-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream deepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Stream deepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-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 - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-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 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-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 - Synchronous Single-Stream srsran: PDSCH Processor Benchmark, Throughput Total srsran: PDSCH Processor Benchmark, Throughput Thread stockfish: Chess Benchmark draco: Lion draco: Church Facade 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 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: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Synchronous Single-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream deepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Stream deepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-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 - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-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 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-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 - Synchronous Single-Stream build-linux-kernel: defconfig build-linux-kernel: allmodconfig compress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compression primesieve: 1e12 primesieve: 1e13 a b c d 7.75 72.86 172.718 168.799 22.033 152.48 457.741 643.525 137.9486 34.0569 4590.2273 304.7581 1789.6958 342.2814 11719.0071 1060.9522 3.1028 14.5001 1800.7146 343.4587 864.3474 197.6133 1238.0561 199.0668 181.7853 35.8292 1904.0783 100.2084 138.305 34.1833 43297.4 755.6 212133268 4060 4837 461.3828 29.3545 13.9187 3.2778 35.7151 2.9188 5.4463 0.9394 16509.1382 68.8874 35.4998 2.9085 73.9698 5.058 51.6596 5.0199 351.8687 27.8836 33.5718 9.9739 460.7323 29.2486 26.074 181.564 1.249184 2.213 25.033 7.531 73.713 168.298 167.052 22.161 152.788 439.119 640.892 137.2758 34.1233 4598.881 304.7953 1792.6939 342.9008 11722.5863 1079.5719 2.9676 14.2937 1788.7978 342.2084 863.6692 195.8717 1241.5488 198.3448 182.1096 35.851 1902.9145 99.7096 137.7909 34.2297 50572.1 728.7 207635904 4041 4793 462.5178 29.2948 13.8924 3.2774 35.6661 2.9135 5.4445 0.9232 17153.2257 69.8791 35.7303 2.9192 73.9961 5.103 51.5131 5.0378 350.3778 27.8666 33.5942 10.0233 461.2167 29.2084 26.364 183.153 1.235156 2.163 24.975 7.541 72.827 169.91 168.2 22.392 153.098 441.419 620.865 136.559 33.9896 4605.9916 304.8963 1781.8907 341.4441 11702.1757 1065.9665 2.9506 14.3408 1803.2322 342.4421 863.8538 195.8325 1233.705 200.2818 182.809 35.1943 1902.1758 100.9536 137.9705 34.1503 52220.4 755.3 221316167 4092 4765 465.457 29.4115 13.8713 3.2761 35.8738 2.9257 5.4544 0.9356 17224.3584 69.6416 35.4543 2.9173 74.0382 5.1037 51.8422 4.9896 349.8032 28.3852 33.5913 9.8997 461.9932 29.2768 26.042 182.434 1.235287 2.159 25.077 7.586 71.511 169.387 168.292 22.24 154.5 442.336 627.59 137.823 33.8913 4589.1483 303.8422 1789.8075 343.5349 11674.2462 1055.1822 3.2137 14.2809 1794.8462 344.0469 863.9257 197.0081 1236.9478 198.3789 182.5524 35.7654 1902.9281 98.7467 137.9657 34.1968 49150.3 756 214224198 4059 4820 460.9087 29.495 13.9223 3.2877 35.7107 2.908 5.4675 0.9449 16021.351 69.945 35.6137 2.9035 74.0261 5.0734 51.7072 5.0371 350.443 27.9309 33.5967 10.1216 462.0284 29.2364 26.131 181.284 1.252094 2.163 24.925 OpenBenchmarking.org
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 a d c b 2 4 6 8 10 7.750 7.586 7.541 7.531 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 b a c d 16 32 48 64 80 73.71 72.86 72.83 71.51 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 d b 40 80 120 160 200 172.72 169.91 169.39 168.30 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 a d c b 40 80 120 160 200 168.80 168.29 168.20 167.05 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 c d b a 5 10 15 20 25 22.39 22.24 22.16 22.03 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 d c b a 30 60 90 120 150 154.50 153.10 152.79 152.48 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 a d c b 100 200 300 400 500 457.74 442.34 441.42 439.12 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 a b d c 140 280 420 560 700 643.53 640.89 627.59 620.87 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 a d b c 30 60 90 120 150 137.95 137.82 137.28 136.56
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 b a c d 8 16 24 32 40 34.12 34.06 33.99 33.89
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 c b a d 1000 2000 3000 4000 5000 4605.99 4598.88 4590.23 4589.15
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 c b a d 70 140 210 280 350 304.90 304.80 304.76 303.84
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 d a c 400 800 1200 1600 2000 1792.69 1789.81 1789.70 1781.89
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 d b a c 70 140 210 280 350 343.53 342.90 342.28 341.44
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 a c d 3K 6K 9K 12K 15K 11722.59 11719.01 11702.18 11674.25
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 c a d 200 400 600 800 1000 1079.57 1065.97 1060.95 1055.18
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 d a b c 0.7231 1.4462 2.1693 2.8924 3.6155 3.2137 3.1028 2.9676 2.9506
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 c b d 4 8 12 16 20 14.50 14.34 14.29 14.28
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 c a d b 400 800 1200 1600 2000 1803.23 1800.71 1794.85 1788.80
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 d a c b 70 140 210 280 350 344.05 343.46 342.44 342.21
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 a d c b 200 400 600 800 1000 864.35 863.93 863.85 863.67
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 a d b c 40 80 120 160 200 197.61 197.01 195.87 195.83
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 a d c 300 600 900 1200 1500 1241.55 1238.06 1236.95 1233.71
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 c a d b 40 80 120 160 200 200.28 199.07 198.38 198.34
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 c d b a 40 80 120 160 200 182.81 182.55 182.11 181.79
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 b a d c 8 16 24 32 40 35.85 35.83 35.77 35.19
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 a d b c 400 800 1200 1600 2000 1904.08 1902.93 1902.91 1902.18
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 c a b d 20 40 60 80 100 100.95 100.21 99.71 98.75
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 a c d b 30 60 90 120 150 138.31 137.97 137.97 137.79
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 b d a c 8 16 24 32 40 34.23 34.20 34.18 34.15
srsRAN Project Test: PDSCH Processor Benchmark, Throughput Total OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240219 Test: PDSCH Processor Benchmark, Throughput Total c b d a 11K 22K 33K 44K 55K 52220.4 50572.1 49150.3 46252.5 1. (CXX) g++ options: -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -O3 -fno-trapping-math -fno-math-errno -ldl
srsRAN Project Test: PDSCH Processor Benchmark, Throughput Thread OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240219 Test: PDSCH Processor Benchmark, Throughput Thread d a c b 160 320 480 640 800 756.0 755.6 755.3 728.7 1. (CXX) g++ options: -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -O3 -fno-trapping-math -fno-math-errno -ldl
Stockfish Chess Benchmark OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 16.1 Chess Benchmark c d a b 50M 100M 150M 200M 250M 221316167 214224198 212133268 207635904 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 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver
Google Draco Model: Lion OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.6 Model: Lion b d a c 900 1800 2700 3600 4500 4041 4059 4060 4092 1. (CXX) g++ options: -O3
Google Draco Model: Church Facade OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.6 Model: Church Facade c b d a 1000 2000 3000 4000 5000 4765 4793 4820 4837 1. (CXX) g++ options: -O3
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 d a b c 100 200 300 400 500 460.91 461.38 462.52 465.46
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 b a c d 7 14 21 28 35 29.29 29.35 29.41 29.50
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 c b a d 4 8 12 16 20 13.87 13.89 13.92 13.92
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 c b a d 0.7397 1.4794 2.2191 2.9588 3.6985 3.2761 3.2774 3.2778 3.2877
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 d a c 8 16 24 32 40 35.67 35.71 35.72 35.87
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 d b a c 0.6583 1.3166 1.9749 2.6332 3.2915 2.9080 2.9135 2.9188 2.9257
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 a c d 1.2302 2.4604 3.6906 4.9208 6.151 5.4445 5.4463 5.4544 5.4675
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 c a d 0.2126 0.4252 0.6378 0.8504 1.063 0.9232 0.9356 0.9394 0.9449
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 d a b c 4K 8K 12K 16K 20K 16021.35 16509.14 17153.23 17224.36
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 c b d 16 32 48 64 80 68.89 69.64 69.88 69.95
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 c a d b 8 16 24 32 40 35.45 35.50 35.61 35.73
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 d a c b 0.6568 1.3136 1.9704 2.6272 3.284 2.9035 2.9085 2.9173 2.9192
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 a b d c 16 32 48 64 80 73.97 74.00 74.03 74.04
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 a d b c 1.1483 2.2966 3.4449 4.5932 5.7415 5.0580 5.0734 5.1030 5.1037
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 a d c 12 24 36 48 60 51.51 51.66 51.71 51.84
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 c a d b 1.1335 2.267 3.4005 4.534 5.6675 4.9896 5.0199 5.0371 5.0378
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 c b d a 80 160 240 320 400 349.80 350.38 350.44 351.87
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 b a d c 7 14 21 28 35 27.87 27.88 27.93 28.39
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 a c b d 8 16 24 32 40 33.57 33.59 33.59 33.60
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 c a b d 3 6 9 12 15 9.8997 9.9739 10.0233 10.1216
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 d 100 200 300 400 500 460.73 461.22 461.99 462.03
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 b d a c 7 14 21 28 35 29.21 29.24 29.25 29.28
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: defconfig c a d b 6 12 18 24 30 26.04 26.07 26.13 26.36
Timed Linux Kernel Compilation Build: allmodconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: allmodconfig d a c b 40 80 120 160 200 181.28 181.56 182.43 183.15
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 c a d 0.2817 0.5634 0.8451 1.1268 1.4085 1.235156 1.235287 1.249184 1.252094 1. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
Primesieve Length: 1e12 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e12 c b d a 0.4979 0.9958 1.4937 1.9916 2.4895 2.159 2.163 2.163 2.213 1. (CXX) g++ options: -O3
Primesieve Length: 1e13 OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e13 d b a c 6 12 18 24 30 24.93 24.98 25.03 25.08 1. (CXX) g++ options: -O3
Phoronix Test Suite v10.8.5