jan tr AMD Ryzen Threadripper 7980X 64-Cores testing with a ASUS Pro WS TRX50-SAGE WIFI (0217 BIOS) and AMD Radeon RX 7900 XT 20GB on Ubuntu 23.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2401036-NE-JANTR931223 .
jan tr Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution a b c d AMD Ryzen Threadripper 7980X 64-Cores @ 8.21GHz (64 Cores / 128 Threads) ASUS Pro WS TRX50-SAGE WIFI (0217 BIOS) AMD Device 14a4 128GB 2000GB Corsair MP700 PRO + 1000GB Western Digital WDS100T1X0E-00AFY0 AMD Radeon RX 7900 XT 20GB (2025/1249MHz) Realtek ALC1220 DELL U2723QE Aquantia Device 04c0 + Intel I226-LM + MEDIATEK MT7922 802.11ax PCI Ubuntu 23.10 6.7.0-060700rc2daily20231126-generic (x86_64) GNOME Shell 45.0 X Server 1.21.1.7 + Wayland 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.56) GCC 13.2.0 ext4 3840x2160 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: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105 Java Details - a: OpenJDK Runtime Environment (build 17.0.9-ea+6-Ubuntu-1) 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: Mitigation of Safe RET + 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 STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
jan tr lczero: BLAS lczero: Eigen xmrig: KawPow - 1M xmrig: Monero - 1M xmrig: Wownero - 1M xmrig: GhostRider - 1M xmrig: CryptoNight-Heavy - 1M xmrig: CryptoNight-Femto UPX2 - 1M rav1e: 1 rav1e: 5 rav1e: 6 rav1e: 10 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 - 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 - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream a b c d 515 453 43081.2 42620.3 51015.2 11640.2 43183.5 42573.1 1.382 5.76 7.713 18.429 9.915 96.136 226.376 233.401 26.897 189.995 679.129 798.11 21.8877 365.461 915.9879 8.7254 274.1817 29.1598 2264.8093 3.5237 127.2897 62.8303 27.3551 292.0795 274.8777 29.0862 131.1166 60.9983 187.9087 42.5413 40.1726 198.9158 401.6767 19.9046 22.1015 361.9023 505 489 43084.9 44163.8 47129.8 12124.6 44058.7 45093.8 1.382 5.747 7.75 18.219 9.876 95.978 226.714 235.404 26.753 187.998 686.948 810.674 21.9253 364.8116 912.7841 8.756 274.7766 29.1019 2262.1303 3.5287 128.0399 62.4296 27.2964 292.2247 274.6803 29.1069 131.3943 60.8629 188.1679 42.4824 40.1875 198.9152 402.9691 19.8409 22.2547 359.3444 530 450 42260.1 43269.4 49907.7 11899.9 43573 44012.1 1.376 5.748 7.69 18.35 9.95 97.286 217.36 230.908 26.904 188.495 684.733 766.923 21.9125 365.0508 912.5416 8.7584 274.6214 29.1135 2304.9777 3.4631 128.1369 62.3992 27.3271 292.2096 274.7142 29.1084 131.0807 60.9718 187.9182 42.5559 40.239 198.5435 402.0241 19.8876 22.2164 359.9871 513 453 43368.9 43097.9 49729 11952.1 43740.7 43979.2 1.384 5.768 7.729 18.396 9.998 95.979 229.79 224.792 27.048 191.464 660.562 772.842 21.8896 364.3545 912.7754 8.7558 274.7306 29.1065 2278.9172 3.5027 127.0074 62.974 27.3123 292.0917 274.4904 29.1325 130.3016 61.3755 187.7392 42.5972 40.1784 198.9994 402.1847 19.8795 21.998 363.6337 OpenBenchmarking.org
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.30 Backend: BLAS a b c d 110 220 330 440 550 515 505 530 513 1. (CXX) g++ options: -flto -pthread
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.30 Backend: Eigen a b c d 110 220 330 440 550 453 489 450 453 1. (CXX) g++ options: -flto -pthread
Xmrig Variant: KawPow - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: KawPow - Hash Count: 1M a b c d 9K 18K 27K 36K 45K 43081.2 43084.9 42260.1 43368.9 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Xmrig Variant: Monero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: Monero - Hash Count: 1M a b c d 9K 18K 27K 36K 45K 42620.3 44163.8 43269.4 43097.9 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Xmrig Variant: Wownero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: Wownero - Hash Count: 1M a b c d 11K 22K 33K 44K 55K 51015.2 47129.8 49907.7 49729.0 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Xmrig Variant: GhostRider - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: GhostRider - Hash Count: 1M a b c d 3K 6K 9K 12K 15K 11640.2 12124.6 11899.9 11952.1 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Xmrig Variant: CryptoNight-Heavy - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: CryptoNight-Heavy - Hash Count: 1M a b c d 9K 18K 27K 36K 45K 43183.5 44058.7 43573.0 43740.7 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Xmrig Variant: CryptoNight-Femto UPX2 - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: CryptoNight-Femto UPX2 - Hash Count: 1M a b c d 10K 20K 30K 40K 50K 42573.1 45093.8 44012.1 43979.2 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
rav1e Speed: 1 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.7 Speed: 1 a b c d 0.3114 0.6228 0.9342 1.2456 1.557 1.382 1.382 1.376 1.384
rav1e Speed: 5 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.7 Speed: 5 a b c d 1.2978 2.5956 3.8934 5.1912 6.489 5.760 5.747 5.748 5.768
rav1e Speed: 6 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.7 Speed: 6 a b c d 2 4 6 8 10 7.713 7.750 7.690 7.729
rav1e Speed: 10 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.7 Speed: 10 a b c d 5 10 15 20 25 18.43 18.22 18.35 18.40
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 4 - Input: Bosphorus 4K a b c d 3 6 9 12 15 9.915 9.876 9.950 9.998 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 1.8 Encoder Mode: Preset 8 - Input: Bosphorus 4K a b c d 20 40 60 80 100 96.14 95.98 97.29 95.98 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 1.8 Encoder Mode: Preset 12 - Input: Bosphorus 4K a b c d 50 100 150 200 250 226.38 226.71 217.36 229.79 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 1.8 Encoder Mode: Preset 13 - Input: Bosphorus 4K a b c d 50 100 150 200 250 233.40 235.40 230.91 224.79 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 1.8 Encoder Mode: Preset 4 - Input: Bosphorus 1080p a b c d 6 12 18 24 30 26.90 26.75 26.90 27.05 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 1.8 Encoder Mode: Preset 8 - Input: Bosphorus 1080p a b c d 40 80 120 160 200 190.00 188.00 188.50 191.46 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 1.8 Encoder Mode: Preset 12 - Input: Bosphorus 1080p a b c d 150 300 450 600 750 679.13 686.95 684.73 660.56 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 1.8 Encoder Mode: Preset 13 - Input: Bosphorus 1080p a b c d 200 400 600 800 1000 798.11 810.67 766.92 772.84 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 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream a b c d 5 10 15 20 25 21.89 21.93 21.91 21.89
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 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream a b c d 80 160 240 320 400 365.46 364.81 365.05 364.35
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 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c d 200 400 600 800 1000 915.99 912.78 912.54 912.78
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 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c d 2 4 6 8 10 8.7254 8.7560 8.7584 8.7558
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream a b c d 60 120 180 240 300 274.18 274.78 274.62 274.73
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream a b c d 7 14 21 28 35 29.16 29.10 29.11 29.11
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c d 500 1000 1500 2000 2500 2264.81 2262.13 2304.98 2278.92
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c d 0.794 1.588 2.382 3.176 3.97 3.5237 3.5287 3.4631 3.5027
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream a b c d 30 60 90 120 150 127.29 128.04 128.14 127.01
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream a b c d 14 28 42 56 70 62.83 62.43 62.40 62.97
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream a b c d 6 12 18 24 30 27.36 27.30 27.33 27.31
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream a b c d 60 120 180 240 300 292.08 292.22 292.21 292.09
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b c d 60 120 180 240 300 274.88 274.68 274.71 274.49
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b c d 7 14 21 28 35 29.09 29.11 29.11 29.13
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c d 30 60 90 120 150 131.12 131.39 131.08 130.30
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c d 14 28 42 56 70 61.00 60.86 60.97 61.38
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b c d 40 80 120 160 200 187.91 188.17 187.92 187.74
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b c d 10 20 30 40 50 42.54 42.48 42.56 42.60
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b c d 9 18 27 36 45 40.17 40.19 40.24 40.18
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b c d 40 80 120 160 200 198.92 198.92 198.54 199.00
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 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c d 90 180 270 360 450 401.68 402.97 402.02 402.18
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 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c d 5 10 15 20 25 19.90 19.84 19.89 19.88
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 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b c d 5 10 15 20 25 22.10 22.25 22.22 22.00
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 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b c d 80 160 240 320 400 361.90 359.34 359.99 363.63
Phoronix Test Suite v10.8.4