AMD Custom APU 0405 testing with a Valve Jupiter v1 (F7A0110 BIOS) and AMD Custom GPU 0405 1GB on SteamOS rolling via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2309052-NE-DECKING9724 decking - Phoronix Test Suite decking AMD Custom APU 0405 testing with a Valve Jupiter v1 (F7A0110 BIOS) and AMD Custom GPU 0405 1GB on SteamOS rolling via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2309052-NE-DECKING9724&sro&gru .
decking Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution a b c AMD Custom APU 0405 @ 2.80GHz (4 Cores / 8 Threads) Valve Jupiter v1 (F7A0110 BIOS) AMD VanGogh Root Complex 16GB 512GB Phison ESMP512GKB4C3-E13TS + 1000GB RTL9210B-CG AMD Custom GPU 0405 1GB (1600/400MHz) AMD Rembrandt Radeon HD Audio ANX7530 U Realtek RTL8822CE 802.11ac PCIe SteamOS rolling 5.13.0-valve36-1-neptune (x86_64) KDE Plasma 5.26.1 X Server 1.21.1.3 4.6 Mesa 22.2.0 (git-17e5312102) (LLVM 14.0.6 DRM 3.45) 1.3.238 GCC 12.2.0 ext4 1280x800 OpenBenchmarking.org Kernel Details - amdgpu.gttsize=8128 spi_amd.speed_dev=1 - Transparent Huge Pages: madvise Processor Details - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8900201 Graphics Details - GLAMOR - BAR1 / Visible vRAM Size: 1024 MB - vBIOS Version: 113-AMDAerithJ-004 Java Details - OpenJDK Runtime Environment (build 11.0.17+1) Python Details - Python 3.10.8 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
decking vkpeak: fp32-scalar vkpeak: fp32-vec4 vkpeak: fp16-scalar vkpeak: fp16-vec4 vkpeak: fp64-scalar vkpeak: fp64-vec4 vkpeak: int32-scalar vkpeak: int32-vec4 vkpeak: int16-scalar vkpeak: int16-vec4 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: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - 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: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering - 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 Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - 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 cassandra: Writes apache-iotdb: 100 - 1 - 500 apache-iotdb: 100 - 1 - 500 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: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - 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: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering - 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 Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - 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 a b c 1638.24 1626.08 1638.6 2618.33 102.02 279.05 326.93 1638.31 2620 2.1122 2.1732 53.703 50.1845 21.3085 18.1783 6.423 6.0942 26.9902 25.1393 188.9603 170.8681 12.9044 12.3337 2.7457 2.6313 26.5799 24.5736 13.1293 12.5215 18.1143 15.6395 2.2637 2.3648 27.7184 25.7729 9.9683 8.7687 2.1364 2.2291 31081 711045.2 56.1 940.7032 460.1402 37.1925 19.9099 93.8248 54.9957 311.1324 164.0752 74.0619 39.7569 10.5418 5.8323 154.7848 81.0533 724.8871 380.0204 75.1762 40.6737 152.0727 79.8452 110.3133 63.922 878.3129 422.8352 72.108 38.7851 200.4555 114.0271 932.3056 448.6054 1638.72 1626.6 1639.31 2618.49 102.01 102.03 279.13 326.95 1638.91 2619.45 2.1213 2.1968 53.3204 50.2327 21.0947 18.1777 6.4754 6.1143 26.6504 24.9051 188.3105 170.4127 12.961 12.3783 28.872 26.9723 14.2177 13.509 19.2761 16.377 2.6289 2.556 29.8442 28.554 11.0097 9.4427 2.2798 2.3896 29616 940.4732 455.1871 37.4598 19.8905 94.7494 54.9971 308.5592 163.5343 75.0032 40.1323 10.5794 5.8481 154.1224 80.7619 69.2135 37.0593 140.6311 74.0106 103.5922 61.0449 760.724 391.2056 66.9637 35.0067 181.6241 105.8874 877.2339 418.4656 1639.27 1628.05 1639.19 2619.64 102.03 102.06 279.16 327.27 1639.04 2621.89 2.3264 2.3847 58.1446 55.6174 22.179 19.4976 7.3794 6.6652 29.4727 27.0662 203.5527 184.0044 13.9757 13.1751 29.5078 26.9725 14.2805 13.5048 19.6773 16.4839 2.5672 2.5558 29.8109 28.7074 10.9375 9.4377 2.342 2.3825 853.076 419.3245 34.3521 17.9622 90.1375 51.2707 270.324 150.0141 67.8272 36.9295 9.7887 5.4147 143.0633 75.8765 67.7439 37.0592 140.0128 74.033 101.6061 60.6503 778.4706 391.2325 67.0376 34.8195 182.6961 105.9419 850.6684 419.7098 OpenBenchmarking.org
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp32-scalar a b c 400 800 1200 1600 2000 1638.24 1638.72 1639.27
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp32-vec4 a b c 300 600 900 1200 1500 1626.08 1626.60 1628.05
vkpeak fp16-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp16-scalar a b c 400 800 1200 1600 2000 1638.60 1639.31 1639.19
vkpeak fp16-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp16-vec4 a b c 600 1200 1800 2400 3000 2618.33 2618.49 2619.64
vkpeak fp64-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp64-scalar a b c 20 40 60 80 100 102.02 102.01 102.03
vkpeak fp64-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp64-vec4 b c 20 40 60 80 100 102.03 102.06
vkpeak int32-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int32-scalar a b c 60 120 180 240 300 279.05 279.13 279.16
vkpeak int32-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int32-vec4 a b c 70 140 210 280 350 326.93 326.95 327.27
vkpeak int16-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int16-scalar a b c 400 800 1200 1600 2000 1638.31 1638.91 1639.04
vkpeak int16-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int16-vec4 a b c 600 1200 1800 2400 3000 2620.00 2619.45 2621.89
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 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream a b c 0.5234 1.0468 1.5702 2.0936 2.617 2.1122 2.1213 2.3264
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 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream a b c 0.5366 1.0732 1.6098 2.1464 2.683 2.1732 2.1968 2.3847
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 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 13 26 39 52 65 53.70 53.32 58.14
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 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 12 24 36 48 60 50.18 50.23 55.62
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream a b c 5 10 15 20 25 21.31 21.09 22.18
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream a b c 5 10 15 20 25 18.18 18.18 19.50
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream a b c 2 4 6 8 10 6.4230 6.4754 7.3794
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream a b c 2 4 6 8 10 6.0942 6.1143 6.6652
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream a b c 7 14 21 28 35 26.99 26.65 29.47
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream a b c 6 12 18 24 30 25.14 24.91 27.07
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 40 80 120 160 200 188.96 188.31 203.55
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 40 80 120 160 200 170.87 170.41 184.00
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream a b c 4 8 12 16 20 12.90 12.96 13.98
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream a b c 3 6 9 12 15 12.33 12.38 13.18
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream a 0.6178 1.2356 1.8534 2.4712 3.089 2.7457
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream a 0.592 1.184 1.776 2.368 2.96 2.6313
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b c 7 14 21 28 35 26.58 28.87 29.51
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b c 6 12 18 24 30 24.57 26.97 26.97
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 4 8 12 16 20 13.13 14.22 14.28
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 3 6 9 12 15 12.52 13.51 13.50
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b c 5 10 15 20 25 18.11 19.28 19.68
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream a b c 4 8 12 16 20 15.64 16.38 16.48
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b c 0.5915 1.183 1.7745 2.366 2.9575 2.2637 2.6289 2.5672
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a b c 0.5751 1.1502 1.7253 2.3004 2.8755 2.3648 2.5560 2.5558
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 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 7 14 21 28 35 27.72 29.84 29.81
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 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 7 14 21 28 35 25.77 28.55 28.71
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream a b c 3 6 9 12 15 9.9683 11.0097 10.9375
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream a b c 3 6 9 12 15 8.7687 9.4427 9.4377
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 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b c 0.527 1.054 1.581 2.108 2.635 2.1364 2.2798 2.3420
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 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a b c 0.5377 1.0754 1.6131 2.1508 2.6885 2.2291 2.3896 2.3825
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.1.3 Test: Writes a b 7K 14K 21K 28K 35K 31081 29616
Apache IoTDB Device Count: 100 - Batch Size Per Write: 1 - Sensor Count: 500 OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.1.2 Device Count: 100 - Batch Size Per Write: 1 - Sensor Count: 500 a 150K 300K 450K 600K 750K 711045.2
Apache IoTDB Device Count: 100 - Batch Size Per Write: 1 - Sensor Count: 500 OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.1.2 Device Count: 100 - Batch Size Per Write: 1 - Sensor Count: 500 a 13 26 39 52 65 56.1 MAX: 1675.14
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 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream a b c 200 400 600 800 1000 940.70 940.47 853.08
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 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream a b c 100 200 300 400 500 460.14 455.19 419.32
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 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 9 18 27 36 45 37.19 37.46 34.35
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 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 5 10 15 20 25 19.91 19.89 17.96
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream a b c 20 40 60 80 100 93.82 94.75 90.14
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream a b c 12 24 36 48 60 55.00 55.00 51.27
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream a b c 70 140 210 280 350 311.13 308.56 270.32
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream a b c 40 80 120 160 200 164.08 163.53 150.01
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream a b c 20 40 60 80 100 74.06 75.00 67.83
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream a b c 9 18 27 36 45 39.76 40.13 36.93
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 3 6 9 12 15 10.5418 10.5794 9.7887
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 1.3158 2.6316 3.9474 5.2632 6.579 5.8323 5.8481 5.4147
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream a b c 30 60 90 120 150 154.78 154.12 143.06
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream a b c 20 40 60 80 100 81.05 80.76 75.88
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream a 160 320 480 640 800 724.89
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream a 80 160 240 320 400 380.02
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b c 20 40 60 80 100 75.18 69.21 67.74
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b c 9 18 27 36 45 40.67 37.06 37.06
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 30 60 90 120 150 152.07 140.63 140.01
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 20 40 60 80 100 79.85 74.01 74.03
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b c 20 40 60 80 100 110.31 103.59 101.61
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream a b c 14 28 42 56 70 63.92 61.04 60.65
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b c 200 400 600 800 1000 878.31 760.72 778.47
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a b c 90 180 270 360 450 422.84 391.21 391.23
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 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream a b c 16 32 48 64 80 72.11 66.96 67.04
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 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream a b c 9 18 27 36 45 38.79 35.01 34.82
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream a b c 40 80 120 160 200 200.46 181.62 182.70
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream a b c 30 60 90 120 150 114.03 105.89 105.94
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 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b c 200 400 600 800 1000 932.31 877.23 850.67
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 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a b c 100 200 300 400 500 448.61 418.47 419.71
Phoronix Test Suite v10.8.4