sdfa AMD Ryzen Threadripper 3990X 64-Core testing with a Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS) and AMD Radeon RX 5700 8GB on Ubuntu 23.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2312122-PTS-SDFA911983&grr&sor .
sdfa 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 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads) Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS) AMD Starship/Matisse 128GB Samsung SSD 970 EVO Plus 500GB AMD Radeon RX 5700 8GB (1750/875MHz) AMD Navi 10 HDMI Audio DELL P2415Q Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 23.10 6.5.0-13-generic (x86_64) GNOME Shell 45.0 X Server + Wayland 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54) GCC 13.2.0 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Processor Details - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x830107a Java Details - OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10) 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: Mitigation of untrained return thunk; SMT enabled with STIBP protection + 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 Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
sdfa spark-tpch: 50 - Q22 spark-tpch: 50 - Q21 spark-tpch: 50 - Q20 spark-tpch: 50 - Q19 spark-tpch: 50 - Q18 spark-tpch: 50 - Q17 spark-tpch: 50 - Q16 spark-tpch: 50 - Q15 spark-tpch: 50 - Q14 spark-tpch: 50 - Q13 spark-tpch: 50 - Q12 spark-tpch: 50 - Q11 spark-tpch: 50 - Q10 spark-tpch: 50 - Q09 spark-tpch: 50 - Q08 spark-tpch: 50 - Q07 spark-tpch: 50 - Q06 spark-tpch: 50 - Q05 spark-tpch: 50 - Q04 spark-tpch: 50 - Q03 spark-tpch: 50 - Q02 spark-tpch: 50 - Q01 spark-tpch: 50 - Geometric Mean Of All Queries spark-tpch: 10 - Q22 spark-tpch: 10 - Q21 spark-tpch: 10 - Q20 spark-tpch: 10 - Q19 spark-tpch: 10 - Q18 spark-tpch: 10 - Q17 spark-tpch: 10 - Q16 spark-tpch: 10 - Q15 spark-tpch: 10 - Q14 spark-tpch: 10 - Q13 spark-tpch: 10 - Q12 spark-tpch: 10 - Q11 spark-tpch: 10 - Q10 spark-tpch: 10 - Q09 spark-tpch: 10 - Q08 spark-tpch: 10 - Q07 spark-tpch: 10 - Q06 spark-tpch: 10 - Q05 spark-tpch: 10 - Q04 spark-tpch: 10 - Q03 spark-tpch: 10 - Q02 spark-tpch: 10 - Q01 spark-tpch: 10 - Geometric Mean Of All Queries deepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream spark-tpch: 1 - Q22 spark-tpch: 1 - Q21 spark-tpch: 1 - Q20 spark-tpch: 1 - Q19 spark-tpch: 1 - Q18 spark-tpch: 1 - Q17 spark-tpch: 1 - Q16 spark-tpch: 1 - Q15 spark-tpch: 1 - Q14 spark-tpch: 1 - Q13 spark-tpch: 1 - Q12 spark-tpch: 1 - Q11 spark-tpch: 1 - Q10 spark-tpch: 1 - Q09 spark-tpch: 1 - Q08 spark-tpch: 1 - Q07 spark-tpch: 1 - Q06 spark-tpch: 1 - Q05 spark-tpch: 1 - Q04 spark-tpch: 1 - Q03 spark-tpch: 1 - Q02 spark-tpch: 1 - Q01 spark-tpch: 1 - Geometric Mean Of All Queries 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: 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: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - 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 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 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: 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 Detection, YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-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: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream spark-tpch: 100 a b c d 10.67486382 130.86564128 30.70769501 24.71872266 62.50857417 55.60917791 10.58654118 23.04547437 25.48705292 12.33711910 30.43039259 9.06239065 35.92603938 46.89715449 38.35942205 35.63054784 20.38117282 41.16542689 30.58487765 36.61449941 10.48352242 26.02234904 27.97562823 3.53586213 29.31493378 8.84160964 7.21627538 14.86223253 12.45044740 4.32050626 5.83709431 5.79615275 4.45708307 8.03465001 4.54931625 10.26555188 14.89943695 10.99399408 10.63118744 4.40131362 12.47607358 8.63682970 10.24406719 4.85099522 8.67833742 8.17090667 88.4675 11.3088 15.4510 64.7072 649.9348 49.2180 1.08502284 7.39505470 2.75555176 1.02847038 4.00372249 2.66192222 1.42731291 1.99491587 1.83231536 1.40058664 2.14987269 1.30849856 2.83789939 4.40090740 2.29091269 3.16296500 0.75870752 3.46156806 2.96026391 3.15890259 2.19916511 4.69511843 2.20328734 7.7066 129.7041 836.9172 37.9294 32.6019 980.4497 63.4770 503.4132 71.9375 13.8987 841.4259 37.7351 71.0390 14.0751 736.7739 43.1906 58.5511 17.0745 95.0151 336.1917 17.5978 56.7902 11.5611 86.3769 10.9635 91.1432 158.1544 201.9130 147.9620 215.8297 12.4868 2555.4232 72.4193 441.4407 9.6462 103.5643 9.3853 106.4432 71.1719 449.3079 1.5897 627.7539 10.52690792 131.45526123 30.53813362 25.07553101 61.9550209 55.27999115 10.53230286 22.88924599 25.39692879 12.13110542 30.40716553 8.69320774 36.27207947 46.31754303 37.97156906 35.34214783 20.29723358 43.25001144 30.26870918 36.02916718 10.45031643 25.99035454 27.78682893 3.40110779 28.79863548 8.87663841 6.0425024 14.87680531 12.44107723 4.15591764 5.68089533 5.82840872 4.03698015 8.10859299 4.26761341 10.18445492 14.1802969 10.67045593 10.531744 4.62162924 12.91888523 8.70809078 10.32122612 4.88495016 8.70151806 7.89399455 86.1505 11.6057 15.522 64.3985 648.524 49.3328 0.98886323 7.70369244 2.58762598 1.1739459 4.0458951 2.72264194 1.43939853 2.17460775 1.78157055 1.45866323 2.0294199 1.36447799 3.07959628 4.51510048 2.32780766 3.30348134 0.73223764 3.3776865 3.09257221 3.2391243 2.20726132 4.73092079 2.24531415 7.6192 131.167 806.3928 39.3833 32.1567 993.6037 62.8112 508.5902 69.4174 14.4029 837.4581 37.9456 69.8784 14.3078 726.2504 43.8384 55.5621 17.9912 94.8818 337.0821 16.9355 59.0082 11.3279 88.165 11.1265 89.8018 154.3035 206.9627 150.2259 212.7552 12.1095 2635.5729 70.9424 450.8062 9.3424 106.9295 9.377 106.5387 71.2672 448.7603 1.6656 599.1863 10.63667170 131.42175293 30.78961944 24.89447530 62.29955419 55.33429082 10.82443651 22.94638952 25.45622126 13.13648542 30.88582865 8.75260639 36.82142385 47.10843913 37.80742772 35.45530701 20.34083811 39.70042801 30.22341601 37.05844625 10.56094869 26.00166639 28.11219413 3.69966158 29.03367678 8.91217136 6.54328155 16.11452039 12.41860390 4.17572975 5.81021436 5.86177413 4.09777006 8.17116038 4.38963429 10.41971207 14.81898117 10.85271359 10.62009271 4.30036068 12.66337935 8.50457668 10.26445103 4.92897081 8.66681448 8.11142575 84.4587 11.8387 15.5926 64.1154 649.7550 49.0805 1.05880324 7.46197589 2.75284823 1.20837911 3.99324067 2.58527072 1.49448760 2.14363774 1.83836599 1.39991681 2.04039538 1.28974267 3.02914357 4.32967218 2.35779921 3.18430217 0.71082556 3.52418653 2.94428595 3.34556897 2.27846766 4.84034109 2.23705911 7.5689 132.1047 841.3435 37.7845 32.3392 988.4905 63.1295 506.1330 72.0273 13.8813 837.1418 37.9380 70.8989 14.1048 737.9777 43.0454 58.8526 16.9865 94.6789 337.7813 17.4779 57.1793 11.3576 87.9306 10.9619 91.1565 160.2780 199.2162 147.4889 216.3914 12.5199 2548.3771 71.8091 445.1623 9.4215 106.0333 9.3277 107.1042 70.7399 452.0401 1.6887 591.2570 10.26505438 131.00612386 30.51781400 25.02892049 62.73364003 55.42181269 10.91404247 23.00236766 25.42378616 13.68457921 30.04180272 9.01768939 35.92824809 46.99718602 38.38075257 35.40038427 20.38204702 38.99460093 30.55707931 35.99200439 10.44357236 26.11903827 28.12394226 3.59682607 28.90806135 8.82452583 8.02795347 14.91129049 12.40058359 4.34601260 5.85565599 5.73522472 4.61340586 8.09419775 4.48057460 10.35872300 14.92097505 10.81727695 10.74541600 4.36710962 12.65661907 8.33958340 10.15224552 4.79437430 8.73231697 8.24567273 85.1572 11.7423 15.6001 64.0842 650.6931 49.1687 1.06113847 7.40773551 2.74797662 0.99435820 3.86921136 2.57773050 1.53928820 2.27715731 1.83219139 1.39225551 2.06954416 1.29190469 3.14210590 4.55872504 2.22529737 3.25330043 0.74262398 3.30995369 2.85856040 3.15447322 2.27512868 4.84622987 2.22356446 7.4402 134.3975 820.1208 38.7188 32.3108 989.0589 63.2965 504.8420 71.9192 13.9020 845.4438 37.4534 71.4165 13.9997 737.8524 43.0569 58.5011 17.0878 95.4458 335.0968 17.5761 56.8599 11.4172 87.4654 11.1539 89.5918 158.1065 201.9444 148.2827 215.2909 12.5483 2543.1138 72.4572 441.3941 9.6084 103.9791 9.5802 104.2930 71.0506 450.0598 1.6090 620.2412 OpenBenchmarking.org
Apache Spark TPC-H Scale Factor: 50 - Q22 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q22 d b c a 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 SE +/- 0.26, N = 3 10.27 10.53 10.64 10.67
Apache Spark TPC-H Scale Factor: 50 - Q21 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q21 a d c b 30 60 90 120 150 SE +/- 0.28, N = 3 SE +/- 0.96, N = 3 SE +/- 0.77, N = 3 130.87 131.01 131.42 131.46
Apache Spark TPC-H Scale Factor: 50 - Q20 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q20 d b a c 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.24, N = 3 30.52 30.54 30.71 30.79
Apache Spark TPC-H Scale Factor: 50 - Q19 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q19 a c d b 6 12 18 24 30 SE +/- 0.11, N = 3 SE +/- 0.11, N = 3 SE +/- 0.24, N = 3 24.72 24.89 25.03 25.08
Apache Spark TPC-H Scale Factor: 50 - Q18 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q18 b c a d 14 28 42 56 70 SE +/- 0.13, N = 3 SE +/- 0.41, N = 3 SE +/- 0.54, N = 3 61.96 62.30 62.51 62.73
Apache Spark TPC-H Scale Factor: 50 - Q17 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q17 b c d a 12 24 36 48 60 SE +/- 0.19, N = 3 SE +/- 0.55, N = 3 SE +/- 0.08, N = 3 55.28 55.33 55.42 55.61
Apache Spark TPC-H Scale Factor: 50 - Q16 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q16 b a c d 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 SE +/- 0.47, N = 3 10.53 10.59 10.82 10.91
Apache Spark TPC-H Scale Factor: 50 - Q15 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q15 b c d a 6 12 18 24 30 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 22.89 22.95 23.00 23.05
Apache Spark TPC-H Scale Factor: 50 - Q14 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q14 b d c a 6 12 18 24 30 SE +/- 0.20, N = 3 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 25.40 25.42 25.46 25.49
Apache Spark TPC-H Scale Factor: 50 - Q13 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q13 b a c d 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.87, N = 3 SE +/- 0.76, N = 3 12.13 12.34 13.14 13.68
Apache Spark TPC-H Scale Factor: 50 - Q12 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q12 d b a c 7 14 21 28 35 SE +/- 0.21, N = 3 SE +/- 0.31, N = 3 SE +/- 0.47, N = 3 30.04 30.41 30.43 30.89
Apache Spark TPC-H Scale Factor: 50 - Q11 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q11 b c d a 3 6 9 12 15 SE +/- 0.09627546, N = 3 SE +/- 0.14619367, N = 3 SE +/- 0.17117283, N = 3 8.69320774 8.75260639 9.01768939 9.06239065
Apache Spark TPC-H Scale Factor: 50 - Q10 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q10 a d b c 8 16 24 32 40 SE +/- 0.66, N = 3 SE +/- 0.22, N = 3 SE +/- 0.34, N = 3 35.93 35.93 36.27 36.82
Apache Spark TPC-H Scale Factor: 50 - Q09 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q09 b a d c 11 22 33 44 55 SE +/- 0.20, N = 3 SE +/- 0.25, N = 3 SE +/- 0.54, N = 3 46.32 46.90 47.00 47.11
Apache Spark TPC-H Scale Factor: 50 - Q08 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q08 c b a d 9 18 27 36 45 SE +/- 0.08, N = 3 SE +/- 0.55, N = 3 SE +/- 0.24, N = 3 37.81 37.97 38.36 38.38
Apache Spark TPC-H Scale Factor: 50 - Q07 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q07 b d c a 8 16 24 32 40 SE +/- 0.15, N = 3 SE +/- 0.13, N = 3 SE +/- 0.46, N = 3 35.34 35.40 35.46 35.63
Apache Spark TPC-H Scale Factor: 50 - Q06 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q06 b c a d 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 20.30 20.34 20.38 20.38
Apache Spark TPC-H Scale Factor: 50 - Q05 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q05 d c a b 10 20 30 40 50 SE +/- 0.23, N = 3 SE +/- 1.29, N = 3 SE +/- 0.81, N = 3 38.99 39.70 41.17 43.25
Apache Spark TPC-H Scale Factor: 50 - Q04 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q04 c b d a 7 14 21 28 35 SE +/- 0.12, N = 3 SE +/- 0.40, N = 3 SE +/- 0.26, N = 3 30.22 30.27 30.56 30.58
Apache Spark TPC-H Scale Factor: 50 - Q03 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q03 d b a c 9 18 27 36 45 SE +/- 0.42, N = 3 SE +/- 0.49, N = 3 SE +/- 0.13, N = 3 35.99 36.03 36.61 37.06
Apache Spark TPC-H Scale Factor: 50 - Q02 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q02 d b a c 3 6 9 12 15 SE +/- 0.12, N = 3 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 10.44 10.45 10.48 10.56
Apache Spark TPC-H Scale Factor: 50 - Q01 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Q01 b c a d 6 12 18 24 30 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 SE +/- 0.18, N = 3 25.99 26.00 26.02 26.12
Apache Spark TPC-H Scale Factor: 50 - Geometric Mean Of All Queries OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 50 - Geometric Mean Of All Queries b a c d 7 14 21 28 35 SE +/- 0.09, N = 3 SE +/- 0.14, N = 3 SE +/- 0.15, N = 3 27.79 27.98 28.11 28.12 MIN: 8.69 / MAX: 131.46 MIN: 8.84 / MAX: 131.32 MIN: 8.58 / MAX: 132.82 MIN: 8.73 / MAX: 132.42
Apache Spark TPC-H Scale Factor: 10 - Q22 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q22 b a d c 0.8324 1.6648 2.4972 3.3296 4.162 SE +/- 0.10541256, N = 3 SE +/- 0.01543789, N = 3 SE +/- 0.18733559, N = 3 3.40110779 3.53586213 3.59682607 3.69966158
Apache Spark TPC-H Scale Factor: 10 - Q21 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q21 b d c a 7 14 21 28 35 SE +/- 0.20, N = 3 SE +/- 0.12, N = 3 SE +/- 0.25, N = 3 28.80 28.91 29.03 29.31
Apache Spark TPC-H Scale Factor: 10 - Q20 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q20 d a b c 2 4 6 8 10 SE +/- 0.08793082, N = 3 SE +/- 0.06394497, N = 3 SE +/- 0.01360476, N = 3 8.82452583 8.84160964 8.87663841 8.91217136
Apache Spark TPC-H Scale Factor: 10 - Q19 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q19 b c a d 2 4 6 8 10 SE +/- 0.63365910, N = 3 SE +/- 0.61100502, N = 3 SE +/- 0.02955483, N = 3 6.04250240 6.54328155 7.21627538 8.02795347
Apache Spark TPC-H Scale Factor: 10 - Q18 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q18 a b d c 4 8 12 16 20 SE +/- 0.12, N = 3 SE +/- 0.10, N = 3 SE +/- 0.79, N = 3 14.86 14.88 14.91 16.11
Apache Spark TPC-H Scale Factor: 10 - Q17 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q17 d c b a 3 6 9 12 15 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 12.40 12.42 12.44 12.45
Apache Spark TPC-H Scale Factor: 10 - Q16 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q16 b c a d 0.9779 1.9558 2.9337 3.9116 4.8895 SE +/- 0.08541494, N = 3 SE +/- 0.04048184, N = 3 SE +/- 0.00250658, N = 3 4.15591764 4.17572975 4.32050626 4.34601260
Apache Spark TPC-H Scale Factor: 10 - Q15 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q15 b c a d 1.3175 2.635 3.9525 5.27 6.5875 SE +/- 0.03487590, N = 3 SE +/- 0.03384145, N = 3 SE +/- 0.04663640, N = 3 5.68089533 5.81021436 5.83709431 5.85565599
Apache Spark TPC-H Scale Factor: 10 - Q14 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q14 d a b c 1.3189 2.6378 3.9567 5.2756 6.5945 SE +/- 0.04489420, N = 3 SE +/- 0.02725146, N = 3 SE +/- 0.02997105, N = 3 5.73522472 5.79615275 5.82840872 5.86177413
Apache Spark TPC-H Scale Factor: 10 - Q13 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q13 b c a d 1.038 2.076 3.114 4.152 5.19 SE +/- 0.05603992, N = 3 SE +/- 0.30907989, N = 3 SE +/- 0.25379241, N = 3 4.03698015 4.09777006 4.45708307 4.61340586
Apache Spark TPC-H Scale Factor: 10 - Q12 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q12 a d b c 2 4 6 8 10 SE +/- 0.04371011, N = 3 SE +/- 0.05148904, N = 3 SE +/- 0.01728126, N = 3 8.03465001 8.09419775 8.10859299 8.17116038
Apache Spark TPC-H Scale Factor: 10 - Q11 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q11 b c d a 1.0236 2.0472 3.0708 4.0944 5.118 SE +/- 0.02158043, N = 3 SE +/- 0.00931035, N = 3 SE +/- 0.03938644, N = 3 4.26761341 4.38963429 4.48057460 4.54931625
Apache Spark TPC-H Scale Factor: 10 - Q10 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q10 b a d c 3 6 9 12 15 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 10.18 10.27 10.36 10.42
Apache Spark TPC-H Scale Factor: 10 - Q09 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q09 b c a d 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.27, N = 3 SE +/- 0.31, N = 3 14.18 14.82 14.90 14.92
Apache Spark TPC-H Scale Factor: 10 - Q08 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q08 b d c a 3 6 9 12 15 SE +/- 0.08, N = 3 SE +/- 0.15, N = 3 SE +/- 0.13, N = 3 10.67 10.82 10.85 10.99
Apache Spark TPC-H Scale Factor: 10 - Q07 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q07 b c a d 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 SE +/- 0.17, N = 3 10.53 10.62 10.63 10.75
Apache Spark TPC-H Scale Factor: 10 - Q06 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q06 c d a b 1.0399 2.0798 3.1197 4.1596 5.1995 SE +/- 0.01079337, N = 3 SE +/- 0.03080177, N = 3 SE +/- 0.04431026, N = 3 4.30036068 4.36710962 4.40131362 4.62162924
Apache Spark TPC-H Scale Factor: 10 - Q05 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q05 a d c b 3 6 9 12 15 SE +/- 0.23, N = 3 SE +/- 0.18, N = 3 SE +/- 0.33, N = 3 12.48 12.66 12.66 12.92
Apache Spark TPC-H Scale Factor: 10 - Q04 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q04 d c a b 2 4 6 8 10 SE +/- 0.07436974, N = 3 SE +/- 0.08517991, N = 3 SE +/- 0.24804165, N = 3 8.33958340 8.50457668 8.63682970 8.70809078
Apache Spark TPC-H Scale Factor: 10 - Q03 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q03 d a c b 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.28, N = 3 SE +/- 0.27, N = 3 10.15 10.24 10.26 10.32
Apache Spark TPC-H Scale Factor: 10 - Q02 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q02 d a b c 1.109 2.218 3.327 4.436 5.545 SE +/- 0.02874460, N = 3 SE +/- 0.02777661, N = 3 SE +/- 0.06191683, N = 3 4.79437430 4.85099522 4.88495016 4.92897081
Apache Spark TPC-H Scale Factor: 10 - Q01 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Q01 c a b d 2 4 6 8 10 SE +/- 0.10886176, N = 3 SE +/- 0.07219277, N = 3 SE +/- 0.05844458, N = 3 8.66681448 8.67833742 8.70151806 8.73231697
Apache Spark TPC-H Scale Factor: 10 - Geometric Mean Of All Queries OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 10 - Geometric Mean Of All Queries b c a d 2 4 6 8 10 SE +/- 0.05385571, N = 3 SE +/- 0.00516651, N = 3 SE +/- 0.01945474, N = 3 7.89399455 8.11142575 8.17090667 8.24567273 MIN: 3.4 / MAX: 28.8 MIN: 3.43 / MAX: 29.17 MIN: 3.42 / MAX: 29.75 MIN: 3.57 / MAX: 29.28
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream c d b a 20 40 60 80 100 SE +/- 0.42, N = 3 SE +/- 0.61, N = 3 SE +/- 0.60, N = 15 84.46 85.16 86.15 88.47
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream c d b a 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 15 11.84 11.74 11.61 11.31
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 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream a b c d 4 8 12 16 20 SE +/- 0.16, N = 3 SE +/- 0.12, N = 3 SE +/- 0.14, N = 3 15.45 15.52 15.59 15.60
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 1.6 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream a b c d 14 28 42 56 70 SE +/- 0.66, N = 3 SE +/- 0.51, N = 3 SE +/- 0.57, N = 3 64.71 64.40 64.12 64.08
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 b c a d 140 280 420 560 700 SE +/- 1.51, N = 3 SE +/- 0.29, N = 3 SE +/- 1.27, N = 3 648.52 649.76 649.93 650.69
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 b a d c 11 22 33 44 55 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.26, N = 3 49.33 49.22 49.17 49.08
Apache Spark TPC-H Scale Factor: 1 - Q22 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q22 b c d a 0.2441 0.4882 0.7323 0.9764 1.2205 SE +/- 0.00495537, N = 3 SE +/- 0.01300436, N = 3 SE +/- 0.00972834, N = 4 0.98886323 1.05880324 1.06113847 1.08502284
Apache Spark TPC-H Scale Factor: 1 - Q21 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q21 a d c b 2 4 6 8 10 SE +/- 0.08062589, N = 4 SE +/- 0.17170189, N = 3 SE +/- 0.11898636, N = 3 7.39505470 7.40773551 7.46197589 7.70369244
Apache Spark TPC-H Scale Factor: 1 - Q20 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q20 b d c a 0.62 1.24 1.86 2.48 3.1 SE +/- 0.14206756, N = 3 SE +/- 0.13759046, N = 3 SE +/- 0.09583966, N = 4 2.58762598 2.74797662 2.75284823 2.75555176
Apache Spark TPC-H Scale Factor: 1 - Q19 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q19 d a b c 0.2719 0.5438 0.8157 1.0876 1.3595 SE +/- 0.01874751, N = 3 SE +/- 0.02636608, N = 4 SE +/- 0.07878807, N = 3 0.99435820 1.02847038 1.17394590 1.20837911
Apache Spark TPC-H Scale Factor: 1 - Q18 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q18 d c a b 0.9103 1.8206 2.7309 3.6412 4.5515 SE +/- 0.13038086, N = 3 SE +/- 0.10019808, N = 3 SE +/- 0.10303949, N = 4 3.86921136 3.99324067 4.00372249 4.04589510
Apache Spark TPC-H Scale Factor: 1 - Q17 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q17 d c a b 0.6126 1.2252 1.8378 2.4504 3.063 SE +/- 0.03392729, N = 3 SE +/- 0.01865956, N = 3 SE +/- 0.02035298, N = 4 2.57773050 2.58527072 2.66192222 2.72264194
Apache Spark TPC-H Scale Factor: 1 - Q16 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q16 a b c d 0.3463 0.6926 1.0389 1.3852 1.7315 SE +/- 0.01144007, N = 4 SE +/- 0.05940937, N = 3 SE +/- 0.04799671, N = 3 1.42731291 1.43939853 1.49448760 1.53928820
Apache Spark TPC-H Scale Factor: 1 - Q15 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q15 a c b d 0.5124 1.0248 1.5372 2.0496 2.562 SE +/- 0.04340326, N = 4 SE +/- 0.20579960, N = 3 SE +/- 0.09001964, N = 3 1.99491587 2.14363774 2.17460775 2.27715731
Apache Spark TPC-H Scale Factor: 1 - Q14 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q14 b d a c 0.4136 0.8272 1.2408 1.6544 2.068 SE +/- 0.02463739, N = 3 SE +/- 0.03540160, N = 4 SE +/- 0.01014717, N = 3 1.78157055 1.83219139 1.83231536 1.83836599
Apache Spark TPC-H Scale Factor: 1 - Q13 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q13 d c a b 0.3282 0.6564 0.9846 1.3128 1.641 SE +/- 0.02733553, N = 3 SE +/- 0.04981792, N = 3 SE +/- 0.03676867, N = 4 1.39225551 1.39991681 1.40058664 1.45866323
Apache Spark TPC-H Scale Factor: 1 - Q12 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q12 b c d a 0.4837 0.9674 1.4511 1.9348 2.4185 SE +/- 0.04470734, N = 3 SE +/- 0.02411619, N = 3 SE +/- 0.15031140, N = 4 2.02941990 2.04039538 2.06954416 2.14987269
Apache Spark TPC-H Scale Factor: 1 - Q11 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q11 c d a b 0.307 0.614 0.921 1.228 1.535 SE +/- 0.15013623, N = 3 SE +/- 0.10958276, N = 3 SE +/- 0.07929998, N = 4 1.28974267 1.29190469 1.30849856 1.36447799
Apache Spark TPC-H Scale Factor: 1 - Q10 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q10 a c b d 0.707 1.414 2.121 2.828 3.535 SE +/- 0.04789727, N = 4 SE +/- 0.03625533, N = 3 SE +/- 0.04198555, N = 3 2.83789939 3.02914357 3.07959628 3.14210590
Apache Spark TPC-H Scale Factor: 1 - Q09 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q09 c a b d 1.0257 2.0514 3.0771 4.1028 5.1285 SE +/- 0.11520840, N = 3 SE +/- 0.13363421, N = 4 SE +/- 0.17668063, N = 3 4.32967218 4.40090740 4.51510048 4.55872504
Apache Spark TPC-H Scale Factor: 1 - Q08 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q08 d a b c 0.5305 1.061 1.5915 2.122 2.6525 SE +/- 0.07315965, N = 3 SE +/- 0.02917526, N = 4 SE +/- 0.06735723, N = 3 2.22529737 2.29091269 2.32780766 2.35779921
Apache Spark TPC-H Scale Factor: 1 - Q07 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q07 a c d b 0.7433 1.4866 2.2299 2.9732 3.7165 SE +/- 0.07379513, N = 4 SE +/- 0.13350733, N = 3 SE +/- 0.03596564, N = 3 3.16296500 3.18430217 3.25330043 3.30348134
Apache Spark TPC-H Scale Factor: 1 - Q06 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q06 c b d a 0.1707 0.3414 0.5121 0.6828 0.8535 SE +/- 0.00867146, N = 3 SE +/- 0.01813313, N = 3 SE +/- 0.03196645, N = 4 0.71082556 0.73223764 0.74262398 0.75870752
Apache Spark TPC-H Scale Factor: 1 - Q05 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q05 d b a c 0.7929 1.5858 2.3787 3.1716 3.9645 SE +/- 0.06648494, N = 3 SE +/- 0.06297205, N = 4 SE +/- 0.08593638, N = 3 3.30995369 3.37768650 3.46156806 3.52418653
Apache Spark TPC-H Scale Factor: 1 - Q04 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q04 d c a b 0.6958 1.3916 2.0874 2.7832 3.479 SE +/- 0.09994253, N = 3 SE +/- 0.05472939, N = 3 SE +/- 0.02567628, N = 4 2.85856040 2.94428595 2.96026391 3.09257221
Apache Spark TPC-H Scale Factor: 1 - Q03 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q03 d a b c 0.7528 1.5056 2.2584 3.0112 3.764 SE +/- 0.04118145, N = 3 SE +/- 0.03420168, N = 4 SE +/- 0.05826206, N = 3 3.15447322 3.15890259 3.23912430 3.34556897
Apache Spark TPC-H Scale Factor: 1 - Q02 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q02 a b d c 0.5127 1.0254 1.5381 2.0508 2.5635 SE +/- 0.05229177, N = 4 SE +/- 0.07468701, N = 3 SE +/- 0.08231744, N = 3 2.19916511 2.20726132 2.27512868 2.27846766
Apache Spark TPC-H Scale Factor: 1 - Q01 OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Q01 a b c d 1.0904 2.1808 3.2712 4.3616 5.452 SE +/- 0.06902799, N = 4 SE +/- 0.05428360, N = 3 SE +/- 0.08250324, N = 3 4.69511843 4.73092079 4.84034109 4.84622987
Apache Spark TPC-H Scale Factor: 1 - Geometric Mean Of All Queries OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark TPC-H 3.5 Scale Factor: 1 - Geometric Mean Of All Queries a d c b 0.5052 1.0104 1.5156 2.0208 2.526 SE +/- 0.02461970, N = 4 SE +/- 0.02256519, N = 3 SE +/- 0.00573499, N = 3 2.20328734 2.22356446 2.23705911 2.24531415 MIN: 0.99 / MAX: 7.56 MIN: 0.97 / MAX: 7.7 MIN: 1.05 / MAX: 7.66 MIN: 0.99 / MAX: 7.7
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 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream d c b a 2 4 6 8 10 SE +/- 0.0842, N = 5 SE +/- 0.0865, N = 4 SE +/- 0.0410, N = 3 7.4402 7.5689 7.6192 7.7066
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 1.6 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream d c b a 30 60 90 120 150 SE +/- 1.48, N = 5 SE +/- 1.51, N = 4 SE +/- 0.69, N = 3 134.40 132.10 131.17 129.70
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 b d a c 200 400 600 800 1000 SE +/- 7.99, N = 3 SE +/- 12.88, N = 3 SE +/- 8.13, N = 6 806.39 820.12 836.92 841.34
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 b d a c 9 18 27 36 45 SE +/- 0.36, N = 3 SE +/- 0.52, N = 3 SE +/- 0.38, N = 6 39.38 38.72 37.93 37.78
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 b d c a 8 16 24 32 40 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 32.16 32.31 32.34 32.60
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 b d c a 200 400 600 800 1000 SE +/- 1.17, N = 3 SE +/- 1.16, N = 3 SE +/- 3.44, N = 3 993.60 989.06 988.49 980.45
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 b c d a 14 28 42 56 70 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 62.81 63.13 63.30 63.48
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 b c d a 110 220 330 440 550 SE +/- 0.45, N = 3 SE +/- 0.62, N = 3 SE +/- 0.37, N = 3 508.59 506.13 504.84 503.41
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 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream b d a c 16 32 48 64 80 SE +/- 0.18, N = 3 SE +/- 0.30, N = 3 SE +/- 0.25, N = 3 69.42 71.92 71.94 72.03
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 1.6 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream b d a c 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 14.40 13.90 13.90 13.88
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 c b a d 200 400 600 800 1000 SE +/- 6.31, N = 3 SE +/- 2.31, N = 3 SE +/- 2.60, N = 3 837.14 837.46 841.43 845.44
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 b c a d 9 18 27 36 45 SE +/- 0.25, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 37.95 37.94 37.74 37.45
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 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream b c a d 16 32 48 64 80 SE +/- 0.72, N = 3 SE +/- 0.43, N = 3 SE +/- 0.16, N = 3 69.88 70.90 71.04 71.42
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 1.6 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream b c a d 4 8 12 16 20 SE +/- 0.14, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 14.31 14.10 14.08 14.00
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 b a d c 160 320 480 640 800 SE +/- 6.44, N = 3 SE +/- 2.01, N = 3 SE +/- 4.42, N = 3 726.25 736.77 737.85 737.98
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 b a d c 10 20 30 40 50 SE +/- 0.30, N = 3 SE +/- 0.06, N = 3 SE +/- 0.28, N = 3 43.84 43.19 43.06 43.05
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream b d a c 13 26 39 52 65 SE +/- 0.11, N = 3 SE +/- 0.38, N = 3 SE +/- 0.30, N = 3 55.56 58.50 58.55 58.85
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream b d a c 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 17.99 17.09 17.07 16.99
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 c b a d 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 SE +/- 0.28, N = 3 94.68 94.88 95.02 95.45
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 c b a d 70 140 210 280 350 SE +/- 0.44, N = 3 SE +/- 0.53, N = 3 SE +/- 1.00, N = 3 337.78 337.08 336.19 335.10
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream b c d a 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 16.94 17.48 17.58 17.60
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream b c d a 13 26 39 52 65 SE +/- 0.19, N = 3 SE +/- 0.19, N = 3 SE +/- 0.15, N = 3 59.01 57.18 56.86 56.79
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream b c d a 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 11.33 11.36 11.42 11.56
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream b c d a 20 40 60 80 100 SE +/- 0.32, N = 3 SE +/- 0.19, N = 3 SE +/- 0.58, N = 3 88.17 87.93 87.47 86.38
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream c a b d 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 10.96 10.96 11.13 11.15
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream c a b d 20 40 60 80 100 SE +/- 0.17, N = 3 SE +/- 0.36, N = 3 SE +/- 0.36, N = 3 91.16 91.14 89.80 89.59
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 b d a c 40 80 120 160 200 SE +/- 1.02, N = 3 SE +/- 0.94, N = 3 SE +/- 1.36, N = 3 154.30 158.11 158.15 160.28
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 b d a c 50 100 150 200 250 SE +/- 1.27, N = 3 SE +/- 1.28, N = 3 SE +/- 1.60, N = 3 206.96 201.94 201.91 199.22
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 c a d b 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.45, N = 3 SE +/- 0.06, N = 3 147.49 147.96 148.28 150.23
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 c a d b 50 100 150 200 250 SE +/- 0.14, N = 3 SE +/- 0.62, N = 3 SE +/- 0.09, N = 3 216.39 215.83 215.29 212.76
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 b a c d 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 12.11 12.49 12.52 12.55
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 b a c d 600 1200 1800 2400 3000 SE +/- 14.52, N = 3 SE +/- 12.01, N = 3 SE +/- 15.60, N = 3 2635.57 2555.42 2548.38 2543.11
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 b c a d 16 32 48 64 80 SE +/- 0.24, N = 3 SE +/- 0.35, N = 3 SE +/- 0.19, N = 3 70.94 71.81 72.42 72.46
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 b c a d 100 200 300 400 500 SE +/- 1.47, N = 3 SE +/- 2.10, N = 3 SE +/- 1.15, N = 3 450.81 445.16 441.44 441.39
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream b c d a 3 6 9 12 15 SE +/- 0.0132, N = 3 SE +/- 0.0758, N = 3 SE +/- 0.0493, N = 3 9.3424 9.4215 9.6084 9.6462
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream b c d a 20 40 60 80 100 SE +/- 0.15, N = 3 SE +/- 0.81, N = 3 SE +/- 0.53, N = 3 106.93 106.03 103.98 103.56
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream c b a d 3 6 9 12 15 SE +/- 0.0294, N = 3 SE +/- 0.0142, N = 3 SE +/- 0.0916, N = 3 9.3277 9.3770 9.3853 9.5802
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream c b a d 20 40 60 80 100 SE +/- 0.34, N = 3 SE +/- 0.16, N = 3 SE +/- 1.00, N = 3 107.10 106.54 106.44 104.29
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 c d a b 16 32 48 64 80 SE +/- 0.10, N = 3 SE +/- 0.25, N = 3 SE +/- 0.17, N = 3 70.74 71.05 71.17 71.27
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 c d a b 100 200 300 400 500 SE +/- 0.60, N = 3 SE +/- 1.54, N = 3 SE +/- 1.01, N = 3 452.04 450.06 449.31 448.76
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream a d b c 0.38 0.76 1.14 1.52 1.9 SE +/- 0.0051, N = 3 SE +/- 0.0037, N = 3 SE +/- 0.0240, N = 3 1.5897 1.6090 1.6656 1.6887
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.6 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream a d b c 140 280 420 560 700 SE +/- 2.01, N = 3 SE +/- 1.41, N = 3 SE +/- 8.33, N = 3 627.75 620.24 599.19 591.26
Phoronix Test Suite v10.8.5