2 x AMD EPYC 7773X 64-Core testing with a AMD DAYTONA_X (RYM1009B BIOS) and ASPEED on Ubuntu 20.04 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 2302094-NE-NEWTESTSF98 new tests feb - Phoronix Test Suite new tests feb 2 x AMD EPYC 7773X 64-Core testing with a AMD DAYTONA_X (RYM1009B BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2302094-NE-NEWTESTSF98&grs&sor .
new tests feb Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Display Server Vulkan Compiler File-System Screen Resolution a b c 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads) AMD DAYTONA_X (RYM1009B BIOS) AMD Starship/Matisse 512GB 800GB INTEL SSDPF21Q800GB ASPEED VE228 2 x Mellanox MT27710 Ubuntu 20.04 6.2.0-rc1-phx (x86_64) X Server 1.1.182 GCC 9.4.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-Av3uEd/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --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-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: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229 Python Details - Python 3.8.10 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
new tests feb pgbench: 100 - 500 - Read Write - Average Latency pgbench: 100 - 500 - Read Write pgbench: 1 - 500 - Read Write pgbench: 1 - 500 - Read Write - Average Latency aom-av1: Speed 6 Realtime - Bosphorus 1080p deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream pgbench: 100 - 1000 - Read Write pgbench: 100 - 1000 - Read Write - Average Latency rocksdb: Rand Fill Sync pgbench: 1 - 1000 - Read Write - Average Latency pgbench: 1 - 1000 - Read Write aom-av1: Speed 8 Realtime - Bosphorus 1080p memcached: 1:5 aom-av1: Speed 6 Two-Pass - Bosphorus 1080p pgbench: 100 - 800 - Read Write - Average Latency pgbench: 100 - 800 - Read Write aom-av1: Speed 8 Realtime - Bosphorus 4K aom-av1: Speed 6 Realtime - Bosphorus 4K pgbench: 1 - 800 - Read Write - Average Latency pgbench: 1 - 800 - Read Write aom-av1: Speed 9 Realtime - Bosphorus 1080p rocksdb: Update Rand rocksdb: Read While Writing aom-av1: Speed 10 Realtime - Bosphorus 1080p deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream pgbench: 1 - 800 - Read Only - Average Latency pgbench: 1 - 800 - Read Only pgbench: 1 - 1000 - Read Only pgbench: 1 - 1000 - Read Only - Average Latency aom-av1: Speed 10 Realtime - Bosphorus 4K embree: Pathtracer ISPC - Asian Dragon pgbench: 100 - 1000 - Read Only aom-av1: Speed 4 Two-Pass - Bosphorus 1080p pgbench: 100 - 1000 - Read Only - Average Latency memcached: 1:10 aom-av1: Speed 4 Two-Pass - Bosphorus 4K pgbench: 100 - 500 - Read Only - Average Latency embree: Pathtracer - Asian Dragon Obj pgbench: 100 - 500 - Read Only rocksdb: Read Rand Write Rand embree: Pathtracer ISPC - Asian Dragon Obj pgbench: 1 - 500 - Read Only pgbench: 1 - 500 - Read Only - Average Latency embree: Pathtracer - Asian Dragon clickhouse: 100M Rows Hits Dataset, First Run / Cold Cache aom-av1: Speed 6 Two-Pass - Bosphorus 4K pgbench: 100 - 800 - Read Only - Average Latency pgbench: 100 - 800 - Read Only deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream aom-av1: Speed 9 Realtime - Bosphorus 4K memcached: 1:100 aom-av1: Speed 0 Two-Pass - Bosphorus 4K vvenc: Bosphorus 4K - Faster deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream clickhouse: 100M Rows Hits Dataset, Second Run deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream clickhouse: 100M Rows Hits Dataset, Third Run vvenc: Bosphorus 4K - Fast deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream aom-av1: Speed 0 Two-Pass - Bosphorus 1080p deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream vvenc: Bosphorus 1080p - Faster rocksdb: Seq Fill rocksdb: Rand Fill deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream rocksdb: Rand Read deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream embree: Pathtracer ISPC - Crown vvenc: Bosphorus 1080p - Fast embree: Pathtracer - Crown deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - 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 deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream pgbench: 1 - 5000 - Read Only a b c 7.168 69750 643 778.086 127.45 12.6372 79.0977 31028 32.229 248033 2713.482 369 108.92 1715028.52 48.86 23.616 33875 47.22 48.34 1962.735 408 115.22 355548 16405765 131.46 42.0763 23.7519 0.267 2990818 3023662 0.331 51.5 99.7415 3077262 20.73 0.325 3329591.88 10.38 0.173 86.4559 2882020 1930699 85.099 2922544 0.171 99.2327 400.63 18.56 0.27 2966831 112.2854 8.9018 52.06 2544101.48 0.42 7.785 48.6951 20.532 152.7329 6.5448 409.80 20.7848 48.1028 410.46 4.171 308.8186 1.18 206.4946 919.7448 69.4816 19.479 312683 324824 28.9903 34.4683 490161595 157.6935 148.0283 6.7527 72.9256 77.1167 828.7139 122.2862 9.199 130.9866 309.8198 404.3013 108.4437 104.4651 611.1989 866.5954 73.2723 206.102 586.6371 57.6844 17.3268 867.5209 13.329 37511 866 577.595 92.17 17.4023 57.4453 25287 39.546 303632 2256.384 443 124.02 2036178.01 46.79 27.844 28732 53.27 50.79 1822.512 439 121.56 322635 17477979 139.32 38.8608 25.7142 0.282 2839215 2878852 0.347 54.31 93.917 2980639 19.57 0.335 3250297.65 10.94 0.167 82.9707 2993559 1986053 83.0478 2907436 0.172 95.6757 414.74 19.15 0.268 2985790 109.9753 9.0882 52.81 2589721.87 0.42 7.936 48.6918 20.5328 150.4615 6.6434 416.27 20.4797 48.8173 413.96 4.216 307.0392 1.17 207.898 915.488 69.762 19.401 311113 326914 28.8092 34.6838 489362655 158.297 147.8807 6.7592 73.0427 77.4654 825.0139 122.7312 9.189 130.4574 309.0474 403.1635 108.6457 104.4808 611.2107 867.5692 73.0861 206.2847 585.8154 57.6734 17.3284 867.2053 13.151 38019 621 804.508 115.67 17.2738 57.873 25872 38.651 289690 2397.172 417 129.87 1920833.99 41.33 26.514 30172 54.93 55.01 1733.168 462 128.76 321956 18106083 126.75 41.2595 24.2179 0.287 2784063 2840003 0.352 51.09 95.4401 2903654 20.2 0.344 3154402.4 10.67 0.176 82.0876 2842685 2026415 86.9493 2806211 0.178 95.8015 414.77 18.66 0.276 2900704 109.0956 9.1614 53.52 2525635.19 0.43 7.95 47.8377 20.8984 150.1962 6.6553 414.21 20.7528 48.1734 415.86 4.217 305.8593 1.17 208.2214 921.9023 69.2876 19.531 313140 325125 28.867 34.6149 487197889 158.5488 147.2768 6.7869 73.2699 77.166 827.9721 122.8282 9.159 130.4851 310.1681 402.8567 108.2597 104.7896 609.4456 868.8313 73.1896 205.8095 586.3552 57.6175 17.345 867.2561 OpenBenchmarking.org
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency a c b 3 6 9 12 15 7.168 13.151 13.329 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Write a c b 15K 30K 45K 60K 75K 69750 38019 37511 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL Scaling Factor: 1 - Clients: 500 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Write b a c 200 400 600 800 1000 866 643 621 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL Scaling Factor: 1 - Clients: 500 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Write - Average Latency b a c 200 400 600 800 1000 577.60 778.09 804.51 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p a c b 30 60 90 120 150 127.45 115.67 92.17 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream a c b 4 8 12 16 20 12.64 17.27 17.40
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream a c b 20 40 60 80 100 79.10 57.87 57.45
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write a c b 7K 14K 21K 28K 35K 31028 25872 25287 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency a c b 9 18 27 36 45 32.23 38.65 39.55 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Random Fill Sync b c a 70K 140K 210K 280K 350K 303632 289690 248033 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
PostgreSQL Scaling Factor: 1 - Clients: 1000 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 1000 - Mode: Read Write - Average Latency b c a 600 1200 1800 2400 3000 2256.38 2397.17 2713.48 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL Scaling Factor: 1 - Clients: 1000 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 1000 - Mode: Read Write b c a 100 200 300 400 500 443 417 369 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p c b a 30 60 90 120 150 129.87 124.02 108.92 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Memcached Set To Get Ratio: 1:5 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.18 Set To Get Ratio: 1:5 b c a 400K 800K 1200K 1600K 2000K 2036178.01 1920833.99 1715028.52 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p a b c 11 22 33 44 55 48.86 46.79 41.33 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency a c b 7 14 21 28 35 23.62 26.51 27.84 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Write a c b 7K 14K 21K 28K 35K 33875 30172 28732 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K c b a 12 24 36 48 60 54.93 53.27 47.22 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K c b a 12 24 36 48 60 55.01 50.79 48.34 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
PostgreSQL Scaling Factor: 1 - Clients: 800 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 800 - Mode: Read Write - Average Latency c b a 400 800 1200 1600 2000 1733.17 1822.51 1962.74 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL Scaling Factor: 1 - Clients: 800 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 800 - Mode: Read Write c b a 100 200 300 400 500 462 439 408 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p c b a 30 60 90 120 150 128.76 121.56 115.22 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Update Random a b c 80K 160K 240K 320K 400K 355548 322635 321956 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Read While Writing c b a 4M 8M 12M 16M 20M 18106083 17477979 16405765 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
AOM AV1 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p b a c 30 60 90 120 150 139.32 131.46 126.75 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
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 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream a c b 10 20 30 40 50 42.08 41.26 38.86
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 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream a c b 6 12 18 24 30 23.75 24.22 25.71
PostgreSQL Scaling Factor: 1 - Clients: 800 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 800 - Mode: Read Only - Average Latency a b c 0.0646 0.1292 0.1938 0.2584 0.323 0.267 0.282 0.287 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL Scaling Factor: 1 - Clients: 800 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 800 - Mode: Read Only a b c 600K 1200K 1800K 2400K 3000K 2990818 2839215 2784063 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL Scaling Factor: 1 - Clients: 1000 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 1000 - Mode: Read Only a b c 600K 1200K 1800K 2400K 3000K 3023662 2878852 2840003 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL Scaling Factor: 1 - Clients: 1000 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 1000 - Mode: Read Only - Average Latency a b c 0.0792 0.1584 0.2376 0.3168 0.396 0.331 0.347 0.352 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
AOM AV1 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K b a c 12 24 36 48 60 54.31 51.50 51.09 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer ISPC - Model: Asian Dragon a c b 20 40 60 80 100 99.74 95.44 93.92 MIN: 98.23 / MAX: 103.23 MIN: 92.18 / MAX: 102.02 MIN: 90.2 / MAX: 98.9
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only a b c 700K 1400K 2100K 2800K 3500K 3077262 2980639 2903654 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
AOM AV1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p a c b 5 10 15 20 25 20.73 20.20 19.57 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency a b c 0.0774 0.1548 0.2322 0.3096 0.387 0.325 0.335 0.344 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Memcached Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.18 Set To Get Ratio: 1:10 a b c 700K 1400K 2100K 2800K 3500K 3329591.88 3250297.65 3154402.40 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
AOM AV1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K b c a 3 6 9 12 15 10.94 10.67 10.38 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency b a c 0.0396 0.0792 0.1188 0.1584 0.198 0.167 0.173 0.176 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Embree Binary: Pathtracer - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer - Model: Asian Dragon Obj a b c 20 40 60 80 100 86.46 82.97 82.09 MIN: 84.45 / MAX: 88.79 MIN: 79.84 / MAX: 86.19 MIN: 79.6 / MAX: 86.93
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only b a c 600K 1200K 1800K 2400K 3000K 2993559 2882020 2842685 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Read Random Write Random c b a 400K 800K 1200K 1600K 2000K 2026415 1986053 1930699 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer ISPC - Model: Asian Dragon Obj c a b 20 40 60 80 100 86.95 85.10 83.05 MIN: 85.11 / MAX: 89.77 MIN: 82.35 / MAX: 88.55 MIN: 81.22 / MAX: 86.62
PostgreSQL Scaling Factor: 1 - Clients: 500 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Only a b c 600K 1200K 1800K 2400K 3000K 2922544 2907436 2806211 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL Scaling Factor: 1 - Clients: 500 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Only - Average Latency a b c 0.0401 0.0802 0.1203 0.1604 0.2005 0.171 0.172 0.178 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer - Model: Asian Dragon a c b 20 40 60 80 100 99.23 95.80 95.68 MIN: 97.77 / MAX: 101.75 MIN: 92.08 / MAX: 101.1 MIN: 94.26 / MAX: 98.12
ClickHouse 100M Rows Hits Dataset, First Run / Cold Cache OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache c b a 90 180 270 360 450 414.77 414.74 400.63 MIN: 54.25 / MAX: 3750 MIN: 55.35 / MAX: 3529.41 MIN: 52.22 / MAX: 3750
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K b c a 5 10 15 20 25 19.15 18.66 18.56 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency b a c 0.0621 0.1242 0.1863 0.2484 0.3105 0.268 0.270 0.276 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Only b a c 600K 1200K 1800K 2400K 3000K 2985790 2966831 2900704 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
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 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream a b c 30 60 90 120 150 112.29 109.98 109.10
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 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream a b c 3 6 9 12 15 8.9018 9.0882 9.1614
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K c b a 12 24 36 48 60 53.52 52.81 52.06 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Memcached Set To Get Ratio: 1:100 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.18 Set To Get Ratio: 1:100 b a c 600K 1200K 1800K 2400K 3000K 2589721.87 2544101.48 2525635.19 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
AOM AV1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K c b a 0.0968 0.1936 0.2904 0.3872 0.484 0.43 0.42 0.42 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
VVenC Video Input: Bosphorus 4K - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Faster c b a 2 4 6 8 10 7.950 7.936 7.785 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto -lpthread
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 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream c b a 11 22 33 44 55 47.84 48.69 48.70
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 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream c b a 5 10 15 20 25 20.90 20.53 20.53
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream a b c 30 60 90 120 150 152.73 150.46 150.20
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream a b c 2 4 6 8 10 6.5448 6.6434 6.6553
ClickHouse 100M Rows Hits Dataset, Second Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run b c a 90 180 270 360 450 416.27 414.21 409.80 MIN: 51.81 / MAX: 4000 MIN: 58.65 / MAX: 4615.38 MIN: 58.42 / MAX: 4615.38
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 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a c b 5 10 15 20 25 20.78 20.75 20.48
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 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a c b 11 22 33 44 55 48.10 48.17 48.82
ClickHouse 100M Rows Hits Dataset, Third Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run c b a 90 180 270 360 450 415.86 413.96 410.46 MIN: 58.08 / MAX: 4615.38 MIN: 51.81 / MAX: 3000 MIN: 56.55 / MAX: 4000
VVenC Video Input: Bosphorus 4K - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Fast c b a 0.9488 1.8976 2.8464 3.7952 4.744 4.217 4.216 4.171 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto -lpthread
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 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream a b c 70 140 210 280 350 308.82 307.04 305.86
AOM AV1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p a c b 0.2655 0.531 0.7965 1.062 1.3275 1.18 1.17 1.17 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
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 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream a b c 50 100 150 200 250 206.49 207.90 208.22
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 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream c a b 200 400 600 800 1000 921.90 919.74 915.49
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 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream c a b 16 32 48 64 80 69.29 69.48 69.76
VVenC Video Input: Bosphorus 1080p - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Faster c a b 5 10 15 20 25 19.53 19.48 19.40 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto -lpthread
RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Sequential Fill c a b 70K 140K 210K 280K 350K 313140 312683 311113 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Random Fill b c a 70K 140K 210K 280K 350K 326914 325125 324824 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a c b 7 14 21 28 35 28.99 28.87 28.81
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a c b 8 16 24 32 40 34.47 34.61 34.68
RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Random Read a b c 100M 200M 300M 400M 500M 490161595 489362655 487197889 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream a b c 40 80 120 160 200 157.69 158.30 158.55
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b c 30 60 90 120 150 148.03 147.88 147.28
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b c 2 4 6 8 10 6.7527 6.7592 6.7869
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 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream c b a 16 32 48 64 80 73.27 73.04 72.93
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a c b 20 40 60 80 100 77.12 77.17 77.47
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a c b 200 400 600 800 1000 828.71 827.97 825.01
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer ISPC - Model: Crown c b a 30 60 90 120 150 122.83 122.73 122.29 MIN: 120.35 / MAX: 131.08 MIN: 120.29 / MAX: 130.38 MIN: 119.79 / MAX: 130.16
VVenC Video Input: Bosphorus 1080p - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Fast a b c 3 6 9 12 15 9.199 9.189 9.159 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto -lpthread
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer - Model: Crown a c b 30 60 90 120 150 130.99 130.49 130.46 MIN: 128.55 / MAX: 138.77 MIN: 128.09 / MAX: 140.15 MIN: 127.88 / MAX: 139.72
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 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream c a b 70 140 210 280 350 310.17 309.82 309.05
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream a b c 90 180 270 360 450 404.30 403.16 402.86
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream b a c 20 40 60 80 100 108.65 108.44 108.26
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b c 20 40 60 80 100 104.47 104.48 104.79
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream b a c 130 260 390 520 650 611.21 611.20 609.45
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 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b c 200 400 600 800 1000 866.60 867.57 868.83
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 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a c b 16 32 48 64 80 73.27 73.19 73.09
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 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream c a b 50 100 150 200 250 205.81 206.10 206.28
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream b c a 130 260 390 520 650 585.82 586.36 586.64
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 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream a b c 13 26 39 52 65 57.68 57.67 57.62
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 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream a b c 4 8 12 16 20 17.33 17.33 17.35
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 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream b c a 200 400 600 800 1000 867.21 867.26 867.52
Phoronix Test Suite v10.8.4