8380 2023 2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Ubuntu 22.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2301278-NE-83802023239&export=pdf&grs&rdt&rro .
8380 2023 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Vulkan Compiler File-System Screen Resolution a b c 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads) Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) Intel Ice Lake IEH 512GB 7682GB INTEL SSDPF2KX076TZ ASPEED VE228 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP Ubuntu 22.10 6.2.0-rc5-phx-dodt (x86_64) GNOME Shell X Server 1.21.1.3 1.3.211 GCC 12.2.0 ext4 1920x1080 1.3.224 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - a: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 - b: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 - c: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd000375 Python Details - a: Python 3.10.6 - b: Python 3.10.6 - c: Python 3.10.7 Security Details - dodt: Vulnerable + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + 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 Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
8380 2023 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 uvg266: Bosphorus 4K - Super Fast uvg266: Bosphorus 4K - Ultra Fast kvazaar: Bosphorus 4K - Ultra Fast uvg266: Bosphorus 4K - Very Fast uvg266: Bosphorus 1080p - Super Fast kvazaar: Bosphorus 1080p - Super Fast rocksdb: Rand Fill Sync rocksdb: Read While Writing uvg266: Bosphorus 1080p - Ultra Fast kvazaar: Bosphorus 1080p - Very Fast clickhouse: 100M Rows Hits Dataset, First Run / Cold Cache deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream kvazaar: Bosphorus 1080p - Medium kvazaar: Bosphorus 1080p - Ultra Fast rocksdb: Rand Read deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream rocksdb: Rand Fill deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream uvg266: Bosphorus 1080p - Very Fast kvazaar: Bosphorus 1080p - Slow clickhouse: 100M Rows Hits Dataset, Third Run kvazaar: Bosphorus 4K - Very Fast 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 kvazaar: Bosphorus 4K - Medium deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream rocksdb: Read Rand Write Rand deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream rocksdb: Update Rand deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream uvg266: Bosphorus 1080p - Medium 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, Second Run 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 kvazaar: Bosphorus 4K - Super Fast deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream uvg266: Bosphorus 4K - Slow deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream rocksdb: Seq Fill deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream uvg266: Bosphorus 1080p - Slow uvg266: Bosphorus 4K - Medium kvazaar: Bosphorus 4K - Slow deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream a b c 13.6531 73.1805 41.47 45.37 49.15 41.18 144.87 189.75 508007 7701319 145.42 185.67 399.61 222.8416 88.85 189.02 283388484 179.334 221.0941 180.8468 608380 52.986 18.864 144.66 84.78 427.97 44.49 20.28 20.2713 49.3215 2711634 82.2356 594126 833.8965 48.7372 47.9378 485.2563 318.7308 125.1889 55.14 49.5217 20.1894 424.16 175.351 5.693 47.91 817.1513 10.051 99.4074 14.53 452.7636 615043 88.198 223.3052 4.4681 34.3394 29.1019 83.3592 11.9851 49.65 16.29 19.81 820.5399 48.24 12.7651 78.2789 44.36 42.43 49.79 42.61 149.29 190.56 490210 7975258 146 179.78 398.98 216.629 86.38 183.89 278662255 184.1672 220.4815 180.9854 609813 53.5789 18.6571 146.27 86.02 418.34 44.3 896.6864 44.575 20.46 20.3063 49.2375 2676508 82.6722 587046 824.2189 48.3407 48.4501 482.3373 315.399 126.4586 55.51 49.9669 20.0097 421.19 175.9203 5.6761 48.11 822.4187 10.1137 98.7992 14.49 451.8421 615815 88.3866 222.2933 4.4899 34.4086 29.0443 82.9971 12.0372 49.85 16.25 19.79 821.7892 48.2451 13.8152 72.3319 42.29 44.99 46.99 40.49 143.45 183.65 508639 7764276 150.5 181.91 387.30 218.0979 86.96 184.65 275851418 182.8814 226.3902 176.3139 624361 52.2091 19.1454 142.73 83.98 426.64 43.49 878.8628 45.4474 20.17 20.0396 49.891 2711331 81.6833 588321 828.2582 48.1986 48.2239 487.4784 316.6124 125.9667 55 49.6057 20.1555 420.61 174.6452 5.7175 48.23 820.7536 10.1149 98.7893 14.44 454.2485 618232 87.9492 223.3966 4.468 34.2443 29.1825 83.31 11.9918 49.79 16.3 19.75 820.3712 48.2951 OpenBenchmarking.org
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 c b a 4 8 12 16 20 13.82 12.77 13.65
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 c b a 20 40 60 80 100 72.33 78.28 73.18
uvg266 Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast c b a 10 20 30 40 50 42.29 44.36 41.47
uvg266 Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast c b a 10 20 30 40 50 44.99 42.43 45.37
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast c b a 11 22 33 44 55 46.99 49.79 49.15 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
uvg266 Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast c b a 10 20 30 40 50 40.49 42.61 41.18
uvg266 Video Input: Bosphorus 1080p - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Super Fast c b a 30 60 90 120 150 143.45 149.29 144.87
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Super Fast c b a 40 80 120 160 200 183.65 190.56 189.75 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Random Fill Sync c b a 110K 220K 330K 440K 550K 508639 490210 508007 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 2M 4M 6M 8M 10M 7764276 7975258 7701319 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
uvg266 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast c b a 30 60 90 120 150 150.50 146.00 145.42
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Very Fast c b a 40 80 120 160 200 181.91 179.78 185.67 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 90 180 270 360 450 387.30 398.98 399.61 MIN: 35.55 / MAX: 5000 MIN: 36.81 / MAX: 4285.71 MIN: 36.92 / MAX: 4000
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 b a 50 100 150 200 250 218.10 216.63 222.84
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Medium c b a 20 40 60 80 100 86.96 86.38 88.85 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast c b a 40 80 120 160 200 184.65 183.89 189.02 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Random Read c b a 60M 120M 180M 240M 300M 275851418 278662255 283388484 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
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 b a 40 80 120 160 200 182.88 184.17 179.33
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 c b a 50 100 150 200 250 226.39 220.48 221.09
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 c b a 40 80 120 160 200 176.31 180.99 180.85
RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Random Fill c b a 130K 260K 390K 520K 650K 624361 609813 608380 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
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 c b a 12 24 36 48 60 52.21 53.58 52.99
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 c b a 5 10 15 20 25 19.15 18.66 18.86
uvg266 Video Input: Bosphorus 1080p - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Very Fast c b a 30 60 90 120 150 142.73 146.27 144.66
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Slow c b a 20 40 60 80 100 83.98 86.02 84.78 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 90 180 270 360 450 426.64 418.34 427.97 MIN: 36.9 / MAX: 4285.71 MIN: 36.14 / MAX: 4615.38 MIN: 37.34 / MAX: 6000
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast c b a 10 20 30 40 50 43.49 44.30 44.49 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 b 200 400 600 800 1000 878.86 896.69
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 b 10 20 30 40 50 45.45 44.58
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium c b a 5 10 15 20 25 20.17 20.46 20.28 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 20.04 20.31 20.27
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 49.89 49.24 49.32
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 600K 1200K 1800K 2400K 3000K 2711331 2676508 2711634 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: 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 c b a 20 40 60 80 100 81.68 82.67 82.24
RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Update Random c b a 130K 260K 390K 520K 650K 588321 587046 594126 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
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 c b a 200 400 600 800 1000 828.26 824.22 833.90
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 11 22 33 44 55 48.20 48.34 48.74
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 c b a 11 22 33 44 55 48.22 48.45 47.94
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 c b a 110 220 330 440 550 487.48 482.34 485.26
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 c b a 70 140 210 280 350 316.61 315.40 318.73
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 c b a 30 60 90 120 150 125.97 126.46 125.19
uvg266 Video Input: Bosphorus 1080p - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Medium c b a 12 24 36 48 60 55.00 55.51 55.14
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 c b a 11 22 33 44 55 49.61 49.97 49.52
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 c b a 5 10 15 20 25 20.16 20.01 20.19
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 c b a 90 180 270 360 450 420.61 421.19 424.16 MIN: 36.88 / MAX: 4285.71 MIN: 36.34 / MAX: 5000 MIN: 35.19 / MAX: 6666.67
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 c b a 40 80 120 160 200 174.65 175.92 175.35
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 c b a 1.2864 2.5728 3.8592 5.1456 6.432 5.7175 5.6761 5.6930
Kvazaar Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast c b a 11 22 33 44 55 48.23 48.11 47.91 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 c b a 200 400 600 800 1000 820.75 822.42 817.15
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 c b a 3 6 9 12 15 10.11 10.11 10.05
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 c b a 20 40 60 80 100 98.79 98.80 99.41
uvg266 Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow c b a 4 8 12 16 20 14.44 14.49 14.53
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 c b a 100 200 300 400 500 454.25 451.84 452.76
RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Sequential Fill c b a 130K 260K 390K 520K 650K 618232 615815 615043 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
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 c b a 20 40 60 80 100 87.95 88.39 88.20
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 c b a 50 100 150 200 250 223.40 222.29 223.31
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 c b a 1.0102 2.0204 3.0306 4.0408 5.051 4.4680 4.4899 4.4681
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 c b a 8 16 24 32 40 34.24 34.41 34.34
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 c b a 7 14 21 28 35 29.18 29.04 29.10
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 c b a 20 40 60 80 100 83.31 83.00 83.36
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 c b a 3 6 9 12 15 11.99 12.04 11.99
uvg266 Video Input: Bosphorus 1080p - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Slow c b a 11 22 33 44 55 49.79 49.85 49.65
uvg266 Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium c b a 4 8 12 16 20 16.30 16.25 16.29
Kvazaar Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow c b a 5 10 15 20 25 19.75 19.79 19.81 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 c b a 200 400 600 800 1000 820.37 821.79 820.54
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 c b a 11 22 33 44 55 48.30 48.25 48.24
Phoronix Test Suite v10.8.5