benchmarks for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2310231-NE-EXTRATEST13 extra tests - Phoronix Test Suite extra tests benchmarks for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2310231-NE-EXTRATEST13&grs&rdt .
extra tests Processor Motherboard Memory Disk Graphics Monitor OS Kernel Compiler File-System Screen Resolution RESET RESET2 RESET3 AMD EPYC 9124 16-Core @ 3.00GHz (16 Cores / 32 Threads) Supermicro H13SSW (1.1 BIOS) 12 x 64 GB DDR5-4800MT/s HMCG94MEBRA123N 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07 astdrmfb AlmaLinux 9.2 5.14.0-284.25.1.el9_2.x86_64 (x86_64) GCC 11.3.1 20221121 ext4 1024x768 AMD EPYC 9334 32-Core @ 2.70GHz (32 Cores / 64 Threads) DELL E207WFP 1680x1050 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: always Compiler Details - --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl Processor Details - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111 Java Details - OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS) Python Details - Python 3.9.16 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
extra tests hadoop: Open - 50 - 1000000 stress-ng: Malloc hadoop: File Status - 20 - 1000000 hadoop: File Status - 50 - 1000000 hadoop: File Status - 500 - 100000 dragonflydb: 20 - 1:100 stress-ng: Semaphores hadoop: File Status - 500 - 1000000 stress-ng: x86_64 RdRand stress-ng: Hash stress-ng: Vector Shuffle stress-ng: CPU Stress stress-ng: Floating Point deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream stress-ng: Poll stress-ng: Function Call dragonflydb: 20 - 1:10 dragonflydb: 10 - 1:10 stress-ng: Zlib dragonflydb: 50 - 1:10 embree: Pathtracer - Crown deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream embree: Pathtracer ISPC - Crown deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream dragonflydb: 50 - 1:100 deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream stress-ng: Memory Copying stress-ng: Context Switching stress-ng: Crypto deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream stress-ng: Glibc C String Functions stress-ng: AVL Tree deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream dragonflydb: 10 - 1:100 deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream embree: Pathtracer - Asian Dragon Obj embree: Pathtracer ISPC - Asian Dragon Obj ospray: gravity_spheres_volume/dim_512/ao/real_time liquid-dsp: 64 - 256 - 32 ospray: gravity_spheres_volume/dim_512/scivis/real_time stress-ng: MMAP embree: Pathtracer - Asian Dragon ospray: particle_volume/ao/real_time ospray: particle_volume/scivis/real_time deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream stress-ng: Socket Activity embree: Pathtracer ISPC - Asian Dragon deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream brl-cad: VGR Performance Metric oidn: RT.ldr_alb_nrm.3840x2160 - CPU-Only stress-ng: NUMA oidn: RTLightmap.hdr.4096x4096 - CPU-Only blender: Barbershop - CPU-Only oidn: RT.hdr_alb_nrm.3840x2160 - CPU-Only stress-ng: Vector Floating Point ospray: gravity_spheres_volume/dim_512/pathtracer/real_time blender: Pabellon Barcelona - CPU-Only stress-ng: Vector Math blender: Fishy Cat - CPU-Only stress-ng: Glibc Qsort Data Sorting blender: BMW27 - CPU-Only stress-ng: Fused Multiply-Add stress-ng: Wide Vector Math blender: Classroom - CPU-Only stress-ng: Matrix Math stress-ng: Pipe stress-ng: AVX-512 VNNI specfem3d: Mount St. Helens liquid-dsp: 64 - 256 - 512 specfem3d: Tomographic Model deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream specfem3d: Homogeneous Halfspace deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream specfem3d: Layered Halfspace 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 tidb: oltp_read_write - 256 liquid-dsp: 64 - 256 - 57 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 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Stream specfem3d: Water-layered Halfspace hadoop: Open - 100 - 100000 stress-ng: Forking cassandra: Writes build-linux-kernel: defconfig hadoop: File Status - 50 - 100000 deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-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 tidb: oltp_read_write - 32 stress-ng: SENDFILE tidb: oltp_update_non_index - 128 hadoop: Open - 100 - 1000000 stress-ng: Matrix 3D Math tidb: oltp_update_non_index - 64 tidb: oltp_point_select - 128 deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream remhos: Sample Remap Example 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 kripke: tidb: oltp_point_select - 256 svt-av1: Preset 8 - Bosphorus 4K liquid-dsp: 32 - 256 - 512 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 Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream svt-av1: Preset 12 - Bosphorus 4K hadoop: File Status - 100 - 100000 svt-av1: Preset 13 - Bosphorus 4K deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream liquid-dsp: 32 - 256 - 57 svt-av1: Preset 8 - Bosphorus 4K tidb: oltp_update_non_index - 32 deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream deepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Stream stress-ng: Mixed Scheduler svt-av1: Preset 12 - Bosphorus 4K tidb: oltp_read_write - 16 ncnn: CPU - regnety_400m svt-av1: Preset 12 - Bosphorus 1080p tidb: oltp_update_non_index - 16 svt-av1: Preset 4 - Bosphorus 4K ospray: particle_volume/pathtracer/real_time ncnn: CPU - vision_transformer svt-av1: Preset 8 - Bosphorus 1080p stress-ng: System V Message Passing svt-av1: Preset 8 - Bosphorus 1080p hadoop: File Status - 100 - 1000000 svt-av1: Preset 4 - Bosphorus 4K hadoop: Open - 50 - 100000 hadoop: Open - 20 - 1000000 svt-av1: Preset 13 - Bosphorus 1080p dragonflydb: 60 - 1:100 vvenc: Bosphorus 4K - Fast nekrs: TurboPipe Periodic svt-av1: Preset 4 - Bosphorus 1080p ncnn: CPU - blazeface vvenc: Bosphorus 4K - Faster ncnn: CPU - alexnet vvenc: Bosphorus 1080p - Fast stress-ng: MEMFD svt-av1: Preset 4 - Bosphorus 1080p liquid-dsp: 1 - 256 - 57 stress-ng: Cloning nekrs: Kershaw ncnn: CPU - efficientnet-b0 liquid-dsp: 8 - 256 - 57 liquid-dsp: 32 - 256 - 32 stress-ng: Futex vvenc: Bosphorus 1080p - Faster hadoop: Delete - 500 - 100000 dragonflydb: 60 - 1:10 ncnn: CPU - vgg16 svt-av1: Preset 12 - Bosphorus 1080p tidb: oltp_update_non_index - 1 liquid-dsp: 1 - 256 - 512 liquid-dsp: 8 - 256 - 512 ncnn: CPU - shufflenet-v2 hadoop: Create - 20 - 1000000 hadoop: Open - 500 - 1000000 stress-ng: Atomic liquid-dsp: 4 - 256 - 512 hadoop: Rename - 500 - 1000000 hadoop: Delete - 100 - 100000 ncnn: CPU - googlenet ncnn: CPU-v3-v3 - mobilenet-v3 hadoop: Open - 20 - 100000 liquid-dsp: 16 - 256 - 32 hadoop: Rename - 20 - 1000000 liquid-dsp: 4 - 256 - 32 hadoop: Delete - 20 - 1000000 hadoop: Create - 20 - 100000 liquid-dsp: 16 - 256 - 512 hadoop: Create - 500 - 100000 hadoop: Open - 500 - 100000 hadoop: Create - 100 - 1000000 hadoop: Rename - 50 - 100000 svt-av1: Preset 13 - Bosphorus 1080p liquid-dsp: 8 - 256 - 32 liquid-dsp: 1 - 256 - 32 liquid-dsp: 2 - 256 - 32 hadoop: Delete - 500 - 1000000 ncnn: CPU - mnasnet stress-ng: Mutex stress-ng: CPU Cache liquid-dsp: 4 - 256 - 57 ncnn: CPU-v2-v2 - mobilenet-v2 hadoop: Rename - 500 - 100000 ncnn: CPU - resnet18 hadoop: Create - 50 - 1000000 hadoop: Delete - 50 - 100000 ncnn: CPU - FastestDet liquid-dsp: 16 - 256 - 57 ncnn: CPU - squeezenet_ssd deepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Stream stress-ng: Pthread liquid-dsp: 2 - 256 - 512 hadoop: Delete - 20 - 100000 liquid-dsp: 2 - 256 - 57 deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream hadoop: Rename - 20 - 100000 hadoop: Delete - 50 - 1000000 deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream hadoop: Create - 50 - 100000 ncnn: CPU - mobilenet hadoop: Create - 100 - 100000 hadoop: Rename - 50 - 1000000 hadoop: Rename - 100 - 100000 ncnn: CPU - resnet50 ncnn: CPU - yolov4-tiny tidb: oltp_point_select - 1 hadoop: Delete - 100 - 1000000 hadoop: Create - 500 - 1000000 hadoop: Rename - 100 - 1000000 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: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream deepsparse: ResNet-50, Baseline - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Stream svt-av1: Preset 13 - Bosphorus 4K tidb: oltp_point_select - 64 tidb: oltp_point_select - 32 tidb: oltp_point_select - 16 tidb: oltp_read_write - 128 tidb: oltp_read_write - 64 tidb: oltp_read_write - 1 hadoop: File Status - 20 - 100000 build-linux-kernel: allmodconfig RESET RESET2 RESET3 264831 31210490.91 1879699 593120 215517 9932666.12 42481788.68 1779359 6022050.43 3622490.53 12554.84 41635.43 5845.74 1591.1704 2214330.78 13421.19 10162330.86 8302009.42 1466.4 12469755.6 21.5762 240.3763 22.68 163.1825 163.0849 11746361.87 71.844 7269.2 10072239.66 39959.41 72.7336 19957308.6 205.07 16.1569 8637294.18 109.0813 505.2797 257.567 13.137 55.5354 13.1024 22.2481 23.8331 5.61038 1056400000 5.46527 297.29 24.8143 5.5677 5.56275 70.9221 10472.15 28.2868 24.4932 295626 0.72 664.87 0.34 670.71 0.72 53844.48 6.60071 223.6 117532.19 90.46 463.11 71.89 16158855.4 772551.49 183.11 87537.46 13860878.09 1851108.77 27.1059135 282490000 27.094676107 69.6312 14.355 35.678749142 14.4253 69.2739 69.741995513 20.5061 48.7468 62965 1100900000 68.0326 14.6975 68.0846 14.6865 56.29 17.7631 64.317983137 305810 32071.19 194642 55.159 476190 38.5655 25.9193 143.2619 6.973 143.6947 6.952 46972 419265.75 41635 1256281 5817.58 34234 131165 10.7278 93.1249 31.017 7.0815 141.086 237641100 143244 67.596 273720000 202.745 4.9273 9.8064 101.9101 165.65 531915 165.948 18.2395 54.808 1031700000 59.64 26459 1.0875 916.5817 39604.33 162.288 36124 17.13 466.982 18663 4.502 151.866 55.73 119.222 7982733.22 128.583 1828154 4.152 537634 1191895 600.202 11419293.83 6.126 7950340000 14.211 3.35 12.13 6.01 18.012 431.59 10.727 52897000 3317.1 10295200000 9.35 337660000 1047500000 4273978.26 34.698 93721 12065388.34 22.59 528.292 1687 12685000 97011000 8.67 72317 1164144 246.62 48886000 76722 99701 17.98 7.55 636943 545570000 89095 138520000 116333 59630 196300000 52383 205761 69638 83333 590.49 277560000 35186000 68854000 109673 7.47 789472.5 1163806.08 190540000 7.36 78555 9.13 71403 108696 11.3 695920000 15.52 5.0159 119839.68 25206000 107875 105200000 112.6037 87032 110963 325.022 60314 16.73 59242 87912 85616 16.83 25.42 5956 112587 66037 85800 143.8424 31.0244 33.2488 15.8073 73.2047 607.0287 608.1609 48.9952 48.9994 111.1048 109.8869 493.6079 161.603 118850 97200 59739 3204 869565 9367141.2 1588.2049 9527420.8 8584414.13 11249348.91 21.427 22.6729 162.9543 12138788.95 72.1606 8951592.94 505.4126 257.395 13.0346 22.1946 23.9249 5.60814 1056700000 5.44882 24.8241 5.57113 5.55955 71.1423 28.4159 0.72 0.34 0.72 6.58666 26.340764968 282060000 27.373652887 35.320025891 69.182422904 20.4749 48.8206 1098600000 68.3818 14.6225 63.198053782 55.21 143.3333 6.9693 30.936 6.9594 143.5607 274570000 203.219 4.9157 164.103 164.679 1013800000 59.058 1.0807 922.3569 469.491 4.528 151.794 128.472 595.138 13659195.83 6.147 7961240000 14.065 12.231 18.089 48803000 10068200000 343950000 1046500000 34.694 10983543.66 12264000 99404000 49614000 544800000 136520000 196070000 277780000 35179000 68905000 188640000 686540000 5.0233 25050000 104020000 112.2518 31.0532 15.8033 607.4694 49.0574 110.7358 1256281 137709065.86 428816 1890359 598802 21025616.3 92985304.75 816327 12951786.69 7756366.8 26692.66 87949.71 12241.13 3312.5115 4603498.17 27709.8 19505101.23 16927170.48 2988.69 22835296.84 43.3981 486.7274 45.6761 327.9694 327.7891 23607335.01 143.7693 14537.11 20135718.92 79692.92 145.0143 39779508.19 407.92 32.0656 17116522.17 215.9185 999.0564 508.3448 25.7 109.2794 25.7218 43.5147 46.4622 10.9153 2053800000 10.5908 577.78 48.1476 10.7935 10.7542 136.892 20183.09 54.5018 47.1505 569090 1.38 1272.74 0.65 351.79 1.37 102433.04 12.5075 119.19 219207.68 48.68 858.22 38.91 29786647.25 1424072.34 99.35 160597.83 25368697.9 3384972.44 14.862106087 510160000 15.275376628 124.3655 8.0375 20.006271694 8.1111 123.1967 39.276372578 11.565 86.4112 111354 1911400000 39.4641 25.336 39.3077 25.4366 32.8274 30.4561 37.54996531 518135 54137.34 318052 33.904 769231 23.9807 41.6733 229.6935 4.3494 229.1517 4.3595 74741 665723.58 65674 805802 9028.11 51897 197386 7.1439 139.8342 20.688 4.7514 210.2053 351062800 210553 97.764 393800000 291.4682 3.4287 6.9453 143.8696 231.172 740741 229.116 13.1662 75.9168 1397500000 81.062 36066 0.8023 1241.8448 53630.31 216.625 47703 22.32 599.14 23758 5.719 192.555 44.06 150.628 10016615.7 160.665 2252252 5.089 653595 981354 721.7 7.293 6776830000 16.396 3.86 13.941 5.23 20.675 495.03 12.3 55677000 3751.82 9111820000 10.56 380280000 1169700000 4747454.51 38.358 103306 20.62 577.734 1843 13359000 105480000 9.38 78223 1257862 265.54 52587000 82529 107181 19.29 8.08 595238 582930000 95293 145900000 124054 63492 208610000 55525 217865 73692 88183 558.191 292720000 37083000 72570000 104362 7.11 828974.29 1221906.48 197890000 7.72 82305 8.72 74722 103950 11.81 716650000 16.2 4.8202 124853.18 26065000 112233 108010000 116.5553 90253 115022 336.7636 62189 16.29 60790 89985 83752 17.19 25.96 6080 114732 67087 84474 145.9974 31.4441 32.8336 15.9951 73.9772 613.0328 614.0225 48.7397 48.7687 111.0762 110.1322 494.298 161.431 87667 94643 869565 OpenBenchmarking.org
Apache Hadoop Operation: Open - Threads: 50 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Open - Threads: 50 - Files: 1000000 RESET RESET3 300K 600K 900K 1200K 1500K 264831 1256281
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Malloc RESET RESET3 30M 60M 90M 120M 150M 31210490.91 137709065.86 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Apache Hadoop Operation: File Status - Threads: 20 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: File Status - Threads: 20 - Files: 1000000 RESET RESET3 400K 800K 1200K 1600K 2000K 1879699 428816
Apache Hadoop Operation: File Status - Threads: 50 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: File Status - Threads: 50 - Files: 1000000 RESET RESET3 400K 800K 1200K 1600K 2000K 593120 1890359
Apache Hadoop Operation: File Status - Threads: 500 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: File Status - Threads: 500 - Files: 100000 RESET RESET3 130K 260K 390K 520K 650K 215517 598802
Dragonflydb Clients Per Thread: 20 - Set To Get Ratio: 1:100 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 20 - Set To Get Ratio: 1:100 RESET RESET2 RESET3 5M 10M 15M 20M 25M 9932666.12 9367141.20 21025616.30 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Semaphores RESET RESET3 20M 40M 60M 80M 100M 42481788.68 92985304.75 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Apache Hadoop Operation: File Status - Threads: 500 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: File Status - Threads: 500 - Files: 1000000 RESET RESET3 400K 800K 1200K 1600K 2000K 1779359 816327
Stress-NG Test: x86_64 RdRand OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: x86_64 RdRand RESET RESET3 3M 6M 9M 12M 15M 6022050.43 12951786.69 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Hash OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Hash RESET RESET3 1.7M 3.4M 5.1M 6.8M 8.5M 3622490.53 7756366.80 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Vector Shuffle OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Shuffle RESET RESET3 6K 12K 18K 24K 30K 12554.84 26692.66 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: CPU Stress RESET RESET3 20K 40K 60K 80K 100K 41635.43 87949.71 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Floating Point OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Floating Point RESET RESET3 3K 6K 9K 12K 15K 5845.74 12241.13 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 700 1400 2100 2800 3500 1591.17 1588.20 3312.51
Stress-NG Test: Poll OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Poll RESET RESET3 1000K 2000K 3000K 4000K 5000K 2214330.78 4603498.17 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Function Call OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Function Call RESET RESET3 6K 12K 18K 24K 30K 13421.19 27709.80 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Dragonflydb Clients Per Thread: 20 - Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 20 - Set To Get Ratio: 1:10 RESET RESET2 RESET3 4M 8M 12M 16M 20M 10162330.86 9527420.80 19505101.23 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Dragonflydb Clients Per Thread: 10 - Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:10 RESET RESET2 RESET3 4M 8M 12M 16M 20M 8302009.42 8584414.13 16927170.48 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Stress-NG Test: Zlib OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Zlib RESET RESET3 600 1200 1800 2400 3000 1466.40 2988.69 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Dragonflydb Clients Per Thread: 50 - Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 50 - Set To Get Ratio: 1:10 RESET RESET2 RESET3 5M 10M 15M 20M 25M 12469755.60 11249348.91 22835296.84 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.1 Binary: Pathtracer - Model: Crown RESET RESET2 RESET3 10 20 30 40 50 21.58 21.43 43.40 MIN: 21.45 / MAX: 21.93 MIN: 21.27 / MAX: 21.76 MIN: 42.87 / MAX: 44.59
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream RESET RESET3 110 220 330 440 550 240.38 486.73
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.1 Binary: Pathtracer ISPC - Model: Crown RESET RESET2 RESET3 10 20 30 40 50 22.68 22.67 45.68 MIN: 22.49 / MAX: 22.98 MIN: 22.51 / MAX: 23.04 MIN: 45.1 / MAX: 46.91
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 70 140 210 280 350 163.18 162.95 327.97
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream RESET RESET3 70 140 210 280 350 163.08 327.79
Dragonflydb Clients Per Thread: 50 - Set To Get Ratio: 1:100 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 50 - Set To Get Ratio: 1:100 RESET RESET2 RESET3 5M 10M 15M 20M 25M 11746361.87 12138788.95 23607335.01 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 30 60 90 120 150 71.84 72.16 143.77
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Memory Copying RESET RESET3 3K 6K 9K 12K 15K 7269.20 14537.11 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Context Switching RESET RESET3 4M 8M 12M 16M 20M 10072239.66 20135718.92 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Crypto RESET RESET3 20K 40K 60K 80K 100K 39959.41 79692.92 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream RESET RESET3 30 60 90 120 150 72.73 145.01
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Glibc C String Functions RESET RESET3 9M 18M 27M 36M 45M 19957308.60 39779508.19 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: AVL Tree OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: AVL Tree RESET RESET3 90 180 270 360 450 205.07 407.92 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream RESET RESET3 7 14 21 28 35 16.16 32.07
Dragonflydb Clients Per Thread: 10 - Set To Get Ratio: 1:100 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:100 RESET RESET2 RESET3 4M 8M 12M 16M 20M 8637294.18 8951592.94 17116522.17 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream RESET RESET3 50 100 150 200 250 109.08 215.92
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 200 400 600 800 1000 505.28 505.41 999.06
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 110 220 330 440 550 257.57 257.40 508.34
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 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 6 12 18 24 30 13.14 13.03 25.70
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream RESET RESET3 20 40 60 80 100 55.54 109.28
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream RESET RESET3 6 12 18 24 30 13.10 25.72
Embree Binary: Pathtracer - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.1 Binary: Pathtracer - Model: Asian Dragon Obj RESET RESET2 RESET3 10 20 30 40 50 22.25 22.19 43.51 MIN: 22.17 / MAX: 22.47 MIN: 22.12 / MAX: 22.35 MIN: 43.25 / MAX: 44.05
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.1 Binary: Pathtracer ISPC - Model: Asian Dragon Obj RESET RESET2 RESET3 11 22 33 44 55 23.83 23.92 46.46 MIN: 23.74 / MAX: 24.04 MIN: 23.83 / MAX: 24.22 MIN: 46.18 / MAX: 47.04
OSPRay Benchmark: gravity_spheres_volume/dim_512/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/ao/real_time RESET RESET2 RESET3 3 6 9 12 15 5.61038 5.60814 10.91530
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 32 RESET RESET2 RESET3 400M 800M 1200M 1600M 2000M 1056400000 1056700000 2053800000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OSPRay Benchmark: gravity_spheres_volume/dim_512/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time RESET RESET2 RESET3 3 6 9 12 15 5.46527 5.44882 10.59080
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: MMAP RESET RESET3 120 240 360 480 600 297.29 577.78 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.1 Binary: Pathtracer - Model: Asian Dragon RESET RESET2 RESET3 11 22 33 44 55 24.81 24.82 48.15 MIN: 24.73 / MAX: 25.07 MIN: 24.74 / MAX: 24.99 MIN: 47.9 / MAX: 48.87
OSPRay Benchmark: particle_volume/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: particle_volume/ao/real_time RESET RESET2 RESET3 3 6 9 12 15 5.56770 5.57113 10.79350
OSPRay Benchmark: particle_volume/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: particle_volume/scivis/real_time RESET RESET2 RESET3 3 6 9 12 15 5.56275 5.55955 10.75420
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 30 60 90 120 150 70.92 71.14 136.89
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Socket Activity RESET RESET3 4K 8K 12K 16K 20K 10472.15 20183.09 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.1 Binary: Pathtracer ISPC - Model: Asian Dragon RESET RESET2 RESET3 12 24 36 48 60 28.29 28.42 54.50 MIN: 28.19 / MAX: 28.56 MIN: 28.3 / MAX: 28.73 MIN: 54.24 / MAX: 54.99
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream RESET RESET3 11 22 33 44 55 24.49 47.15
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.36 VGR Performance Metric RESET RESET3 120K 240K 360K 480K 600K 295626 569090 1. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6
Intel Open Image Denoise Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.0 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only RESET RESET2 RESET3 0.3105 0.621 0.9315 1.242 1.5525 0.72 0.72 1.38
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: NUMA RESET RESET3 300 600 900 1200 1500 664.87 1272.74 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Intel Open Image Denoise Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.0 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only RESET RESET2 RESET3 0.1463 0.2926 0.4389 0.5852 0.7315 0.34 0.34 0.65
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.6 Blend File: Barbershop - Compute: CPU-Only RESET RESET3 140 280 420 560 700 670.71 351.79
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.0 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only RESET RESET2 RESET3 0.3083 0.6166 0.9249 1.2332 1.5415 0.72 0.72 1.37
Stress-NG Test: Vector Floating Point OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Floating Point RESET RESET3 20K 40K 60K 80K 100K 53844.48 102433.04 1. (CXX) g++ options: -O2 -std=gnu99 -lc
OSPRay Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time RESET RESET2 RESET3 3 6 9 12 15 6.60071 6.58666 12.50750
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.6 Blend File: Pabellon Barcelona - Compute: CPU-Only RESET RESET3 50 100 150 200 250 223.60 119.19
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Vector Math RESET RESET3 50K 100K 150K 200K 250K 117532.19 219207.68 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.6 Blend File: Fishy Cat - Compute: CPU-Only RESET RESET3 20 40 60 80 100 90.46 48.68
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Glibc Qsort Data Sorting RESET RESET3 200 400 600 800 1000 463.11 858.22 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.6 Blend File: BMW27 - Compute: CPU-Only RESET RESET3 16 32 48 64 80 71.89 38.91
Stress-NG Test: Fused Multiply-Add OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Fused Multiply-Add RESET RESET3 6M 12M 18M 24M 30M 16158855.40 29786647.25 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Wide Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Wide Vector Math RESET RESET3 300K 600K 900K 1200K 1500K 772551.49 1424072.34 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.6 Blend File: Classroom - Compute: CPU-Only RESET RESET3 40 80 120 160 200 183.11 99.35
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Matrix Math RESET RESET3 30K 60K 90K 120K 150K 87537.46 160597.83 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: Pipe OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Pipe RESET RESET3 5M 10M 15M 20M 25M 13860878.09 25368697.90 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: AVX-512 VNNI OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: AVX-512 VNNI RESET RESET3 700K 1400K 2100K 2800K 3500K 1851108.77 3384972.44 1. (CXX) g++ options: -O2 -std=gnu99 -lc
SPECFEM3D Model: Mount St. Helens OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.0 Model: Mount St. Helens RESET RESET2 RESET3 6 12 18 24 30 27.11 26.34 14.86 1. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 512 RESET RESET2 RESET3 110M 220M 330M 440M 550M 282490000 282060000 510160000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
SPECFEM3D Model: Tomographic Model OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.0 Model: Tomographic Model RESET RESET2 RESET3 6 12 18 24 30 27.09 27.37 15.28 1. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream RESET RESET3 30 60 90 120 150 69.63 124.37
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream RESET RESET3 4 8 12 16 20 14.3550 8.0375
SPECFEM3D Model: Homogeneous Halfspace OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.0 Model: Homogeneous Halfspace RESET RESET2 RESET3 8 16 24 32 40 35.68 35.32 20.01 1. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream RESET RESET3 4 8 12 16 20 14.4253 8.1111
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream RESET RESET3 30 60 90 120 150 69.27 123.20
SPECFEM3D Model: Layered Halfspace OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.0 Model: Layered Halfspace RESET RESET2 RESET3 16 32 48 64 80 69.74 69.18 39.28 1. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream RESET RESET2 RESET3 5 10 15 20 25 20.51 20.47 11.57
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream RESET RESET2 RESET3 20 40 60 80 100 48.75 48.82 86.41
TiDB Community Server Test: oltp_read_write - Threads: 256 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_read_write - Threads: 256 RESET RESET3 20K 40K 60K 80K 100K 62965 111354
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 57 RESET RESET2 RESET3 400M 800M 1200M 1600M 2000M 1100900000 1098600000 1911400000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream RESET RESET2 RESET3 15 30 45 60 75 68.03 68.38 39.46
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream RESET RESET2 RESET3 6 12 18 24 30 14.70 14.62 25.34
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream RESET RESET3 15 30 45 60 75 68.08 39.31
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream RESET RESET3 6 12 18 24 30 14.69 25.44
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream RESET RESET3 13 26 39 52 65 56.29 32.83
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream RESET RESET3 7 14 21 28 35 17.76 30.46
SPECFEM3D Model: Water-layered Halfspace OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.0 Model: Water-layered Halfspace RESET RESET2 RESET3 14 28 42 56 70 64.32 63.20 37.55 1. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi
Apache Hadoop Operation: Open - Threads: 100 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Open - Threads: 100 - Files: 100000 RESET RESET3 110K 220K 330K 440K 550K 305810 518135
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Forking RESET RESET3 12K 24K 36K 48K 60K 32071.19 54137.34 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.1.3 Test: Writes RESET RESET3 70K 140K 210K 280K 350K 194642 318052
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.1 Build: defconfig RESET RESET2 RESET3 12 24 36 48 60 55.16 55.21 33.90
Apache Hadoop Operation: File Status - Threads: 50 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: File Status - Threads: 50 - Files: 100000 RESET RESET3 160K 320K 480K 640K 800K 476190 769231
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream RESET RESET3 9 18 27 36 45 38.57 23.98
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream RESET RESET3 10 20 30 40 50 25.92 41.67
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream RESET RESET2 RESET3 50 100 150 200 250 143.26 143.33 229.69
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream RESET RESET2 RESET3 2 4 6 8 10 6.9730 6.9693 4.3494
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream RESET RESET3 50 100 150 200 250 143.69 229.15
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream RESET RESET3 2 4 6 8 10 6.9520 4.3595
TiDB Community Server Test: oltp_read_write - Threads: 32 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_read_write - Threads: 32 RESET RESET3 16K 32K 48K 64K 80K 46972 74741
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: SENDFILE RESET RESET3 140K 280K 420K 560K 700K 419265.75 665723.58 1. (CXX) g++ options: -O2 -std=gnu99 -lc
TiDB Community Server Test: oltp_update_non_index - Threads: 128 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_update_non_index - Threads: 128 RESET RESET3 14K 28K 42K 56K 70K 41635 65674
Apache Hadoop Operation: Open - Threads: 100 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Open - Threads: 100 - Files: 1000000 RESET RESET3 300K 600K 900K 1200K 1500K 1256281 805802
Stress-NG Test: Matrix 3D Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Matrix 3D Math RESET RESET3 2K 4K 6K 8K 10K 5817.58 9028.11 1. (CXX) g++ options: -O2 -std=gnu99 -lc
TiDB Community Server Test: oltp_update_non_index - Threads: 64 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_update_non_index - Threads: 64 RESET RESET3 11K 22K 33K 44K 55K 34234 51897
TiDB Community Server Test: oltp_point_select - Threads: 128 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_point_select - Threads: 128 RESET RESET3 40K 80K 120K 160K 200K 131165 197386
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream RESET RESET3 3 6 9 12 15 10.7278 7.1439
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream RESET RESET3 30 60 90 120 150 93.12 139.83
Remhos Test: Sample Remap Example OpenBenchmarking.org Seconds, Fewer Is Better Remhos 1.0 Test: Sample Remap Example RESET RESET2 RESET3 7 14 21 28 35 31.02 30.94 20.69 1. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream RESET RESET2 RESET3 2 4 6 8 10 7.0815 6.9594 4.7514
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream RESET RESET2 RESET3 50 100 150 200 250 141.09 143.56 210.21
Kripke OpenBenchmarking.org Throughput FoM, More Is Better Kripke 1.2.6 RESET RESET3 80M 160M 240M 320M 400M 237641100 351062800 1. (CXX) g++ options: -O3 -fopenmp -ldl
TiDB Community Server Test: oltp_point_select - Threads: 256 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_point_select - Threads: 256 RESET RESET3 50K 100K 150K 200K 250K 143244 210553
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K RESET RESET3 20 40 60 80 100 67.60 97.76 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Liquid-DSP Threads: 32 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 512 RESET RESET2 RESET3 80M 160M 240M 320M 400M 273720000 274570000 393800000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream RESET RESET2 RESET3 60 120 180 240 300 202.75 203.22 291.47
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream RESET RESET2 RESET3 1.1086 2.2172 3.3258 4.4344 5.543 4.9273 4.9157 3.4287
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream RESET RESET3 3 6 9 12 15 9.8064 6.9453
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream RESET RESET3 30 60 90 120 150 101.91 143.87
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 12 - Input: Bosphorus 4K RESET RESET2 RESET3 50 100 150 200 250 165.65 164.10 231.17 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Apache Hadoop Operation: File Status - Threads: 100 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: File Status - Threads: 100 - Files: 100000 RESET RESET3 160K 320K 480K 640K 800K 531915 740741
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 13 - Input: Bosphorus 4K RESET RESET2 RESET3 50 100 150 200 250 165.95 164.68 229.12 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream RESET RESET3 4 8 12 16 20 18.24 13.17
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream RESET RESET3 20 40 60 80 100 54.81 75.92
Liquid-DSP Threads: 32 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 57 RESET RESET2 RESET3 300M 600M 900M 1200M 1500M 1031700000 1013800000 1397500000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 8 - Input: Bosphorus 4K RESET RESET2 RESET3 20 40 60 80 100 59.64 59.06 81.06 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
TiDB Community Server Test: oltp_update_non_index - Threads: 32 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_update_non_index - Threads: 32 RESET RESET3 8K 16K 24K 32K 40K 26459 36066
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream RESET RESET2 RESET3 0.2447 0.4894 0.7341 0.9788 1.2235 1.0875 1.0807 0.8023
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream RESET RESET2 RESET3 300 600 900 1200 1500 916.58 922.36 1241.84
Stress-NG Test: Mixed Scheduler OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Mixed Scheduler RESET RESET3 11K 22K 33K 44K 55K 39604.33 53630.31 1. (CXX) g++ options: -O2 -std=gnu99 -lc
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 4K RESET RESET3 50 100 150 200 250 162.29 216.63 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
TiDB Community Server Test: oltp_read_write - Threads: 16 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_read_write - Threads: 16 RESET RESET3 10K 20K 30K 40K 50K 36124 47703
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: regnety_400m RESET RESET3 5 10 15 20 25 17.13 22.32 MIN: 16.89 / MAX: 19.07 MIN: 22.1 / MAX: 22.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 12 - Input: Bosphorus 1080p RESET RESET2 RESET3 130 260 390 520 650 466.98 469.49 599.14 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
TiDB Community Server Test: oltp_update_non_index - Threads: 16 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_update_non_index - Threads: 16 RESET RESET3 5K 10K 15K 20K 25K 18663 23758
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 4 - Input: Bosphorus 4K RESET RESET2 RESET3 1.2868 2.5736 3.8604 5.1472 6.434 4.502 4.528 5.719 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OSPRay Benchmark: particle_volume/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: particle_volume/pathtracer/real_time RESET RESET2 RESET3 40 80 120 160 200 151.87 151.79 192.56
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vision_transformer RESET RESET3 13 26 39 52 65 55.73 44.06 MIN: 54.17 / MAX: 116.29 MIN: 43.6 / MAX: 47.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 1080p RESET RESET3 30 60 90 120 150 119.22 150.63 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: System V Message Passing RESET RESET3 2M 4M 6M 8M 10M 7982733.22 10016615.70 1. (CXX) g++ options: -O2 -std=gnu99 -lc
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 8 - Input: Bosphorus 1080p RESET RESET2 RESET3 40 80 120 160 200 128.58 128.47 160.67 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Apache Hadoop Operation: File Status - Threads: 100 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: File Status - Threads: 100 - Files: 1000000 RESET RESET3 500K 1000K 1500K 2000K 2500K 1828154 2252252
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K RESET RESET3 1.145 2.29 3.435 4.58 5.725 4.152 5.089 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Apache Hadoop Operation: Open - Threads: 50 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Open - Threads: 50 - Files: 100000 RESET RESET3 140K 280K 420K 560K 700K 537634 653595
Apache Hadoop Operation: Open - Threads: 20 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Open - Threads: 20 - Files: 1000000 RESET RESET3 300K 600K 900K 1200K 1500K 1191895 981354
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 13 - Input: Bosphorus 1080p RESET RESET2 RESET3 160 320 480 640 800 600.20 595.14 721.70 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Dragonflydb Clients Per Thread: 60 - Set To Get Ratio: 1:100 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:100 RESET RESET2 3M 6M 9M 12M 15M 11419293.83 13659195.83 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
VVenC Video Input: Bosphorus 4K - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Fast RESET RESET2 RESET3 2 4 6 8 10 6.126 6.147 7.293 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
nekRS Input: TurboPipe Periodic OpenBenchmarking.org flops/rank, More Is Better nekRS 23.0 Input: TurboPipe Periodic RESET RESET2 RESET3 2000M 4000M 6000M 8000M 10000M 7950340000 7961240000 6776830000 1. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 4 - Input: Bosphorus 1080p RESET RESET2 RESET3 4 8 12 16 20 14.21 14.07 16.40 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: blazeface RESET RESET3 0.8685 1.737 2.6055 3.474 4.3425 3.35 3.86 MIN: 3.27 / MAX: 3.52 MIN: 3.79 / MAX: 4.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
VVenC Video Input: Bosphorus 4K - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Faster RESET RESET2 RESET3 4 8 12 16 20 12.13 12.23 13.94 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: alexnet RESET RESET3 2 4 6 8 10 6.01 5.23 MIN: 5.86 / MAX: 7.74 MIN: 5.01 / MAX: 5.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
VVenC Video Input: Bosphorus 1080p - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Fast RESET RESET2 RESET3 5 10 15 20 25 18.01 18.09 20.68 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: MEMFD RESET RESET3 110 220 330 440 550 431.59 495.03 1. (CXX) g++ options: -O2 -std=gnu99 -lc
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 1080p RESET RESET3 3 6 9 12 15 10.73 12.30 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 57 RESET RESET2 RESET3 12M 24M 36M 48M 60M 52897000 48803000 55677000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Stress-NG Test: Cloning OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Cloning RESET RESET3 800 1600 2400 3200 4000 3317.10 3751.82 1. (CXX) g++ options: -O2 -std=gnu99 -lc
nekRS Input: Kershaw OpenBenchmarking.org flops/rank, More Is Better nekRS 23.0 Input: Kershaw RESET RESET2 RESET3 2000M 4000M 6000M 8000M 10000M 10295200000 10068200000 9111820000 1. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: efficientnet-b0 RESET RESET3 3 6 9 12 15 9.35 10.56 MIN: 9.25 / MAX: 10.78 MIN: 9.78 / MAX: 160.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Liquid-DSP Threads: 8 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 57 RESET RESET2 RESET3 80M 160M 240M 320M 400M 337660000 343950000 380280000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 32 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 32 RESET RESET2 RESET3 300M 600M 900M 1200M 1500M 1047500000 1046500000 1169700000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Stress-NG Test: Futex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Futex RESET RESET3 1000K 2000K 3000K 4000K 5000K 4273978.26 4747454.51 1. (CXX) g++ options: -O2 -std=gnu99 -lc
VVenC Video Input: Bosphorus 1080p - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Faster RESET RESET2 RESET3 9 18 27 36 45 34.70 34.69 38.36 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
Apache Hadoop Operation: Delete - Threads: 500 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Delete - Threads: 500 - Files: 100000 RESET RESET3 20K 40K 60K 80K 100K 93721 103306
Dragonflydb Clients Per Thread: 60 - Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:10 RESET RESET2 3M 6M 9M 12M 15M 12065388.34 10983543.66 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vgg16 RESET RESET3 5 10 15 20 25 22.59 20.62 MIN: 20.48 / MAX: 23.4 MIN: 20.22 / MAX: 23.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 1080p RESET RESET3 120 240 360 480 600 528.29 577.73 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
TiDB Community Server Test: oltp_update_non_index - Threads: 1 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_update_non_index - Threads: 1 RESET RESET3 400 800 1200 1600 2000 1687 1843
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 512 RESET RESET2 RESET3 3M 6M 9M 12M 15M 12685000 12264000 13359000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 8 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 512 RESET RESET2 RESET3 20M 40M 60M 80M 100M 97011000 99404000 105480000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: shufflenet-v2 RESET RESET3 3 6 9 12 15 8.67 9.38 MIN: 8.53 / MAX: 10.83 MIN: 9.25 / MAX: 12.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Apache Hadoop Operation: Create - Threads: 20 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Create - Threads: 20 - Files: 1000000 RESET RESET3 20K 40K 60K 80K 100K 72317 78223
Apache Hadoop Operation: Open - Threads: 500 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Open - Threads: 500 - Files: 1000000 RESET RESET3 300K 600K 900K 1200K 1500K 1164144 1257862
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Atomic RESET RESET3 60 120 180 240 300 246.62 265.54 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Liquid-DSP Threads: 4 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 512 RESET RESET2 RESET3 11M 22M 33M 44M 55M 48886000 49614000 52587000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Apache Hadoop Operation: Rename - Threads: 500 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Rename - Threads: 500 - Files: 1000000 RESET RESET3 20K 40K 60K 80K 100K 76722 82529
Apache Hadoop Operation: Delete - Threads: 100 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Delete - Threads: 100 - Files: 100000 RESET RESET3 20K 40K 60K 80K 100K 99701 107181
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: googlenet RESET RESET3 5 10 15 20 25 17.98 19.29 MIN: 17.82 / MAX: 18.6 MIN: 18.99 / MAX: 22.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 RESET RESET3 2 4 6 8 10 7.55 8.08 MIN: 7.41 / MAX: 11.7 MIN: 7.94 / MAX: 8.54 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Apache Hadoop Operation: Open - Threads: 20 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Open - Threads: 20 - Files: 100000 RESET RESET3 140K 280K 420K 560K 700K 636943 595238
Liquid-DSP Threads: 16 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 32 RESET RESET2 RESET3 120M 240M 360M 480M 600M 545570000 544800000 582930000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Apache Hadoop Operation: Rename - Threads: 20 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Rename - Threads: 20 - Files: 1000000 RESET RESET3 20K 40K 60K 80K 100K 89095 95293
Liquid-DSP Threads: 4 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 32 RESET RESET2 RESET3 30M 60M 90M 120M 150M 138520000 136520000 145900000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Apache Hadoop Operation: Delete - Threads: 20 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Delete - Threads: 20 - Files: 1000000 RESET RESET3 30K 60K 90K 120K 150K 116333 124054
Apache Hadoop Operation: Create - Threads: 20 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Create - Threads: 20 - Files: 100000 RESET RESET3 14K 28K 42K 56K 70K 59630 63492
Liquid-DSP Threads: 16 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 512 RESET RESET2 RESET3 40M 80M 120M 160M 200M 196300000 196070000 208610000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Apache Hadoop Operation: Create - Threads: 500 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Create - Threads: 500 - Files: 100000 RESET RESET3 12K 24K 36K 48K 60K 52383 55525
Apache Hadoop Operation: Open - Threads: 500 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Open - Threads: 500 - Files: 100000 RESET RESET3 50K 100K 150K 200K 250K 205761 217865
Apache Hadoop Operation: Create - Threads: 100 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Create - Threads: 100 - Files: 1000000 RESET RESET3 16K 32K 48K 64K 80K 69638 73692
Apache Hadoop Operation: Rename - Threads: 50 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Rename - Threads: 50 - Files: 100000 RESET RESET3 20K 40K 60K 80K 100K 83333 88183
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 1080p RESET RESET3 130 260 390 520 650 590.49 558.19 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Liquid-DSP Threads: 8 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 32 RESET RESET2 RESET3 60M 120M 180M 240M 300M 277560000 277780000 292720000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 32 RESET RESET2 RESET3 8M 16M 24M 32M 40M 35186000 35179000 37083000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 2 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 32 RESET RESET2 RESET3 16M 32M 48M 64M 80M 68854000 68905000 72570000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Apache Hadoop Operation: Delete - Threads: 500 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Delete - Threads: 500 - Files: 1000000 RESET RESET3 20K 40K 60K 80K 100K 109673 104362
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mnasnet RESET RESET3 2 4 6 8 10 7.47 7.11 MIN: 6.42 / MAX: 190.35 MIN: 7.04 / MAX: 7.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG Test: Mutex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Mutex RESET RESET3 200K 400K 600K 800K 1000K 789472.50 828974.29 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: CPU Cache RESET RESET3 300K 600K 900K 1200K 1500K 1163806.08 1221906.48 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Liquid-DSP Threads: 4 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 57 RESET RESET2 RESET3 40M 80M 120M 160M 200M 190540000 188640000 197890000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 RESET RESET3 2 4 6 8 10 7.36 7.72 MIN: 6.92 / MAX: 8.19 MIN: 7.29 / MAX: 8.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Apache Hadoop Operation: Rename - Threads: 500 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Rename - Threads: 500 - Files: 100000 RESET RESET3 20K 40K 60K 80K 100K 78555 82305
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet18 RESET RESET3 3 6 9 12 15 9.13 8.72 MIN: 9 / MAX: 11.27 MIN: 8.48 / MAX: 9.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Apache Hadoop Operation: Create - Threads: 50 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Create - Threads: 50 - Files: 1000000 RESET RESET3 16K 32K 48K 64K 80K 71403 74722
Apache Hadoop Operation: Delete - Threads: 50 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Delete - Threads: 50 - Files: 100000 RESET RESET3 20K 40K 60K 80K 100K 108696 103950
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: FastestDet RESET RESET3 3 6 9 12 15 11.30 11.81 MIN: 11.03 / MAX: 14.81 MIN: 11.65 / MAX: 12.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Liquid-DSP Threads: 16 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 57 RESET RESET2 RESET3 150M 300M 450M 600M 750M 695920000 686540000 716650000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: squeezenet_ssd RESET RESET3 4 8 12 16 20 15.52 16.20 MIN: 15.22 / MAX: 20.06 MIN: 15.81 / MAX: 54.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Neural Magic DeepSparse Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 1.1302 2.2604 3.3906 4.5208 5.651 5.0159 5.0233 4.8202
Stress-NG Test: Pthread OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.16.04 Test: Pthread RESET RESET3 30K 60K 90K 120K 150K 119839.68 124853.18 1. (CXX) g++ options: -O2 -std=gnu99 -lc
Liquid-DSP Threads: 2 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 512 RESET RESET2 RESET3 6M 12M 18M 24M 30M 25206000 25050000 26065000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Apache Hadoop Operation: Delete - Threads: 20 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Delete - Threads: 20 - Files: 100000 RESET RESET3 20K 40K 60K 80K 100K 107875 112233
Liquid-DSP Threads: 2 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 57 RESET RESET2 RESET3 20M 40M 60M 80M 100M 105200000 104020000 108010000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 30 60 90 120 150 112.60 112.25 116.56
Apache Hadoop Operation: Rename - Threads: 20 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Rename - Threads: 20 - Files: 100000 RESET RESET3 20K 40K 60K 80K 100K 87032 90253
Apache Hadoop Operation: Delete - Threads: 50 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Delete - Threads: 50 - Files: 1000000 RESET RESET3 20K 40K 60K 80K 100K 110963 115022
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream RESET RESET3 70 140 210 280 350 325.02 336.76
Apache Hadoop Operation: Create - Threads: 50 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Create - Threads: 50 - Files: 100000 RESET RESET3 13K 26K 39K 52K 65K 60314 62189
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mobilenet RESET RESET3 4 8 12 16 20 16.73 16.29 MIN: 16.57 / MAX: 18.96 MIN: 16.05 / MAX: 16.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Apache Hadoop Operation: Create - Threads: 100 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Create - Threads: 100 - Files: 100000 RESET RESET3 13K 26K 39K 52K 65K 59242 60790
Apache Hadoop Operation: Rename - Threads: 50 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Rename - Threads: 50 - Files: 1000000 RESET RESET3 20K 40K 60K 80K 100K 87912 89985
Apache Hadoop Operation: Rename - Threads: 100 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Rename - Threads: 100 - Files: 100000 RESET RESET3 20K 40K 60K 80K 100K 85616 83752
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet50 RESET RESET3 4 8 12 16 20 16.83 17.19 MIN: 16.57 / MAX: 24.47 MIN: 16.86 / MAX: 35.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: yolov4-tiny RESET RESET3 6 12 18 24 30 25.42 25.96 MIN: 24.66 / MAX: 60.7 MIN: 25.03 / MAX: 29.61 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
TiDB Community Server Test: oltp_point_select - Threads: 1 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_point_select - Threads: 1 RESET RESET3 1300 2600 3900 5200 6500 5956 6080
Apache Hadoop Operation: Delete - Threads: 100 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Delete - Threads: 100 - Files: 1000000 RESET RESET3 20K 40K 60K 80K 100K 112587 114732
Apache Hadoop Operation: Create - Threads: 500 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Create - Threads: 500 - Files: 1000000 RESET RESET3 14K 28K 42K 56K 70K 66037 67087
Apache Hadoop Operation: Rename - Threads: 100 - Files: 1000000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: Rename - Threads: 100 - Files: 1000000 RESET RESET3 20K 40K 60K 80K 100K 85800 84474
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream RESET RESET3 30 60 90 120 150 143.84 146.00
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 7 14 21 28 35 31.02 31.05 31.44
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream RESET RESET3 8 16 24 32 40 33.25 32.83
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 4 8 12 16 20 15.81 15.80 16.00
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream RESET RESET3 16 32 48 64 80 73.20 73.98
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 130 260 390 520 650 607.03 607.47 613.03
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream RESET RESET3 130 260 390 520 650 608.16 614.02
Neural Magic DeepSparse Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 11 22 33 44 55 49.00 49.06 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 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream RESET RESET3 11 22 33 44 55 49.00 48.77
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream RESET RESET2 RESET3 20 40 60 80 100 111.10 110.74 111.08
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream RESET RESET3 20 40 60 80 100 109.89 110.13
Neural Magic DeepSparse Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream RESET RESET3 110 220 330 440 550 493.61 494.30
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 4K RESET RESET3 40 80 120 160 200 161.60 161.43 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
TiDB Community Server Test: oltp_point_select - Threads: 64 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_point_select - Threads: 64 RESET 30K 60K 90K 120K 150K 118850
TiDB Community Server Test: oltp_point_select - Threads: 32 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_point_select - Threads: 32 RESET 20K 40K 60K 80K 100K 97200
TiDB Community Server Test: oltp_point_select - Threads: 16 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_point_select - Threads: 16 RESET3 20K 40K 60K 80K 100K 87667
TiDB Community Server Test: oltp_read_write - Threads: 128 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_read_write - Threads: 128 RESET 13K 26K 39K 52K 65K 59739
TiDB Community Server Test: oltp_read_write - Threads: 64 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_read_write - Threads: 64 RESET3 20K 40K 60K 80K 100K 94643
TiDB Community Server Test: oltp_read_write - Threads: 1 OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_read_write - Threads: 1 RESET 700 1400 2100 2800 3500 3204
Apache Hadoop Operation: File Status - Threads: 20 - Files: 100000 OpenBenchmarking.org Ops per sec, More Is Better Apache Hadoop 3.3.6 Operation: File Status - Threads: 20 - Files: 100000 RESET RESET3 200K 400K 600K 800K 1000K 869565 869565
Phoronix Test Suite v10.8.4