2970WX July AMD Ryzen Threadripper 2970WX 24-Core testing with a Gigabyte X399 AORUS Gaming 7 (F12h BIOS) and Sapphire AMD Radeon RX 550 640SP / 560/560X 4GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2108019-IB-2970WXJUL61&grs&rdt .
2970WX July Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution 1 2 3 4 5 AMD Ryzen Threadripper 2970WX 24-Core @ 3.00GHz (24 Cores / 48 Threads) Gigabyte X399 AORUS Gaming 7 (F12h BIOS) AMD 17h 16GB 120GB Corsair Force MP500 Sapphire AMD Radeon RX 550 640SP / 560/560X 4GB (1300/1750MHz) Realtek ALC1220 VA2431 Qualcomm Atheros Killer E2500 + 2 x QLogic cLOM8214 1/10GbE + Intel 8265 / 8275 Ubuntu 20.04 5.9.0-050900rc6daily20200926-generic (x86_64) 20200925 GNOME Shell 3.36.4 X Server 1.20.9 4.6 Mesa 20.2.6 (LLVM 11.0.0) GCC 9.3.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x800820d Graphics Details - GLAMOR Java Details - OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04) Python Details - 1: Python 3.8.5 - 2: Python 3.8.10 - 3: Python 3.8.10 - 4: Python 3.8.10 - 5: Python 3.8.10 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected
2970WX July ncnn: CPU - resnet18 rocksdb: Rand Fill Sync cassandra: Reads ncnn: CPU - alexnet ncnn: CPU - resnet50 mnn: squeezenetv1.1 ncnn: CPU - vgg16 mnn: mobilenetV3 natron: Spaceship renaissance: Apache Spark PageRank rocksdb: Rand Fill ncnn: CPU - squeezenet_ssd renaissance: Scala Dotty cassandra: Mixed 1:3 mnn: SqueezeNetV1.0 ncnn: CPU - googlenet ncnn: Vulkan GPU - blazeface mnn: resnet-v2-50 rocksdb: Seq Fill ncnn: CPU - yolov4-tiny mnn: MobileNetV2_224 cassandra: Mixed 1:1 ncnn: CPU - mnasnet ncnn: CPU - shufflenet-v2 ncnn: CPU - blazeface ncnn: CPU-v3-v3 - mobilenet-v3 renaissance: Savina Reactors.IO ncnn: CPU - mobilenet mnn: inception-v3 ncnn: CPU - regnety_400m renaissance: Apache Spark ALS ncnn: Vulkan GPU - squeezenet_ssd ncnn: CPU - efficientnet-b0 renaissance: Apache Spark Bayes rocksdb: Read While Writing cassandra: Writes renaissance: In-Memory Database Shootout renaissance: Finagle HTTP Requests rocksdb: Rand Read rocksdb: Update Rand rocksdb: Read Rand Write Rand ncnn: CPU-v2-v2 - mobilenet-v2 mnn: mobilenet-v1-1.0 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 renaissance: Rand Forest renaissance: Genetic Algorithm Using Jenetics + Futures yafaray: Total Time For Sample Scene renaissance: Akka Unbalanced Cobwebbed Tree ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - regnety_400m tnn: CPU - SqueezeNet v2 ncnn: Vulkan GPU - mobilenet renaissance: ALS Movie Lens blosc: blosclz ncnn: Vulkan GPU - efficientnet-b0 tnn: CPU - SqueezeNet v1.1 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - vgg16 tnn: CPU - MobileNet v2 tnn: CPU - DenseNet gravitymark: 1920 x 1080 - Vulkan 1 2 3 4 5 44.83 16365 91943 24.56 68.54 9.868 97.15 5.165 3.4 5088.7 559506 42.91 1132.9 97181 12.281 35.87 3.11 44.868 629253 52 7.707 107795 12.19 14 5.79 13.01 12292.6 29.59 59.53 38.7 2359.6 13.47 17.03 1209.1 3684442 137190 6178.5 4099.4 105202520 516006 1929291 13.38 5.114 7.35 920.0 2665.9 96.086 21703.7 5.56 7.05 11.31 10.19 72.115 13.12 9836.8 15950.7 15.48 256.355 5.85 10.29 20 4.97 15.32 28.93 306.266 3034.7 33.2 56.06 17701 105525 26.93 53.95 8.954 87.61 4.324 3.2 5443.7 629001 36.43 1111.5 105086 11.024 30.9 3.1 50.67 593316 47.08 8.046 98990 12.86 12.78 5.33 13.65 12326.5 31.08 61.552 36.84 2279.6 13.18 16.06 1184.2 3795875 130153 6439.5 3906.7 106197835 518649 2007692 13.53 4.948 7.43 892.7 2700.4 98.403 21813.4 5.6 7.11 11.34 10.37 72.513 12.92 9878.2 15733 15.27 256.485 5.83 10.43 20.24 4.97 15.16 29.1 305.278 3023.791 33.2 47.96 12380 138409 22.99 50.1 8.024 80.57 5.225 3.3 5041.3 558560 38.83 1038.3 112837 11.363 31.94 2.97 46.243 654095 49.51 7.615 105033 11.84 13.56 5.58 12.74 11693.4 28.71 59.596 36.1 2305.2 14.09 17.12 1180.9 3593614 131113 6178.3 4055.7 107926092 497709 1985772 13.02 5.109 7.59 902.9 2679.7 98.825 21476.3 5.61 6.99 11.58 10.12 71.38 13.17 10001.3 15895.6 15.26 256.321 5.91 10.39 20 4.97 15.32 28.8 306.189 3026.058 33.2 51.53 20282 102666 27.83 54.6 10.299 98.93 4.359 3.2 4485.8 563861 41.15 968.0 96271 12.684 33.67 3.03 46.475 586679 49.12 7.59 109065 12.29 13.81 5.61 12.59 12667.5 28.82 59.249 36.25 2202.1 13.19 16.68 1162.1 3656007 131846 6142.0 4040.6 110355654 498715 1986790 13.28 5.011 7.39 911.1 2620.0 98.453 22068.2 5.5 6.92 11.38 10.34 71.217 12.98 9814.8 16025.3 15.21 256.303 5.88 10.33 19.98 4.93 15.2 29.06 305.568 3035.013 33.2 31.22 19465 106201 32.93 67.92 9.974 83.42 4.266 2.8 5102.0 524031 41.54 965.4 111614 12.806 31.59 3.44 46.217 662215 48.67 7.292 105682 11.71 13.53 5.53 13.56 11704.2 28.75 57.156 36.55 2220.6 13.25 16.52 1231.9 3634278 130920 6457.2 4006.9 108371044 515847 1986640 13.5 4.996 7.35 891.3 2660.0 96.467 21886.5 5.46 7.06 11.28 10.15 72.72 12.97 9857.0 15930.8 15.3 260.288 5.86 10.38 20.01 4.99 15.23 28.9 304.27 3035.692 33.2 OpenBenchmarking.org
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet18 1 2 3 4 5 13 26 39 52 65 44.83 56.06 47.96 51.53 31.22 MIN: 23.94 / MAX: 207.98 MIN: 23.61 / MAX: 202.81 MIN: 21.37 / MAX: 192.24 MIN: 22.9 / MAX: 210.3 MIN: 23.82 / MAX: 211.9 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Sync 1 2 3 4 5 4K 8K 12K 16K 20K 16365 17701 12380 20282 19465 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Apache Cassandra Test: Reads OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Reads 1 2 3 4 5 30K 60K 90K 120K 150K 91943 105525 138409 102666 106201
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: alexnet 1 2 3 4 5 8 16 24 32 40 24.56 26.93 22.99 27.83 32.93 MIN: 15.88 / MAX: 92.56 MIN: 19.47 / MAX: 85.7 MIN: 15.58 / MAX: 92.05 MIN: 18.52 / MAX: 91.86 MIN: 19.24 / MAX: 89.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet50 1 2 3 4 5 15 30 45 60 75 68.54 53.95 50.10 54.60 67.92 MIN: 39.32 / MAX: 510.25 MIN: 37.14 / MAX: 491.26 MIN: 37.92 / MAX: 520.46 MIN: 36.7 / MAX: 497.36 MIN: 38.45 / MAX: 507.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: squeezenetv1.1 1 2 3 4 5 3 6 9 12 15 9.868 8.954 8.024 10.299 9.974 MIN: 9.54 / MAX: 23.89 MIN: 8.01 / MAX: 11.74 MIN: 7.58 / MAX: 11.85 MIN: 9.73 / MAX: 18.57 MIN: 7.53 / MAX: 12.21 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: vgg16 1 2 3 4 5 20 40 60 80 100 97.15 87.61 80.57 98.93 83.42 MIN: 64.38 / MAX: 202.68 MIN: 68.85 / MAX: 190.59 MIN: 62.68 / MAX: 197.8 MIN: 74.18 / MAX: 190.37 MIN: 66.24 / MAX: 193.76 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenetV3 1 2 3 4 5 1.1756 2.3512 3.5268 4.7024 5.878 5.165 4.324 5.225 4.359 4.266 MIN: 5.09 / MAX: 5.32 MIN: 4.26 / MAX: 4.41 MIN: 5.17 / MAX: 5.3 MIN: 4.19 / MAX: 4.5 MIN: 4.19 / MAX: 4.34 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Natron Input: Spaceship OpenBenchmarking.org FPS, More Is Better Natron 2.4 Input: Spaceship 1 2 3 4 5 0.765 1.53 2.295 3.06 3.825 3.4 3.2 3.3 3.2 2.8
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark PageRank 1 2 3 4 5 1200 2400 3600 4800 6000 5088.7 5443.7 5041.3 4485.8 5102.0 MIN: 4448.56 / MAX: 6210.19 MIN: 4391.93 / MAX: 6021.74 MIN: 4424.93 / MAX: 5742.67 MIN: 3933.91 / MAX: 4772.53 MIN: 4315.23 / MAX: 5711.89
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill 1 2 3 4 5 130K 260K 390K 520K 650K 559506 629001 558560 563861 524031 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: squeezenet_ssd 1 2 3 4 5 10 20 30 40 50 42.91 36.43 38.83 41.15 41.54 MIN: 30.87 / MAX: 416.32 MIN: 30.42 / MAX: 410.51 MIN: 30.73 / MAX: 374.79 MIN: 31.18 / MAX: 416.67 MIN: 30.67 / MAX: 413.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Scala Dotty 1 2 3 4 5 200 400 600 800 1000 1132.9 1111.5 1038.3 968.0 965.4 MIN: 869.98 / MAX: 1652.27 MIN: 825.61 / MAX: 1673.04 MIN: 789.12 / MAX: 1519.26 MIN: 797.44 / MAX: 1715.9 MIN: 822.35 / MAX: 1656.11
Apache Cassandra Test: Mixed 1:3 OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Mixed 1:3 1 2 3 4 5 20K 40K 60K 80K 100K 97181 105086 112837 96271 111614
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: SqueezeNetV1.0 1 2 3 4 5 3 6 9 12 15 12.28 11.02 11.36 12.68 12.81 MIN: 11.38 / MAX: 19.14 MIN: 10.22 / MAX: 21.7 MIN: 11.04 / MAX: 29.01 MIN: 12.08 / MAX: 18.74 MIN: 11.94 / MAX: 21.8 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: googlenet 1 2 3 4 5 8 16 24 32 40 35.87 30.90 31.94 33.67 31.59 MIN: 28.45 / MAX: 481.26 MIN: 27.29 / MAX: 397.95 MIN: 27.72 / MAX: 426.31 MIN: 27.61 / MAX: 462.78 MIN: 28.02 / MAX: 460.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: blazeface 1 2 3 4 5 0.774 1.548 2.322 3.096 3.87 3.11 3.10 2.97 3.03 3.44 MIN: 2.56 / MAX: 5.4 MIN: 2.87 / MAX: 5.62 MIN: 2.58 / MAX: 3.52 MIN: 2.87 / MAX: 3.67 MIN: 2.52 / MAX: 6.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: resnet-v2-50 1 2 3 4 5 11 22 33 44 55 44.87 50.67 46.24 46.48 46.22 MIN: 41.23 / MAX: 54.09 MIN: 44.15 / MAX: 55.02 MIN: 42.25 / MAX: 53.65 MIN: 43.11 / MAX: 50.9 MIN: 41.32 / MAX: 52.99 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Sequential Fill 1 2 3 4 5 140K 280K 420K 560K 700K 629253 593316 654095 586679 662215 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: yolov4-tiny 1 2 3 4 5 12 24 36 48 60 52.00 47.08 49.51 49.12 48.67 MIN: 40.2 / MAX: 208.8 MIN: 42.27 / MAX: 198.04 MIN: 41.22 / MAX: 202.49 MIN: 42.66 / MAX: 205.45 MIN: 40.87 / MAX: 205.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: MobileNetV2_224 1 2 3 4 5 2 4 6 8 10 7.707 8.046 7.615 7.590 7.292 MIN: 7.59 / MAX: 7.99 MIN: 7.62 / MAX: 8.45 MIN: 7.29 / MAX: 12.92 MIN: 7.48 / MAX: 7.71 MIN: 7.11 / MAX: 7.43 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Apache Cassandra Test: Mixed 1:1 OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Mixed 1:1 1 2 3 4 5 20K 40K 60K 80K 100K 107795 98990 105033 109065 105682
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mnasnet 1 2 3 4 5 3 6 9 12 15 12.19 12.86 11.84 12.29 11.71 MIN: 11.38 / MAX: 68.71 MIN: 10.99 / MAX: 95.85 MIN: 11.45 / MAX: 23.8 MIN: 11.63 / MAX: 72.91 MIN: 11.35 / MAX: 33.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: shufflenet-v2 1 2 3 4 5 4 8 12 16 20 14.00 12.78 13.56 13.81 13.53 MIN: 13.87 / MAX: 19.94 MIN: 12.67 / MAX: 14.53 MIN: 13.3 / MAX: 14.22 MIN: 13.54 / MAX: 53.61 MIN: 13.47 / MAX: 15.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: blazeface 1 2 3 4 5 1.3028 2.6056 3.9084 5.2112 6.514 5.79 5.33 5.58 5.61 5.53 MIN: 5.69 / MAX: 6.07 MIN: 5.25 / MAX: 5.58 MIN: 5.47 / MAX: 5.72 MIN: 5.5 / MAX: 7.92 MIN: 5.45 / MAX: 7.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v3-v3 - Model: mobilenet-v3 1 2 3 4 5 4 8 12 16 20 13.01 13.65 12.74 12.59 13.56 MIN: 12.47 / MAX: 57.66 MIN: 11.77 / MAX: 337.64 MIN: 11.95 / MAX: 65 MIN: 12.09 / MAX: 33.96 MIN: 12 / MAX: 333.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Savina Reactors.IO 1 2 3 4 5 3K 6K 9K 12K 15K 12292.6 12326.5 11693.4 12667.5 11704.2 MIN: 12292.59 / MAX: 18810.77 MAX: 24642.39 MAX: 22224.71 MAX: 18487.31 MAX: 16979.22
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mobilenet 1 2 3 4 5 7 14 21 28 35 29.59 31.08 28.71 28.82 28.75 MIN: 27.53 / MAX: 185.96 MIN: 26.18 / MAX: 458.09 MIN: 27.73 / MAX: 39.91 MIN: 27.42 / MAX: 44.83 MIN: 26.67 / MAX: 185.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: inception-v3 1 2 3 4 5 14 28 42 56 70 59.53 61.55 59.60 59.25 57.16 MIN: 56.78 / MAX: 99.98 MIN: 51.43 / MAX: 102.58 MIN: 55.24 / MAX: 97.8 MIN: 52.71 / MAX: 69.65 MIN: 54.43 / MAX: 135.59 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: regnety_400m 1 2 3 4 5 9 18 27 36 45 38.70 36.84 36.10 36.25 36.55 MIN: 37.97 / MAX: 85.56 MIN: 34.73 / MAX: 162.06 MIN: 35.69 / MAX: 56.2 MIN: 35.89 / MAX: 36.77 MIN: 35.32 / MAX: 206.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark ALS 1 2 3 4 5 500 1000 1500 2000 2500 2359.6 2279.6 2305.2 2202.1 2220.6 MIN: 1999.13 / MAX: 2897.65 MIN: 2114.19 / MAX: 2739.91 MIN: 2098.45 / MAX: 2612.05 MIN: 2007.07 / MAX: 2378.82 MIN: 1994.96 / MAX: 2449.6
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: squeezenet_ssd 1 2 3 4 5 4 8 12 16 20 13.47 13.18 14.09 13.19 13.25 MIN: 11.98 / MAX: 19.27 MIN: 12.01 / MAX: 18.7 MIN: 12.14 / MAX: 19.02 MIN: 12.04 / MAX: 20.01 MIN: 12.14 / MAX: 17.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: efficientnet-b0 1 2 3 4 5 4 8 12 16 20 17.03 16.06 17.12 16.68 16.52 MIN: 16.22 / MAX: 51.28 MIN: 15.75 / MAX: 30.09 MIN: 16.12 / MAX: 152.21 MIN: 16.15 / MAX: 50.41 MIN: 16.25 / MAX: 18.02 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark Bayes 1 2 3 4 5 300 600 900 1200 1500 1209.1 1184.2 1180.9 1162.1 1231.9 MIN: 844.99 / MAX: 1362.04 MIN: 844.46 / MAX: 1454.51 MIN: 838.22 / MAX: 1318.56 MIN: 828.94 / MAX: 1413.63 MIN: 895.93 / MAX: 1323.17
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read While Writing 1 2 3 4 5 800K 1600K 2400K 3200K 4000K 3684442 3795875 3593614 3656007 3634278 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Writes 1 2 3 4 5 30K 60K 90K 120K 150K 137190 130153 131113 131846 130920
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: In-Memory Database Shootout 1 2 3 4 5 1400 2800 4200 5600 7000 6178.5 6439.5 6178.3 6142.0 6457.2 MIN: 5704.5 / MAX: 7336.04 MIN: 6072.23 / MAX: 7632.21 MIN: 5620.9 / MAX: 6868.2 MIN: 5851.56 / MAX: 7455.54 MIN: 5915.55 / MAX: 8134.07
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Finagle HTTP Requests 1 2 3 4 5 900 1800 2700 3600 4500 4099.4 3906.7 4055.7 4040.6 4006.9 MIN: 3762.19 / MAX: 4201.46 MIN: 3579.93 / MAX: 4123.16 MIN: 3691.81 / MAX: 4318.24 MIN: 3751.67 / MAX: 4040.65 MIN: 3646.54 / MAX: 4121.13
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read 1 2 3 4 5 20M 40M 60M 80M 100M 105202520 106197835 107926092 110355654 108371044 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Update Random 1 2 3 4 5 110K 220K 330K 440K 550K 516006 518649 497709 498715 515847 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read Random Write Random 1 2 3 4 5 400K 800K 1200K 1600K 2000K 1929291 2007692 1985772 1986790 1986640 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v2-v2 - Model: mobilenet-v2 1 2 3 4 5 3 6 9 12 15 13.38 13.53 13.02 13.28 13.50 MIN: 13 / MAX: 38.43 MIN: 13.01 / MAX: 42.06 MIN: 12.64 / MAX: 48.95 MIN: 12.8 / MAX: 35.47 MIN: 12.07 / MAX: 135.13 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenet-v1-1.0 1 2 3 4 5 1.1507 2.3014 3.4521 4.6028 5.7535 5.114 4.948 5.109 5.011 4.996 MIN: 4.89 / MAX: 30.05 MIN: 4.79 / MAX: 25.01 MIN: 4.71 / MAX: 29.42 MIN: 4.8 / MAX: 22.32 MIN: 4.88 / MAX: 35.84 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 1 2 3 4 5 2 4 6 8 10 7.35 7.43 7.59 7.39 7.35 MIN: 6.43 / MAX: 9.99 MIN: 6.48 / MAX: 9.01 MIN: 6.31 / MAX: 10.66 MIN: 6.27 / MAX: 9.03 MIN: 6.45 / MAX: 9.02 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Random Forest 1 2 3 4 5 200 400 600 800 1000 920.0 892.7 902.9 911.1 891.3 MIN: 857.45 / MAX: 1097.17 MIN: 815.43 / MAX: 1071.54 MIN: 822.24 / MAX: 1077.32 MIN: 823.41 / MAX: 1100.48 MIN: 822.7 / MAX: 1078.04
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Genetic Algorithm Using Jenetics + Futures 1 2 3 4 5 600 1200 1800 2400 3000 2665.9 2700.4 2679.7 2620.0 2660.0 MIN: 2578.84 / MAX: 2774.18 MIN: 2545.29 / MAX: 2761.15 MIN: 2563.63 / MAX: 2741.28 MIN: 2515.57 / MAX: 2711.91 MIN: 2578.14 / MAX: 2737.39
YafaRay Total Time For Sample Scene OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.5.1 Total Time For Sample Scene 1 2 3 4 5 20 40 60 80 100 96.09 98.40 98.83 98.45 96.47 1. (CXX) g++ options: -std=c++11 -pthread -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Akka Unbalanced Cobwebbed Tree 1 2 3 4 5 5K 10K 15K 20K 25K 21703.7 21813.4 21476.3 22068.2 21886.5 MIN: 17470.92 MIN: 17692.66 MIN: 16811.84 MIN: 17854.31 MIN: 17290.55 / MAX: 21886.51
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 1 2 3 4 5 1.2623 2.5246 3.7869 5.0492 6.3115 5.56 5.60 5.61 5.50 5.46 MIN: 4.93 / MAX: 7.18 MIN: 4.95 / MAX: 7.16 MIN: 4.95 / MAX: 7.34 MIN: 4.94 / MAX: 7.18 MIN: 4.93 / MAX: 6.8 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet18 1 2 3 4 5 2 4 6 8 10 7.05 7.11 6.99 6.92 7.06 MIN: 6.43 / MAX: 8.03 MIN: 6.36 / MAX: 8.36 MIN: 6.38 / MAX: 7.85 MIN: 6.38 / MAX: 7.48 MIN: 6.39 / MAX: 7.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: googlenet 1 2 3 4 5 3 6 9 12 15 11.31 11.34 11.58 11.38 11.28 MIN: 10.2 / MAX: 13.65 MIN: 10.3 / MAX: 12.72 MIN: 10.33 / MAX: 13.46 MIN: 10.43 / MAX: 12.85 MIN: 10.25 / MAX: 12.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: regnety_400m 1 2 3 4 5 3 6 9 12 15 10.19 10.37 10.12 10.34 10.15 MIN: 8.08 / MAX: 13.58 MIN: 8 / MAX: 13.62 MIN: 8.01 / MAX: 14.31 MIN: 8.08 / MAX: 13.86 MIN: 8.04 / MAX: 15.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 1 2 3 4 5 16 32 48 64 80 72.12 72.51 71.38 71.22 72.72 MIN: 71.88 / MAX: 72.89 MIN: 72.19 / MAX: 72.84 MIN: 70.98 / MAX: 72.07 MIN: 70.73 / MAX: 73.6 MIN: 72.49 / MAX: 73.01 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mobilenet 1 2 3 4 5 3 6 9 12 15 13.12 12.92 13.17 12.98 12.97 MIN: 11.31 / MAX: 18.96 MIN: 11.38 / MAX: 15.07 MIN: 11.48 / MAX: 18.65 MIN: 11.47 / MAX: 14.98 MIN: 11.33 / MAX: 18.32 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: ALS Movie Lens 1 2 3 4 5 2K 4K 6K 8K 10K 9836.8 9878.2 10001.3 9814.8 9857.0 MIN: 9836.79 / MAX: 10913.95 MIN: 9878.16 / MAX: 10881.78 MAX: 10664.39 MAX: 10837.56 MAX: 10953.76
C-Blosc Compressor: blosclz OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.0 Compressor: blosclz 1 2 3 4 5 3K 6K 9K 12K 15K 15950.7 15733.0 15895.6 16025.3 15930.8 1. (CC) gcc options: -std=gnu99 -O3 -pthread -lrt -lm
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: efficientnet-b0 1 2 3 4 5 4 8 12 16 20 15.48 15.27 15.26 15.21 15.30 MIN: 13.52 / MAX: 20.06 MIN: 14.21 / MAX: 18.36 MIN: 13.95 / MAX: 21.41 MIN: 14.37 / MAX: 21.09 MIN: 14.03 / MAX: 20.69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 1 2 3 4 5 60 120 180 240 300 256.36 256.49 256.32 256.30 260.29 MIN: 256.1 / MAX: 260.81 MIN: 256.23 / MAX: 256.87 MIN: 256.09 / MAX: 256.97 MIN: 256.1 / MAX: 256.7 MIN: 259.71 / MAX: 261.25 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mnasnet 1 2 3 4 5 1.3298 2.6596 3.9894 5.3192 6.649 5.85 5.83 5.91 5.88 5.86 MIN: 5.13 / MAX: 8.18 MIN: 5.18 / MAX: 8.39 MIN: 5.17 / MAX: 10.71 MIN: 5.16 / MAX: 7.25 MIN: 5.15 / MAX: 7.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: alexnet 1 2 3 4 5 3 6 9 12 15 10.29 10.43 10.39 10.33 10.38 MIN: 9.88 / MAX: 11.31 MIN: 10.1 / MAX: 15.52 MIN: 10.04 / MAX: 12.5 MIN: 10.03 / MAX: 11.3 MIN: 9.96 / MAX: 12.15 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: yolov4-tiny 1 2 3 4 5 5 10 15 20 25 20.00 20.24 20.00 19.98 20.01 MIN: 17.77 / MAX: 21.15 MIN: 17.97 / MAX: 24.64 MIN: 18.08 / MAX: 22.14 MIN: 16.44 / MAX: 21.44 MIN: 18.09 / MAX: 21.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: shufflenet-v2 1 2 3 4 5 1.1228 2.2456 3.3684 4.4912 5.614 4.97 4.97 4.97 4.93 4.99 MIN: 4.45 / MAX: 6.44 MIN: 4.43 / MAX: 7.23 MIN: 4.46 / MAX: 6.42 MIN: 4.41 / MAX: 6.3 MIN: 4.45 / MAX: 6.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet50 1 2 3 4 5 4 8 12 16 20 15.32 15.16 15.32 15.20 15.23 MIN: 14.2 / MAX: 17.18 MIN: 14.32 / MAX: 21.23 MIN: 14.18 / MAX: 17.18 MIN: 14.25 / MAX: 18.36 MIN: 14.32 / MAX: 18.03 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: vgg16 1 2 3 4 5 7 14 21 28 35 28.93 29.10 28.80 29.06 28.90 MIN: 28.31 / MAX: 34.95 MIN: 28.36 / MAX: 31.55 MIN: 28.26 / MAX: 37.6 MIN: 28.36 / MAX: 37.22 MIN: 28.29 / MAX: 32.91 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 1 2 3 4 5 70 140 210 280 350 306.27 305.28 306.19 305.57 304.27 MIN: 286.26 / MAX: 326.58 MIN: 285.8 / MAX: 332.42 MIN: 287.51 / MAX: 329.75 MIN: 292.7 / MAX: 327.33 MIN: 290.3 / MAX: 318.91 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet 1 2 3 4 5 700 1400 2100 2800 3500 3034.70 3023.79 3026.06 3035.01 3035.69 MIN: 2912.24 / MAX: 3124.53 MIN: 2920.77 / MAX: 3156.22 MIN: 2928.6 / MAX: 3128.17 MIN: 2955.47 / MAX: 3126.05 MIN: 2892.85 / MAX: 3147.55 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
GravityMark Resolution: 1920 x 1080 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.2 Resolution: 1920 x 1080 - Renderer: Vulkan 1 2 3 4 5 8 16 24 32 40 33.2 33.2 33.2 33.2 33.2
Phoronix Test Suite v10.8.5