tr 3970x july AMD Ryzen Threadripper 3960X 24-Core testing with a MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) and Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2107314-IB-TR3970XJU60&grr .
tr 3970x july Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution 1 2 3 4 AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads) MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) AMD Starship/Matisse 32GB 1000GB Sabrent Rocket 4.0 1TB Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB (1900/875MHz) AMD Navi 10 HDMI Audio VA2431 Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.12.0-051200rc2daily20210307-generic (x86_64) 20210306 GNOME Shell 3.36.4 X Server 1.20.8 4.6 Mesa 20.0.8 (LLVM 10.0.0) 1.2.128 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: 0x8301025 Java Details - OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04) Python Details - 1: Python 3.8.5 - 2: Python 3.8.5 - 3: Python 3.8.5 - 4: 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: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
tr 3970x july unvanquished: 1920 x 1080 - High cassandra: Reads cassandra: Mixed 1:1 pgbench: 100 - 50 - Read Write - Average Latency pgbench: 100 - 50 - Read Write pgbench: 100 - 1 - Read Write - Average Latency pgbench: 100 - 1 - Read Write qe: AUSURF112 pgbench: 100 - 100 - Read Write - Average Latency pgbench: 100 - 100 - Read Write renaissance: Savina Reactors.IO mnn: inception-v3 mnn: mobilenet-v1-1.0 mnn: MobileNetV2_224 mnn: SqueezeNetV1.0 mnn: resnet-v2-50 mnn: squeezenetv1.1 mnn: mobilenetV3 renaissance: Akka Unbalanced Cobwebbed Tree cassandra: Mixed 1:3 pgbench: 1 - 100 - Read Write - Average Latency pgbench: 1 - 100 - Read Write pgbench: 1 - 50 - Read Write - Average Latency pgbench: 1 - 50 - Read Write renaissance: Scala Dotty ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - mobilenet gravitymark: 1920 x 1080 - Vulkan tnn: CPU - DenseNet renaissance: ALS Movie Lens rocksdb: Rand Fill Sync cassandra: Writes renaissance: Apache Spark PageRank pgbench: 100 - 50 - Read Only - Average Latency pgbench: 100 - 50 - Read Only pgbench: 100 - 1 - Read Only - Average Latency pgbench: 100 - 1 - Read Only pgbench: 100 - 100 - Read Only - Average Latency pgbench: 100 - 100 - Read Only ncnn: CPU - mnasnet rocksdb: Read While Writing pgbench: 1 - 1 - Read Write - Average Latency pgbench: 1 - 1 - Read Write pgbench: 1 - 100 - Read Only - Average Latency pgbench: 1 - 100 - Read Only pgbench: 1 - 1 - Read Only - Average Latency pgbench: 1 - 1 - Read Only pgbench: 1 - 50 - Read Only - Average Latency pgbench: 1 - 50 - Read Only yafaray: Total Time For Sample Scene renaissance: Genetic Algorithm Using Jenetics + Futures ncnn: CPU - regnety_400m ncnn: CPU - squeezenet_ssd ncnn: CPU - yolov4-tiny ncnn: CPU - resnet50 ncnn: CPU - alexnet ncnn: CPU - resnet18 ncnn: CPU - vgg16 ncnn: CPU - googlenet ncnn: CPU - blazeface ncnn: CPU - efficientnet-b0 ncnn: CPU - shufflenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU - mobilenet renaissance: In-Memory Database Shootout renaissance: Apache Spark ALS rocksdb: Rand Fill rocksdb: Update Rand rocksdb: Read Rand Write Rand rocksdb: Rand Read rocksdb: Seq Fill renaissance: Rand Forest renaissance: Apache Spark Bayes blosc: blosclz renaissance: Finagle HTTP Requests natron: Spaceship tnn: CPU - MobileNet v2 tnn: CPU - SqueezeNet v1.1 tnn: CPU - SqueezeNet v2 1 2 3 4 295.6 224288 190556 1.606 31142 0.639 1566 362.99 2.429 41170 8864.5 26.532 3.422 4.854 6.974 23.925 5.689 3.538 13979.1 184918 69.434 1441 31.405 1592 841.9 5.05 9.24 23.43 11.22 28.48 4.6 75.19 7.9 2.49 11.64 5.17 3.94 8.08 5.08 14.08 71.1 2550.47 6679.9 25557 234283 3379.8 0.072 690761 0.033 30530 0.161 621853 4720957 0.628 1593 0.122 817585 0.028 36322 0.053 943798 66.191 1681.7 18.76 19.42 25.77 22.63 9.41 13.42 38.61 16.14 3.23 9.32 7.61 6.67 7.34 16.79 4313.4 1580.7 945053 764095 2815361 138658542 991868 712.9 1036.3 27338.8 2434.4 5.1 260.836 235.446 66.046 207855 186092 4.816 12120 0.943 1146 361.68 8.128 12306 9171.6 28.836 3.460 4.908 7.387 24.224 5.440 3.082 14148.0 182818 69.275 1444 31.387 1593 791.9 5.09 8.77 22.60 11.38 28.47 4.58 75.21 7.91 2.51 11.43 5.17 3.95 8.17 5.10 13.11 71.6 2550.546 6785.2 25568 229336 3530.4 0.073 684138 0.033 31035 0.162 617143 6.60 4766424 0.629 1589 0.125 803899 0.027 36633 0.054 928435 66.216 1726.3 19.30 19.90 26.94 23.80 9.89 14.48 38.14 17.12 3.24 9.38 7.61 6.74 7.30 17.19 4089.3 1555.5 880206 757754 2784955 137227263 984415 709.1 1029.7 26319.6 2455.4 5 259.321 236.092 65.294 230883 195980 5.504 9097 1.073 953 360.53 8.718 11495 9307.6 27.943 3.480 5.021 7.314 24.338 5.629 2.958 14154.5 185410 85.172 1189 36.676 1371 797.4 5.10 8.25 22.85 11.22 28.73 4.57 75.36 7.92 2.47 11.40 5.21 3.98 8.25 5.11 12.89 71.5 2544.610 6794.8 21106 226641 3418.0 0.073 688634 0.033 30473 0.162 617424 6.62 4798497 0.696 1437 0.123 813084 0.027 36510 0.053 940290 65.442 1685.5 19.06 19.76 26.58 23.45 9.46 14.03 38.49 17.04 3.24 9.38 7.61 6.75 7.38 17.16 4161.2 1533.3 875695 758180 2802208 139808155 998792 711.6 1016.0 25800.6 2451.6 5.1 259.921 235.585 65.918 361.01 71.6 25802.0 OpenBenchmarking.org
Unvanquished Resolution: 1920 x 1080 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: High 1 60 120 180 240 300 295.6
Apache Cassandra Test: Reads OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Reads 1 2 3 50K 100K 150K 200K 250K SE +/- 6743.65, N = 12 SE +/- 6536.49, N = 12 224288 207855 230883
Apache Cassandra Test: Mixed 1:1 OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Mixed 1:1 1 2 3 40K 80K 120K 160K 200K SE +/- 1560.41, N = 12 SE +/- 2034.97, N = 12 190556 186092 195980
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency 1 2 3 1.2384 2.4768 3.7152 4.9536 6.192 SE +/- 0.333, N = 15 SE +/- 0.054, N = 15 1.606 4.816 5.504 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write 1 2 3 7K 14K 21K 28K 35K SE +/- 1817.49, N = 15 SE +/- 87.29, N = 15 31142 12120 9097 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average Latency 1 2 3 0.2414 0.4828 0.7242 0.9656 1.207 SE +/- 0.081, N = 12 SE +/- 0.045, N = 15 0.639 0.943 1.073 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 1 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 1 - Mode: Read Write 1 2 3 300 600 900 1200 1500 SE +/- 91.72, N = 12 SE +/- 36.13, N = 15 1566 1146 953 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Quantum ESPRESSO Input: AUSURF112 OpenBenchmarking.org Seconds, Fewer Is Better Quantum ESPRESSO 6.8 Input: AUSURF112 1 2 3 4 80 160 240 320 400 SE +/- 0.38, N = 3 SE +/- 0.51, N = 3 SE +/- 1.10, N = 3 362.99 361.68 360.53 361.01 1. (F9X) gfortran options: -ldevXlib -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency 1 2 3 2 4 6 8 10 SE +/- 0.049, N = 3 SE +/- 0.103, N = 15 2.429 8.128 8.718 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write 1 2 3 9K 18K 27K 36K 45K SE +/- 74.54, N = 3 SE +/- 132.49, N = 15 41170 12306 11495 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Savina Reactors.IO 1 2 3 2K 4K 6K 8K 10K SE +/- 120.92, N = 12 SE +/- 36.95, N = 3 8864.5 9171.6 9307.6 MIN: 8864.48 / MAX: 13425.87 MIN: 8507.95 / MAX: 15517.95 MIN: 9240.12 / MAX: 13609.07
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: inception-v3 1 2 3 7 14 21 28 35 SE +/- 0.17, N = 15 SE +/- 0.47, N = 3 26.53 28.84 27.94 MIN: 26.01 / MAX: 28.29 MIN: 26.98 / MAX: 31.12 MIN: 25.54 / MAX: 29.54 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
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 0.783 1.566 2.349 3.132 3.915 SE +/- 0.012, N = 15 SE +/- 0.044, N = 3 3.422 3.460 3.480 MIN: 3.32 / MAX: 3.84 MIN: 3.33 / MAX: 4.01 MIN: 3.36 / MAX: 3.61 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
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: MobileNetV2_224 1 2 3 1.1297 2.2594 3.3891 4.5188 5.6485 SE +/- 0.027, N = 15 SE +/- 0.050, N = 3 4.854 4.908 5.021 MIN: 4.81 / MAX: 5.02 MIN: 4.68 / MAX: 5.22 MIN: 4.92 / MAX: 5.21 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
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: SqueezeNetV1.0 1 2 3 2 4 6 8 10 SE +/- 0.070, N = 15 SE +/- 0.084, N = 3 6.974 7.387 7.314 MIN: 6.92 / MAX: 7.14 MIN: 6.88 / MAX: 7.93 MIN: 7.02 / MAX: 7.59 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
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 6 12 18 24 30 SE +/- 0.23, N = 15 SE +/- 0.25, N = 3 23.93 24.22 24.34 MIN: 21.61 / MAX: 25.2 MIN: 21.87 / MAX: 26.77 MIN: 21.56 / MAX: 26.46 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
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: squeezenetv1.1 1 2 3 1.28 2.56 3.84 5.12 6.4 SE +/- 0.087, N = 15 SE +/- 0.191, N = 3 5.689 5.440 5.629 MIN: 5.59 / MAX: 5.76 MIN: 4.86 / MAX: 6.04 MIN: 5.25 / MAX: 6.07 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
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenetV3 1 2 3 0.7961 1.5922 2.3883 3.1844 3.9805 SE +/- 0.067, N = 15 SE +/- 0.050, N = 3 3.538 3.082 2.958 MIN: 3.51 / MAX: 3.69 MIN: 2.85 / MAX: 3.69 MIN: 2.83 / MAX: 3.07 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
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Akka Unbalanced Cobwebbed Tree 1 2 3 3K 6K 9K 12K 15K SE +/- 118.05, N = 3 SE +/- 75.72, N = 3 13979.1 14148.0 14154.5 MIN: 11025.28 / MAX: 13979.11 MIN: 11016.39 / MAX: 14308.31 MIN: 11158.7 / MAX: 14288.02
Apache Cassandra Test: Mixed 1:3 OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Mixed 1:3 1 2 3 40K 80K 120K 160K 200K SE +/- 2616.16, N = 4 SE +/- 1816.24, N = 9 184918 182818 185410
PostgreSQL pgbench Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency 1 2 3 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 2.57, N = 15 69.43 69.28 85.17 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 100 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Write 1 2 3 300 600 900 1200 1500 SE +/- 2.60, N = 3 SE +/- 34.48, N = 15 1441 1444 1189 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency 1 2 3 8 16 24 32 40 SE +/- 0.04, N = 3 SE +/- 0.76, N = 15 31.41 31.39 36.68 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 50 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Write 1 2 3 300 600 900 1200 1500 SE +/- 2.20, N = 3 SE +/- 26.27, N = 15 1592 1593 1371 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Scala Dotty 1 2 3 200 400 600 800 1000 SE +/- 12.03, N = 15 SE +/- 12.75, N = 15 841.9 791.9 797.4 MIN: 658.36 / MAX: 1132.87 MIN: 633.97 / MAX: 1178.55 MIN: 637.18 / MAX: 1163.81
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: regnety_400m 1 2 3 1.1475 2.295 3.4425 4.59 5.7375 SE +/- 0.01, N = 12 SE +/- 0.03, N = 3 5.05 5.09 5.10 MIN: 5.01 / MAX: 5.43 MIN: 5.02 / MAX: 15.97 MIN: 5.01 / MAX: 15.82 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: squeezenet_ssd 1 2 3 3 6 9 12 15 SE +/- 0.26, N = 15 SE +/- 0.11, N = 3 9.24 8.77 8.25 MIN: 7.56 / MAX: 19.45 MIN: 7.36 / MAX: 20.4 MIN: 7.54 / MAX: 19.93 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 6 12 18 24 30 SE +/- 0.13, N = 15 SE +/- 0.08, N = 3 23.43 22.60 22.85 MIN: 19.2 / MAX: 35.06 MIN: 18.96 / MAX: 50.47 MIN: 19.29 / MAX: 48.17 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 3 6 9 12 15 SE +/- 0.03, N = 15 SE +/- 0.02, N = 3 11.22 11.38 11.22 MIN: 10.77 / MAX: 15.9 MIN: 10.7 / MAX: 38.16 MIN: 10.77 / MAX: 24.72 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 7 14 21 28 35 SE +/- 0.07, N = 15 SE +/- 0.03, N = 3 28.48 28.47 28.73 MIN: 25.89 / MAX: 56.02 MIN: 25.65 / MAX: 59.24 MIN: 25.85 / MAX: 59.99 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 1.035 2.07 3.105 4.14 5.175 SE +/- 0.01, N = 15 SE +/- 0.01, N = 3 4.60 4.58 4.57 MIN: 4.47 / MAX: 8.12 MIN: 4.48 / MAX: 13.13 MIN: 4.47 / MAX: 9.26 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 20 40 60 80 100 SE +/- 0.07, N = 15 SE +/- 0.13, N = 3 75.19 75.21 75.36 MIN: 70.75 / MAX: 99.18 MIN: 70.37 / MAX: 104.78 MIN: 70.85 / MAX: 99.79 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 2 4 6 8 10 SE +/- 0.03, N = 15 SE +/- 0.05, N = 3 7.90 7.91 7.92 MIN: 7.66 / MAX: 12.7 MIN: 7.63 / MAX: 28.47 MIN: 7.66 / MAX: 22.47 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 0.5648 1.1296 1.6944 2.2592 2.824 SE +/- 0.02, N = 15 SE +/- 0.01, N = 3 2.49 2.51 2.47 MIN: 2.45 / MAX: 3.09 MIN: 2.44 / MAX: 5.94 MIN: 2.44 / MAX: 2.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: efficientnet-b0 1 2 3 3 6 9 12 15 SE +/- 0.04, N = 15 SE +/- 0.04, N = 3 11.64 11.43 11.40 MIN: 10.69 / MAX: 33.64 MIN: 10.71 / MAX: 32.96 MIN: 10.73 / MAX: 32.91 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mnasnet 1 2 3 1.1723 2.3446 3.5169 4.6892 5.8615 SE +/- 0.00, N = 14 SE +/- 0.03, N = 3 5.17 5.17 5.21 MIN: 5.02 / MAX: 5.44 MIN: 5 / MAX: 5.81 MIN: 5.01 / MAX: 20.2 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 0.8955 1.791 2.6865 3.582 4.4775 SE +/- 0.01, N = 15 SE +/- 0.03, N = 3 3.94 3.95 3.98 MIN: 3.87 / MAX: 4.28 MIN: 3.86 / MAX: 5.07 MIN: 3.86 / MAX: 15.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
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 2 4 6 8 10 SE +/- 0.02, N = 15 SE +/- 0.09, N = 3 8.08 8.17 8.25 MIN: 7.75 / MAX: 8.34 MIN: 7.69 / MAX: 29.16 MIN: 7.74 / MAX: 24.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
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 1.1498 2.2996 3.4494 4.5992 5.749 SE +/- 0.01, N = 15 SE +/- 0.03, N = 3 5.08 5.10 5.11 MIN: 4.9 / MAX: 5.51 MIN: 4.87 / MAX: 22.63 MIN: 4.89 / MAX: 16.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mobilenet 1 2 3 4 8 12 16 20 SE +/- 0.11, N = 15 SE +/- 0.12, N = 3 14.08 13.11 12.89 MIN: 10.52 / MAX: 28.28 MIN: 9.77 / MAX: 36 MIN: 9.93 / MAX: 23.54 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
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 16 32 48 64 80 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 71.1 71.6 71.5 71.6
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet 1 2 3 500 1000 1500 2000 2500 SE +/- 4.36, N = 3 SE +/- 0.45, N = 3 2550.47 2550.55 2544.61 MIN: 2517.62 / MAX: 2586.38 MIN: 2473.98 / MAX: 2596.7 MIN: 2504.79 / MAX: 2585.11 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: ALS Movie Lens 1 2 3 1500 3000 4500 6000 7500 SE +/- 43.81, N = 3 SE +/- 94.62, N = 3 6679.9 6785.2 6794.8 MIN: 6679.04 / MAX: 7166.09 MIN: 6735.48 / MAX: 7349.09 MIN: 6606.43 / MAX: 7204.36
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 5K 10K 15K 20K 25K SE +/- 32.08, N = 3 SE +/- 1696.77, N = 12 25557 25568 21106 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 50K 100K 150K 200K 250K SE +/- 2314.84, N = 3 SE +/- 2210.58, N = 3 234283 229336 226641
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark PageRank 1 2 3 800 1600 2400 3200 4000 SE +/- 40.90, N = 3 SE +/- 24.47, N = 3 3379.8 3530.4 3418.0 MIN: 3143.08 / MAX: 3492.6 MIN: 3216.94 / MAX: 3727.47 MIN: 3099.91 / MAX: 3479.07
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency 1 2 3 0.0164 0.0328 0.0492 0.0656 0.082 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.072 0.073 0.073 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only 1 2 3 150K 300K 450K 600K 750K SE +/- 1352.75, N = 3 SE +/- 3202.49, N = 3 690761 684138 688634 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average Latency 1 2 3 0.0074 0.0148 0.0222 0.0296 0.037 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.033 0.033 0.033 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 1 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 1 - Mode: Read Only 1 2 3 7K 14K 21K 28K 35K SE +/- 317.30, N = 3 SE +/- 74.95, N = 3 30530 31035 30473 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency 1 2 3 0.0365 0.073 0.1095 0.146 0.1825 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.161 0.162 0.162 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only 1 2 3 130K 260K 390K 520K 650K SE +/- 1719.24, N = 3 SE +/- 640.10, N = 3 621853 617143 617424 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mnasnet 2 3 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 6.60 6.62 MIN: 6.43 / MAX: 7.35 MIN: 6.31 / MAX: 7.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
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 1000K 2000K 3000K 4000K 5000K SE +/- 49320.63, N = 8 SE +/- 70915.08, N = 3 4720957 4766424 4798497 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
PostgreSQL pgbench Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latency 1 2 3 0.1566 0.3132 0.4698 0.6264 0.783 SE +/- 0.001, N = 3 SE +/- 0.008, N = 3 0.628 0.629 0.696 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 1 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 1 - Mode: Read Write 1 2 3 300 600 900 1200 1500 SE +/- 3.23, N = 3 SE +/- 16.63, N = 3 1593 1589 1437 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency 1 2 3 0.0281 0.0562 0.0843 0.1124 0.1405 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 0.122 0.125 0.123 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 100 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Only 1 2 3 200K 400K 600K 800K 1000K SE +/- 2009.26, N = 3 SE +/- 3408.71, N = 3 817585 803899 813084 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average Latency 1 2 3 0.0063 0.0126 0.0189 0.0252 0.0315 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.028 0.027 0.027 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 1 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 1 - Mode: Read Only 1 2 3 8K 16K 24K 32K 40K SE +/- 310.79, N = 3 SE +/- 321.06, N = 3 36322 36633 36510 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency 1 2 3 0.0122 0.0244 0.0366 0.0488 0.061 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.053 0.054 0.053 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 50 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Only 1 2 3 200K 400K 600K 800K 1000K SE +/- 8132.24, N = 3 SE +/- 2718.51, N = 3 943798 928435 940290 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
YafaRay Total Time For Sample Scene OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.5.1 Total Time For Sample Scene 1 2 3 15 30 45 60 75 SE +/- 0.88, N = 5 SE +/- 0.95, N = 4 66.19 66.22 65.44 1. (CXX) g++ options: -std=c++11 -pthread -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Genetic Algorithm Using Jenetics + Futures 1 2 3 400 800 1200 1600 2000 SE +/- 26.29, N = 3 SE +/- 5.20, N = 3 1681.7 1726.3 1685.5 MIN: 1620.58 / MAX: 1751.35 MIN: 1551.64 / MAX: 1865.95 MIN: 1576.44 / MAX: 1744.32
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: regnety_400m 1 2 3 5 10 15 20 25 SE +/- 0.12, N = 3 SE +/- 0.25, N = 3 18.76 19.30 19.06 MIN: 18.63 / MAX: 19.48 MIN: 18.44 / MAX: 20.59 MIN: 18.22 / MAX: 20.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: squeezenet_ssd 1 2 3 5 10 15 20 25 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 19.42 19.90 19.76 MIN: 19.18 / MAX: 20.2 MIN: 19.52 / MAX: 22.73 MIN: 19.44 / MAX: 22.38 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: yolov4-tiny 1 2 3 6 12 18 24 30 SE +/- 0.09, N = 3 SE +/- 0.16, N = 3 25.77 26.94 26.58 MIN: 25.6 / MAX: 30.39 MIN: 26.58 / MAX: 30.94 MIN: 26.08 / MAX: 31.47 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 6 12 18 24 30 SE +/- 0.15, N = 3 SE +/- 0.19, N = 3 22.63 23.80 23.45 MIN: 22.48 / MAX: 23.83 MIN: 23.28 / MAX: 25.56 MIN: 22.96 / MAX: 34.54 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: alexnet 1 2 3 3 6 9 12 15 SE +/- 0.22, N = 3 SE +/- 0.04, N = 3 9.41 9.89 9.46 MIN: 9.29 / MAX: 13.08 MIN: 9.52 / MAX: 19.47 MIN: 9.27 / MAX: 13.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet18 1 2 3 4 8 12 16 20 SE +/- 0.16, N = 3 SE +/- 0.16, N = 3 13.42 14.48 14.03 MIN: 13.26 / MAX: 23.59 MIN: 14 / MAX: 15.52 MIN: 13.55 / MAX: 17.45 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: vgg16 1 2 3 9 18 27 36 45 SE +/- 0.25, N = 3 SE +/- 0.24, N = 3 38.61 38.14 38.49 MIN: 37.92 / MAX: 42.08 MIN: 37.52 / MAX: 48.37 MIN: 37.85 / MAX: 48.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: googlenet 1 2 3 4 8 12 16 20 SE +/- 0.21, N = 3 SE +/- 0.25, N = 3 16.14 17.12 17.04 MIN: 15.89 / MAX: 18.84 MIN: 16.4 / MAX: 18.58 MIN: 16.38 / MAX: 19.27 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 0.729 1.458 2.187 2.916 3.645 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 3.23 3.24 3.24 MIN: 3.15 / MAX: 3.86 MIN: 3.12 / MAX: 4.56 MIN: 3.1 / MAX: 3.9 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 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 9.32 9.38 9.38 MIN: 9.25 / MAX: 9.96 MIN: 9.17 / MAX: 11.89 MIN: 9.22 / MAX: 10.59 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 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 7.61 7.61 7.61 MIN: 7.37 / MAX: 8.66 MIN: 7.3 / MAX: 8.35 MIN: 7.29 / MAX: 8.67 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 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 6.67 6.74 6.75 MIN: 6.55 / MAX: 7.43 MIN: 6.43 / MAX: 18.18 MIN: 6.52 / MAX: 7.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
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 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 7.34 7.30 7.38 MIN: 7.05 / MAX: 7.96 MIN: 6.94 / MAX: 8.52 MIN: 7.12 / MAX: 11.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mobilenet 1 2 3 4 8 12 16 20 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 16.79 17.19 17.16 MIN: 16.6 / MAX: 17.56 MIN: 16.8 / MAX: 18.65 MIN: 16.87 / MAX: 17.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: In-Memory Database Shootout 1 2 3 900 1800 2700 3600 4500 SE +/- 60.18, N = 3 SE +/- 43.29, N = 3 4313.4 4089.3 4161.2 MIN: 3994.18 / MAX: 5060.28 MIN: 3698.76 / MAX: 4582.21 MIN: 3720.55 / MAX: 4919.46
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark ALS 1 2 3 300 600 900 1200 1500 SE +/- 13.20, N = 3 SE +/- 19.28, N = 4 1580.7 1555.5 1533.3 MIN: 1485.71 / MAX: 1663.51 MIN: 1434.41 / MAX: 1734.21 MIN: 1376.97 / MAX: 1746.07
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill 1 2 3 200K 400K 600K 800K 1000K SE +/- 4989.19, N = 3 SE +/- 5726.69, N = 3 945053 880206 875695 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 160K 320K 480K 640K 800K SE +/- 5284.99, N = 3 SE +/- 2429.28, N = 3 764095 757754 758180 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 600K 1200K 1800K 2400K 3000K SE +/- 5858.77, N = 3 SE +/- 7766.59, N = 3 2815361 2784955 2802208 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read 1 2 3 30M 60M 90M 120M 150M SE +/- 1671441.20, N = 3 SE +/- 454135.98, N = 3 138658542 137227263 139808155 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Sequential Fill 1 2 3 200K 400K 600K 800K 1000K SE +/- 11133.01, N = 3 SE +/- 7278.03, N = 3 991868 984415 998792 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Random Forest 1 2 3 150 300 450 600 750 SE +/- 3.23, N = 3 SE +/- 2.33, N = 3 712.9 709.1 711.6 MIN: 669.44 / MAX: 815.76 MIN: 659.19 / MAX: 841.74 MIN: 665.95 / MAX: 824.78
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark Bayes 1 2 3 200 400 600 800 1000 SE +/- 3.06, N = 3 SE +/- 2.71, N = 3 1036.3 1029.7 1016.0 MIN: 767.35 / MAX: 1036.35 MIN: 758.83 / MAX: 1034.69 MIN: 745.98 / MAX: 1019.92
C-Blosc Compressor: blosclz OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.0 Compressor: blosclz 1 2 3 4 6K 12K 18K 24K 30K SE +/- 222.52, N = 3 SE +/- 138.53, N = 3 SE +/- 268.15, N = 3 27338.8 26319.6 25800.6 25802.0 1. (CC) gcc options: -std=gnu99 -O3 -pthread -lrt -lm
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Finagle HTTP Requests 1 2 3 500 1000 1500 2000 2500 SE +/- 9.69, N = 3 SE +/- 12.15, N = 3 2434.4 2455.4 2451.6 MIN: 2261.23 / MAX: 2528.66 MIN: 2283.18 / MAX: 2613.86 MIN: 2258.6 / MAX: 2584.88
Natron Input: Spaceship OpenBenchmarking.org FPS, More Is Better Natron 2.4 Input: Spaceship 1 2 3 1.1475 2.295 3.4425 4.59 5.7375 SE +/- 0.06, N = 3 5.1 5.0 5.1
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 1 2 3 60 120 180 240 300 SE +/- 0.95, N = 3 SE +/- 0.36, N = 3 260.84 259.32 259.92 MIN: 257.26 / MAX: 271.47 MIN: 252.06 / MAX: 272.27 MIN: 255.74 / MAX: 290.91 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
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 50 100 150 200 250 SE +/- 2.38, N = 3 SE +/- 0.56, N = 3 235.45 236.09 235.59 MIN: 234.47 / MAX: 238.08 MIN: 229.68 / MAX: 275.56 MIN: 233.3 / MAX: 238.08 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 1 2 3 15 30 45 60 75 SE +/- 0.70, N = 3 SE +/- 0.54, N = 3 66.05 65.29 65.92 MIN: 65.2 / MAX: 66.76 MIN: 63.44 / MAX: 79.18 MIN: 64.36 / MAX: 68.06 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
Phoronix Test Suite v10.8.4