res.txt

2 x Intel Xeon Gold 6244 testing with a Dell 060K5C (2.4.1 BIOS) and NVIDIA Quadro GV100 32GB on Ubuntu 20.04.6 LTS via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2402069-NE-RESTXT08482&sor&grw.

res.txtProcessorMotherboardMemoryDiskGraphicsOSKernelDisplay DriverVulkanCompilerFile-SystemScreen Resolution2024-02-05 13:532024-02-05 13:582024-02-05 18:032024-02-05 18:362024-02-06 08:562 x Intel Xeon Gold 6244 @ 4.40GHz (16 Cores / 32 Threads)Dell 060K5C (2.4.1 BIOS)128GBPM981a NVMe SAMSUNG 2048GB + 4 x 8002GB TOSHIBA MG06ACA8NVIDIA Quadro GV100 32GBUbuntu 20.04.6 LTS3.10.0-1160.95.1.el7.x86_64 (x86_64)NVIDIA1.1.182GCC 9.4.0 + CUDA 12.0xfs800x600OpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler 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-9-9QDOt0/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- 2024-02-05 13:53: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x5003604- 2024-02-05 13:58: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x5003604- 2024-02-05 18:03: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x5003604- 2024-02-05 18:36: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x5003604- 2024-02-06 08:56: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x5003604Python Details- Python 3.8.10

res.txtplaidml: No - Training - ResNet 50 - CPUplaidml: No - Inference - ResNet 50 - CPUncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDet2024-02-05 13:532024-02-05 13:582024-02-05 18:032024-02-05 18:362024-02-06 08:5616.927.186.727.386.418.472.9116.2143.209.986.8018.4630.8915.3421.4267.778.2716.737.066.677.526.468.693.0116.6843.3510.016.6518.1531.5415.4621.4768.488.1629.71373.65459.15181.58131.208.532.83120.62594.96104.1474.461279.57254.601029.9525.331647.771112.16181.7684.6381.537.296.358.462.9416.22501.679.856.83565.39421.96244.36112.441263.09654.730.375.0317.137.036.577.226.388.373.0219.8178.549.956.7217.9842.9716.0120.7287.128.0918.166.986.537.216.288.212.9916.0885.169.696.6418.0338.8014.9320.7184.987.32OpenBenchmarking.org

PlaidML

FP16: No - Mode: Training - Network: ResNet 50 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Training - Network: ResNet 50 - Device: CPU2024-02-06 08:560.08330.16660.24990.33320.4165SE +/- 0.00, N = 30.37

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU2024-02-06 08:561.13182.26363.39544.52725.659SE +/- 0.02, N = 35.03

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenet2024-02-05 13:582024-02-06 08:562024-02-05 18:36714212835SE +/- 0.30, N = 15SE +/- 0.29, N = 11SE +/- 12.39, N = 916.9217.1329.71MIN: 13.75 / MAX: 53.31MIN: 14.45 / MAX: 20.43MIN: 15.53 / MAX: 1342.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v22024-02-06 08:562024-02-05 13:582024-02-05 18:3680160240320400SE +/- 0.05, N = 11SE +/- 0.12, N = 15SE +/- 175.05, N = 97.037.18373.65MIN: 5.54 / MAX: 11671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v32024-02-06 08:562024-02-05 13:582024-02-05 18:36100200300400500SE +/- 0.04, N = 11SE +/- 0.08, N = 15SE +/- 224.10, N = 96.576.72459.15MIN: 5.6 / MAX: 1369.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v22024-02-06 08:562024-02-05 13:582024-02-05 18:364080120160200SE +/- 0.03, N = 11SE +/- 0.04, N = 15SE +/- 174.29, N = 97.227.38181.58MIN: 6.15 / MAX: 1598.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnet2024-02-06 08:562024-02-05 13:582024-02-05 18:36306090120150SE +/- 0.10, N = 11SE +/- 0.09, N = 15SE +/- 124.99, N = 96.386.41131.20MIN: 4.8 / MAX: 1145.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b02024-02-06 08:562024-02-05 13:582024-02-05 18:36246810SE +/- 0.07, N = 11SE +/- 0.10, N = 15SE +/- 0.14, N = 98.378.478.53MIN: 8.01 / MAX: 11.4MIN: 7.07 / MAX: 42.9MIN: 7.16 / MAX: 13.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazeface2024-02-05 18:362024-02-05 13:582024-02-06 08:560.67951.3592.03852.7183.3975SE +/- 0.12, N = 9SE +/- 0.08, N = 15SE +/- 0.02, N = 112.832.913.02MIN: 2.13 / MAX: 5.08MIN: 2.16 / MAX: 5.98MIN: 2.84 / MAX: 22.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenet2024-02-05 13:582024-02-06 08:562024-02-05 18:36306090120150SE +/- 0.28, N = 15SE +/- 3.51, N = 11SE +/- 104.57, N = 916.2119.81120.62MIN: 12.89 / MAX: 38.38MIN: 15.64 / MAX: 1809.29MIN: 13.63 / MAX: 1852.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg162024-02-05 13:582024-02-06 08:562024-02-05 18:36130260390520650SE +/- 0.31, N = 15SE +/- 4.72, N = 11SE +/- 34.48, N = 943.2078.54594.96MIN: 39.02 / MAX: 663.86MIN: 39.51 / MAX: 679.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet182024-02-06 08:562024-02-05 13:582024-02-05 18:3620406080100SE +/- 0.14, N = 11SE +/- 0.16, N = 15SE +/- 94.16, N = 99.959.98104.14MIN: 9.3 / MAX: 13.2MIN: 8.07 / MAX: 48.75MIN: 8.47 / MAX: 867.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnet2024-02-06 08:562024-02-05 13:582024-02-05 18:3620406080100SE +/- 0.05, N = 11SE +/- 0.08, N = 15SE +/- 46.29, N = 96.726.8074.46MIN: 6.37 / MAX: 397.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet502024-02-06 08:562024-02-05 13:582024-02-05 18:3630060090012001500SE +/- 0.20, N = 11SE +/- 0.18, N = 15SE +/- 237.42, N = 917.9818.461279.57MIN: 17.05 / MAX: 1680.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tiny2024-02-05 13:582024-02-06 08:562024-02-05 18:3660120180240300SE +/- 0.37, N = 15SE +/- 5.42, N = 11SE +/- 110.09, N = 930.8942.97254.60MIN: 25.55 / MAX: 393.68MIN: 25.46 / MAX: 767.17MIN: 26.15 / MAX: 793.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssd2024-02-05 13:582024-02-06 08:562024-02-05 18:362004006008001000SE +/- 0.25, N = 15SE +/- 0.62, N = 11SE +/- 320.29, N = 915.3416.011029.95MIN: 13 / MAX: 1860.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400m2024-02-06 08:562024-02-05 13:582024-02-05 18:36612182430SE +/- 0.08, N = 11SE +/- 0.17, N = 15SE +/- 4.36, N = 920.7221.4225.33MIN: 20.11 / MAX: 89.15MIN: 18.61 / MAX: 50.31MIN: 18.49 / MAX: 8765.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformer2024-02-05 13:582024-02-06 08:562024-02-05 18:36400800120016002000SE +/- 0.47, N = 15SE +/- 7.53, N = 11SE +/- 36.79, N = 967.7787.121647.77MIN: 60.22 / MAX: 1773.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDet2024-02-06 08:562024-02-05 13:582024-02-05 18:362004006008001000SE +/- 0.36, N = 11SE +/- 0.33, N = 15SE +/- 194.42, N = 98.098.271112.16MIN: 5.89 / MAX: 1712.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenet2024-02-05 13:582024-02-06 08:562024-02-05 18:364080120160200SE +/- 0.31, N = 15SE +/- 1.91, N = 9SE +/- 164.65, N = 816.7318.16181.76MIN: 14.72 / MAX: 1345.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v22024-02-06 08:562024-02-05 13:582024-02-05 18:3620406080100SE +/- 0.02, N = 9SE +/- 0.08, N = 15SE +/- 77.74, N = 86.987.0684.63MIN: 5.23 / MAX: 1181.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v32024-02-06 08:562024-02-05 13:582024-02-05 18:3620406080100SE +/- 0.03, N = 9SE +/- 0.05, N = 15SE +/- 74.95, N = 86.536.6781.53MIN: 5.52 / MAX: 1367.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v22024-02-06 08:562024-02-05 18:362024-02-05 13:58246810SE +/- 0.03, N = 9SE +/- 0.11, N = 8SE +/- 0.06, N = 157.217.297.52MIN: 6.9 / MAX: 9.44MIN: 6.09 / MAX: 9.72MIN: 6.49 / MAX: 70.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnet2024-02-06 08:562024-02-05 18:362024-02-05 13:58246810SE +/- 0.03, N = 9SE +/- 0.16, N = 8SE +/- 0.06, N = 156.286.356.46MIN: 6.07 / MAX: 8.66MIN: 5.01 / MAX: 10.28MIN: 5.63 / MAX: 121.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b02024-02-06 08:562024-02-05 18:362024-02-05 13:58246810SE +/- 0.03, N = 9SE +/- 0.18, N = 8SE +/- 0.12, N = 158.218.468.69MIN: 7.9 / MAX: 14.11MIN: 7.17 / MAX: 12.2MIN: 7.5 / MAX: 90.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazeface2024-02-05 18:362024-02-06 08:562024-02-05 13:580.67731.35462.03192.70923.3865SE +/- 0.10, N = 8SE +/- 0.01, N = 9SE +/- 0.04, N = 152.942.993.01MIN: 2.2 / MAX: 5.14MIN: 2.86 / MAX: 5.34MIN: 2.56 / MAX: 5.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenet2024-02-06 08:562024-02-05 18:362024-02-05 13:5848121620SE +/- 0.06, N = 9SE +/- 0.28, N = 8SE +/- 0.13, N = 1516.0816.2216.68MIN: 15.44 / MAX: 19.02MIN: 13.66 / MAX: 19.49MIN: 14.68 / MAX: 41.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg162024-02-05 13:582024-02-06 08:562024-02-05 18:36110220330440550SE +/- 0.55, N = 15SE +/- 8.40, N = 9SE +/- 94.33, N = 843.3585.16501.67MIN: 38.78 / MAX: 657.39MIN: 38.99 / MAX: 680.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet182024-02-06 08:562024-02-05 18:362024-02-05 13:583691215SE +/- 0.04, N = 9SE +/- 0.18, N = 8SE +/- 0.11, N = 159.699.8510.01MIN: 9.24 / MAX: 12.4MIN: 8.54 / MAX: 12.61MIN: 8.29 / MAX: 66.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnet2024-02-06 08:562024-02-05 13:582024-02-05 18:36246810SE +/- 0.02, N = 8SE +/- 0.05, N = 15SE +/- 0.05, N = 86.646.656.83MIN: 6.38 / MAX: 44.69MIN: 5.83 / MAX: 17.95MIN: 6.38 / MAX: 9.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet502024-02-06 08:562024-02-05 13:582024-02-05 18:36120240360480600SE +/- 0.37, N = 9SE +/- 0.16, N = 15SE +/- 236.61, N = 818.0318.15565.39MIN: 16.76 / MAX: 1675.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tiny2024-02-05 13:582024-02-06 08:562024-02-05 18:3690180270360450SE +/- 0.99, N = 15SE +/- 3.53, N = 9SE +/- 120.86, N = 831.5438.80421.96MIN: 26.32 / MAX: 796.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssd2024-02-06 08:562024-02-05 13:582024-02-05 18:3650100150200250SE +/- 0.41, N = 9SE +/- 0.25, N = 15SE +/- 228.09, N = 814.9315.46244.36MIN: 13.25 / MAX: 1854.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400m2024-02-06 08:562024-02-05 13:582024-02-05 18:36306090120150SE +/- 0.04, N = 9SE +/- 0.21, N = 15SE +/- 91.36, N = 820.7121.47112.44MIN: 20.11 / MAX: 57.59MIN: 18.78 / MAX: 94.51MIN: 18.72 / MAX: 8799.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformer2024-02-05 13:582024-02-06 08:562024-02-05 18:3630060090012001500SE +/- 0.79, N = 15SE +/- 7.30, N = 9SE +/- 261.92, N = 868.4884.981263.09MIN: 59.44 / MAX: 1769.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDet2024-02-06 08:562024-02-05 13:582024-02-05 18:36140280420560700SE +/- 0.31, N = 9SE +/- 0.29, N = 15SE +/- 284.19, N = 87.328.16654.73MIN: 5.88 / MAX: 1709.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

Phoronix Test Suite v10.8.5