nn

AMD Ryzen Threadripper PRO 5965WX 24-Cores testing with a ASUS Pro WS WRX80E-SAGE SE WIFI (1003 BIOS) and ASUS NVIDIA NV106 2GB on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2208137-NE-NN282134066&grr&sor.

nnProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionabcAMD Ryzen Threadripper PRO 5965WX 24-Cores @ 3.80GHz (24 Cores / 48 Threads)ASUS Pro WS WRX80E-SAGE SE WIFI (1003 BIOS)AMD Starship/Matisse128GB1000GB Western Digital WDS100T1X0E-00AFY0ASUS NVIDIA NV106 2GBAMD Starship/MatisseVA24312 x Intel 10G X550T + Intel Wi-Fi 6 AX200Ubuntu 22.045.19.0-051900daily20220809-generic (x86_64)GNOME Shell 42.2X Server 1.21.1.3 + Waylandnouveau4.3 Mesa 22.0.11.2.204GCC 11.2.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 schedutil (Boost: Enabled) - CPU Microcode: 0xa008203Security 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 + srbds: Not affected + tsx_async_abort: Not affected

nnmnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: squeezenetv1.1mnn: mobilenetV3ncnn: CPU - FastestDetncnn: CPU - vision_transformerncnn: CPU - regnety_400mncnn: CPU - squeezenet_ssdncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetabc22.1342.7003.8205.94618.4333.6482.2578.76110.2623.8415.5119.4917.105.969.2523.2814.163.098.285.697.255.696.1713.1222.3992.7203.9015.98318.8153.7892.2818.59110.2722.4615.2419.1616.815.899.1323.2513.842.997.985.467.045.455.9412.9319.8542.7293.5455.65817.1153.2912.0388.43110.2722.2615.2318.9916.725.989.1123.3213.82.967.95.466.965.425.9112.84OpenBenchmarking.org

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: inception-v3cab510152025SE +/- 0.25, N = 15SE +/- 0.30, N = 1519.8522.1322.40MIN: 19.7 / MAX: 21.4MIN: 20.33 / MAX: 24.82MIN: 20.02 / MAX: 25.261. (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.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenet-v1-1.0abc0.6141.2281.8422.4563.07SE +/- 0.019, N = 15SE +/- 0.019, N = 152.7002.7202.729MIN: 2.59 / MAX: 3.54MIN: 2.57 / MAX: 4.14MIN: 2.7 / MAX: 3.561. (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.orgms, Fewer Is BetterMobile Neural Network 2.0Model: MobileNetV2_224cab0.87771.75542.63313.51084.3885SE +/- 0.034, N = 15SE +/- 0.047, N = 153.5453.8203.901MIN: 3.51 / MAX: 4.49MIN: 3.54 / MAX: 5.26MIN: 3.55 / MAX: 5.31. (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.orgms, Fewer Is BetterMobile Neural Network 2.0Model: SqueezeNetV1.0cab1.34622.69244.03865.38486.731SE +/- 0.055, N = 15SE +/- 0.052, N = 155.6585.9465.983MIN: 5.59 / MAX: 7.09MIN: 5.24 / MAX: 7.59MIN: 5.55 / MAX: 7.351. (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.orgms, Fewer Is BetterMobile Neural Network 2.0Model: resnet-v2-50cab510152025SE +/- 0.26, N = 15SE +/- 0.25, N = 1517.1218.4318.82MIN: 16.97 / MAX: 18.67MIN: 17.17 / MAX: 21.39MIN: 17.52 / MAX: 21.681. (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.orgms, Fewer Is BetterMobile Neural Network 2.0Model: squeezenetv1.1cab0.85251.7052.55753.414.2625SE +/- 0.056, N = 15SE +/- 0.046, N = 153.2913.6483.789MIN: 3.26 / MAX: 4.16MIN: 3.33 / MAX: 5.24MIN: 3.38 / MAX: 4.921. (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.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3cab0.51321.02641.53962.05282.566SE +/- 0.029, N = 15SE +/- 0.026, N = 152.0382.2572.281MIN: 2.01 / MAX: 3.61MIN: 2.09 / MAX: 3.98MIN: 2.06 / MAX: 3.831. (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: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetcba246810SE +/- 0.14, N = 3SE +/- 0.04, N = 38.438.598.76MIN: 8.35 / MAX: 10.14MIN: 8.26 / MAX: 10.5MIN: 8.6 / MAX: 10.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerabc20406080100SE +/- 0.01, N = 3SE +/- 0.01, N = 3110.26110.27110.27MIN: 109.56 / MAX: 114.27MIN: 109.69 / MAX: 117.06MIN: 109.27 / MAX: 117.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mcba612182430SE +/- 0.29, N = 3SE +/- 0.13, N = 322.2622.4623.84MIN: 21.92 / MAX: 24.69MIN: 21.61 / MAX: 28.98MIN: 23.38 / MAX: 26.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdcba48121620SE +/- 0.09, N = 3SE +/- 0.04, N = 315.2315.2415.51MIN: 14.9 / MAX: 23.96MIN: 14.8 / MAX: 18.11MIN: 15.09 / MAX: 18.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinycba510152025SE +/- 0.21, N = 3SE +/- 0.17, N = 318.9919.1619.49MIN: 18.66 / MAX: 20.52MIN: 18.61 / MAX: 28.33MIN: 18.87 / MAX: 21.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50cba48121620SE +/- 0.04, N = 3SE +/- 0.04, N = 316.7216.8117.10MIN: 16.54 / MAX: 22.07MIN: 16.47 / MAX: 21.24MIN: 16.78 / MAX: 21.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetbac1.34552.6914.03655.3826.7275SE +/- 0.04, N = 3SE +/- 0.07, N = 35.895.965.98MIN: 5.69 / MAX: 9.06MIN: 5.71 / MAX: 9.01MIN: 5.7 / MAX: 8.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18cba3691215SE +/- 0.03, N = 3SE +/- 0.01, N = 39.119.139.25MIN: 8.93 / MAX: 13.05MIN: 8.93 / MAX: 13.18MIN: 9.06 / MAX: 12.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16bac612182430SE +/- 0.04, N = 3SE +/- 0.04, N = 323.2523.2823.32MIN: 22.64 / MAX: 33.92MIN: 22.77 / MAX: 28.58MIN: 22.65 / MAX: 281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetcba48121620SE +/- 0.09, N = 3SE +/- 0.04, N = 313.8013.8414.16MIN: 13.66 / MAX: 15.75MIN: 13.5 / MAX: 17.24MIN: 13.93 / MAX: 19.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefacecba0.69531.39062.08592.78123.4765SE +/- 0.03, N = 3SE +/- 0.01, N = 32.962.993.09MIN: 2.92 / MAX: 3.42MIN: 2.89 / MAX: 3.67MIN: 3.02 / MAX: 5.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0cba246810SE +/- 0.07, N = 3SE +/- 0.03, N = 37.907.988.28MIN: 7.84 / MAX: 9.08MIN: 7.78 / MAX: 9.57MIN: 8.13 / MAX: 13.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetbca1.28032.56063.84095.12126.4015SE +/- 0.07, N = 2SE +/- 0.01, N = 25.465.465.69MIN: 5.33 / MAX: 7.09MIN: 5.39 / MAX: 7.02MIN: 5.59 / MAX: 9.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2cba246810SE +/- 0.05, N = 3SE +/- 0.03, N = 36.967.047.25MIN: 6.9 / MAX: 7.93MIN: 6.85 / MAX: 8.14MIN: 7.12 / MAX: 9.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3cba1.28032.56063.84095.12126.4015SE +/- 0.05, N = 3SE +/- 0.02, N = 35.425.455.69MIN: 5.35 / MAX: 6.75MIN: 5.28 / MAX: 7.8MIN: 5.55 / MAX: 9.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2cba246810SE +/- 0.04, N = 3SE +/- 0.02, N = 35.915.946.17MIN: 5.82 / MAX: 7.49MIN: 5.78 / MAX: 7.68MIN: 6.04 / MAX: 10.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetcba3691215SE +/- 0.06, N = 3SE +/- 0.00, N = 312.8412.9313.12MIN: 12.76 / MAX: 13.27MIN: 12.71 / MAX: 15MIN: 12.95 / MAX: 19.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.5