ncnn mnn 3950x

AMD Ryzen 9 3950X 16-Core testing with a ASUS ROG CROSSHAIR VII HERO (WI-FI) (3103 BIOS) and Sapphire AMD Radeon RX 470/480/570/570X/580/580X/590 4GB on Ubuntu 20.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2208150-NE-NCNNMNN3937
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts

Limit displaying results to tests within:

HPC - High Performance Computing 2 Tests
Machine Learning 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
a
August 15 2022
  5 Hours, 36 Minutes
b
August 15 2022
  4 Hours, 59 Minutes
c
August 15 2022
  4 Hours, 58 Minutes
Invert Hiding All Results Option
  5 Hours, 11 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


ncnn mnn 3950xOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VII HERO (WI-FI) (3103 BIOS)AMD Starship/Matisse16GBSamsung SSD 970 EVO 250GB + 32GB Flash DriveSapphire AMD Radeon RX 470/480/570/570X/580/580X/590 4GB (1260/1750MHz)AMD Ellesmere HDMI AudioDELL S2409WIntel I211 + Realtek RTL8822BE 802.11a/b/g/n/acUbuntu 20.045.11.0-43-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.134.6 Mesa 20.0.8 (LLVM 10.0.0)1.2.128GCC 9.3.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionNcnn Mnn 3950x BenchmarksSystem Logs- Transparent Huge Pages: madvise- --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 - Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8701021- 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

abcResult OverviewPhoronix Test Suite100%102%104%106%Mobile Neural NetworkMobile Neural NetworkNCNNNCNNMobile Neural NetworkMobile Neural NetworkMobile Neural NetworkNCNNNCNNMobile Neural NetworkNCNNNCNNNCNNNCNNNCNNNCNNMobile Neural NetworkNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNmobilenet-v1-1.0squeezenetv1.1Vulkan GPU - shufflenet-v2CPU - FastestDetMobileNetV2_224resnet-v2-50SqueezeNetV1.0Vulkan GPU - googlenetVulkan GPU - FastestDetinception-v3CPU - mnasnetVulkan GPU - vgg16CPU - efficientnet-b0Vulkan GPU - blazefaceVulkan GPU - mnasnetVulkan GPU - mobilenetmobilenetV3CPU - yolov4-tinyVulkan GPU - resnet18CPU - resnet18Vulkan GPU - efficientnet-b0CPU - googlenetCPU - shufflenet-v2Vulkan GPU-v3-v3 - mobilenet-v3CPU - squeezenet_ssdVulkan GPU - vision_transformerVulkan GPU - resnet50Vulkan GPU-v2-v2 - mobilenet-v2Vulkan GPU - regnety_400mCPU - vision_transformerCPU - mobilenetCPU - resnet50CPU - alexnetVulkan GPU - squeezenet_ssdCPU - regnety_400mVulkan GPU - alexnetCPU-v3-v3 - mobilenet-v3CPU-v2-v2 - mobilenet-v2Vulkan GPU - yolov4-tinyCPU - vgg16CPU - blazeface

ncnn mnn 3950xncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetmnn: 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 - mobilenetabc3.22377.059.148.4111.6813.047.705.9518.0011.411.9418.495.043.615.624.439.3835.5264.0565.3177.81232.4674.9372.8486.46146.1516.7823.0627.6223.7411.1414.4153.1017.422.47.304.905.524.765.4415.463.17378.959.108.4411.6612.987.715.9418.1511.601.9518.445.033.715.654.439.3435.5183.7525.4077.77533.1504.9372.8416.68145.7016.8323.1327.4623.6511.1814.5053.0317.462.407.324.875.544.755.4515.443.21377.519.128.4311.6813.007.725.9018.2211.591.9618.585.083.575.624.459.2936.0203.7455.4387.65232.7254.6772.8216.43146.3416.7823.0127.3623.6911.1814.5253.1217.352.407.384.935.514.755.4515.50OpenBenchmarking.org

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetabc0.72451.4492.17352.8983.6225SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 33.223.173.21MIN: 3.01 / MAX: 12.12MIN: 2.96 / MAX: 5.36MIN: 3.01 / MAX: 10.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerabc80160240320400SE +/- 0.16, N = 3SE +/- 1.25, N = 3SE +/- 0.36, N = 3377.05378.95377.51MIN: 364.74 / MAX: 405.75MIN: 365.44 / MAX: 413.13MIN: 364 / MAX: 405.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mabc3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 39.149.109.12MIN: 9 / MAX: 13.8MIN: 8.99 / MAX: 13.11MIN: 8.99 / MAX: 13.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdabc246810SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 38.418.448.43MIN: 7.7 / MAX: 16.57MIN: 7.68 / MAX: 16.47MIN: 7.69 / MAX: 15.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyabc3691215SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 311.6811.6611.68MIN: 10.78 / MAX: 24.97MIN: 10.86 / MAX: 23.92MIN: 10.81 / MAX: 27.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50abc3691215SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 313.0412.9813.00MIN: 11.44 / MAX: 23.92MIN: 11.42 / MAX: 21.3MIN: 11.45 / MAX: 25.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetabc246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 37.707.717.72MIN: 7.25 / MAX: 12.12MIN: 7.25 / MAX: 13.21MIN: 7.26 / MAX: 12.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18abc1.33882.67764.01645.35526.694SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 35.955.945.90MIN: 5.23 / MAX: 19.39MIN: 5.23 / MAX: 13.79MIN: 5.24 / MAX: 12.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16abc48121620SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 318.0018.1518.22MIN: 17.4 / MAX: 27.33MIN: 17.42 / MAX: 31.97MIN: 17.39 / MAX: 30.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetabc3691215SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 311.4111.6011.59MIN: 9.64 / MAX: 19.49MIN: 9.66 / MAX: 18.46MIN: 9.65 / MAX: 18.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceabc0.4410.8821.3231.7642.205SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 31.941.951.96MIN: 1.9 / MAX: 5.27MIN: 1.91 / MAX: 5.7MIN: 1.92 / MAX: 5.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0abc510152025SE +/- 0.14, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 318.4918.4418.58MIN: 17.53 / MAX: 31.63MIN: 17.56 / MAX: 30.09MIN: 17.54 / MAX: 31.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetabc1.1432.2863.4294.5725.715SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 35.045.035.08MIN: 4.47 / MAX: 9.88MIN: 4.46 / MAX: 10.1MIN: 4.47 / MAX: 10.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2abc0.83481.66962.50443.33924.174SE +/- 0.06, N = 3SE +/- 0.14, N = 3SE +/- 0.03, N = 33.613.713.57MIN: 3.13 / MAX: 4.29MIN: 3.12 / MAX: 18.24MIN: 3.13 / MAX: 4.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3abc1.27132.54263.81395.08526.3565SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 35.625.655.62MIN: 5.09 / MAX: 7.52MIN: 5.07 / MAX: 14.38MIN: 5.08 / MAX: 8.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2abc1.00132.00263.00394.00525.0065SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 34.434.434.45MIN: 4.09 / MAX: 9.07MIN: 4.09 / MAX: 10.66MIN: 4.08 / MAX: 12.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetabc3691215SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 39.389.349.29MIN: 8.83 / MAX: 36.65MIN: 8.91 / MAX: 18.4MIN: 8.86 / MAX: 28.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: inception-v3abc816243240SE +/- 0.25, N = 3SE +/- 0.26, N = 3SE +/- 0.10, N = 335.5335.5236.02MIN: 34.03 / MAX: 103.82MIN: 33.72 / MAX: 51.6MIN: 34.52 / MAX: 51.711. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenet-v1-1.0abc0.91261.82522.73783.65044.563SE +/- 0.299, N = 3SE +/- 0.043, N = 3SE +/- 0.028, N = 34.0563.7523.745MIN: 3.59 / MAX: 50.47MIN: 3.64 / MAX: 20.1MIN: 3.64 / MAX: 6.121. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: MobileNetV2_224abc1.22362.44723.67084.89446.118SE +/- 0.085, N = 3SE +/- 0.037, N = 3SE +/- 0.035, N = 35.3175.4075.438MIN: 5.04 / MAX: 7.26MIN: 5.21 / MAX: 10.71MIN: 5.21 / MAX: 17.231. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: SqueezeNetV1.0abc246810SE +/- 0.105, N = 3SE +/- 0.073, N = 3SE +/- 0.084, N = 37.8127.7757.652MIN: 7.46 / MAX: 20.39MIN: 7.45 / MAX: 9.84MIN: 7.35 / MAX: 23.641. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: resnet-v2-50abc816243240SE +/- 0.45, N = 3SE +/- 0.13, N = 3SE +/- 0.35, N = 332.4733.1532.73MIN: 29.56 / MAX: 45.88MIN: 30.5 / MAX: 49.94MIN: 30.01 / MAX: 48.891. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: squeezenetv1.1abc1.11082.22163.33244.44325.554SE +/- 0.036, N = 3SE +/- 0.033, N = 3SE +/- 0.166, N = 34.9374.9374.677MIN: 4.71 / MAX: 21.4MIN: 4.72 / MAX: 5.92MIN: 4.39 / MAX: 6.821. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3abc0.64081.28161.92242.56323.204SE +/- 0.038, N = 3SE +/- 0.014, N = 3SE +/- 0.018, N = 32.8482.8412.821MIN: 2.73 / MAX: 4.37MIN: 2.75 / MAX: 3.06MIN: 2.73 / MAX: 5.051. (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

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetabc246810SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 36.466.686.43MIN: 6.27 / MAX: 6.87MIN: 6.61 / MAX: 7.28MIN: 6.25 / MAX: 7.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerabc306090120150SE +/- 0.83, N = 3SE +/- 0.60, N = 3SE +/- 0.24, N = 3146.15145.70146.34MIN: 143.57 / MAX: 164.8MIN: 143.74 / MAX: 164.73MIN: 143.99 / MAX: 161.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mabc48121620SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 316.7816.8316.78MIN: 16.64 / MAX: 18.85MIN: 16.66 / MAX: 18.76MIN: 16.54 / MAX: 33.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdabc612182430SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 323.0623.1323.01MIN: 20.83 / MAX: 30.07MIN: 20.81 / MAX: 32.42MIN: 20.71 / MAX: 31.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyabc612182430SE +/- 0.02, N = 3SE +/- 0.19, N = 3SE +/- 0.20, N = 327.6227.4627.36MIN: 26.17 / MAX: 36.37MIN: 26.01 / MAX: 39.75MIN: 25.81 / MAX: 67.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50abc612182430SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 323.7423.6523.69MIN: 23.07 / MAX: 40.31MIN: 23.15 / MAX: 25.5MIN: 23.12 / MAX: 32.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetabc3691215SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 311.1411.1811.18MIN: 10.69 / MAX: 12.61MIN: 10.65 / MAX: 27.17MIN: 10.59 / MAX: 12.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18abc48121620SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 314.4114.5014.52MIN: 13.93 / MAX: 15.9MIN: 13.99 / MAX: 30.06MIN: 13.88 / MAX: 17.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16abc1224364860SE +/- 0.23, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 353.1053.0353.12MIN: 51 / MAX: 67MIN: 50.97 / MAX: 63.9MIN: 50.96 / MAX: 60.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetabc48121620SE +/- 0.07, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 317.4217.4617.35MIN: 16.22 / MAX: 26.9MIN: 16.21 / MAX: 68.84MIN: 16.08 / MAX: 19.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceabc0.541.081.622.162.7SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 32.402.402.40MIN: 2.36 / MAX: 2.58MIN: 2.36 / MAX: 2.54MIN: 2.36 / MAX: 2.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0abc246810SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 37.307.327.38MIN: 7.2 / MAX: 7.93MIN: 7.22 / MAX: 7.98MIN: 7.18 / MAX: 63.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetabc1.10932.21863.32794.43725.5465SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 34.904.874.93MIN: 4.81 / MAX: 5.04MIN: 4.79 / MAX: 5.69MIN: 4.79 / MAX: 12.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2abc1.24652.4933.73954.9866.2325SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 35.525.545.51MIN: 5.4 / MAX: 6.11MIN: 5.45 / MAX: 7.44MIN: 5.4 / MAX: 6.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3abc1.0712.1423.2134.2845.355SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 34.764.754.75MIN: 4.67 / MAX: 8.48MIN: 4.66 / MAX: 6.12MIN: 4.63 / MAX: 20.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2abc1.22632.45263.67894.90526.1315SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 35.445.455.45MIN: 5.31 / MAX: 6.31MIN: 5.32 / MAX: 6.78MIN: 5.31 / MAX: 15.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetabc48121620SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 315.4615.4415.50MIN: 15.17 / MAX: 17.01MIN: 15.12 / MAX: 27.48MIN: 15.14 / MAX: 67.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread