nn 4500u

AMD Ryzen 5 4500U testing with a LENOVO LNVNB161216 (EECN20WW BIOS) and AMD Renoir 512MB on Ubuntu 21.04 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 2106182-IB-NN4500U6779
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

Limit displaying results to tests within:

HPC - High Performance Computing 3 Tests
Machine Learning 3 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
1
June 18
  8 Hours, 30 Minutes
2
June 18
  14 Hours, 44 Minutes
3
June 18
  14 Hours, 17 Minutes
Invert Hiding All Results Option
  12 Hours, 31 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):


nn 4500uProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen Resolution123AMD Ryzen 5 4500U @ 2.38GHz (6 Cores)LENOVO LNVNB161216 (EECN20WW BIOS)AMD Renoir Root Complex16GB256GB SK hynix HFM256GDHTNI-87A0BAMD Renoir 512MB (1500/400MHz)AMD Device 1637Realtek RTL8822CE 802.11ac PCIeUbuntu 21.045.11.0-17-generic (x86_64)GNOME Shell 3.38.4X Server + Wayland4.6 Mesa 21.0.1 (LLVM 11.0.1)1.2.145GCC 10.3.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/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-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: 0x8600102 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 IBRS_FW STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

123Result OverviewPhoronix Test Suite 10.6.1100%104%108%112%116%NCNNMobile Neural NetworkTNN

nn 4500umnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: 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: 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_400mtnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.11232.2034.00032.9976.5694.0514.52233.64631.499.4910.8010.3210.0318.293.1541.77107.5437.1019.2560.3646.2442.2723.1833.2512.3911.5510.6711.2718.863.6142.19107.8837.8920.95100.1948.6493.8223.154559.998288.91272.103255.2762.2124.06632.8346.7184.0854.73534.19635.3811.8611.5210.6211.2218.883.6642.59108.0237.9519.9163.5949.9947.7023.1430.239.538.637.438.2813.912.4632.20107.9130.8219.0352.4644.4341.4216.014509.044287.74272.119255.1662.2084.23633.1006.8324.1024.87735.16831.5010.7511.2410.6610.7218.273.3242.03107.5835.0719.1360.4546.2142.5723.2528.219.188.397.607.9013.682.5732.43107.5029.2618.3550.9544.3539.5817.004559.544289.39572.332254.927OpenBenchmarking.org

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV31230.49770.99541.49311.99082.4885SE +/- 0.028, N = 3SE +/- 0.017, N = 3SE +/- 0.011, N = 32.2032.2122.208MIN: 2.11 / MAX: 6.76MIN: 2.12 / MAX: 6.6MIN: 2.13 / MAX: 6.481. (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 1.2Model: mobilenetV3123246810Min: 2.15 / Avg: 2.2 / Max: 2.25Min: 2.18 / Avg: 2.21 / Max: 2.23Min: 2.19 / Avg: 2.21 / Max: 2.231. (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 1.2Model: squeezenetv1.11230.95311.90622.85933.81244.7655SE +/- 0.033, N = 3SE +/- 0.007, N = 3SE +/- 0.152, N = 34.0004.0664.236MIN: 3.87 / MAX: 8.61MIN: 3.76 / MAX: 22.69MIN: 3.83 / MAX: 21.261. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.1123246810Min: 3.93 / Avg: 4 / Max: 4.04Min: 4.05 / Avg: 4.07 / Max: 4.08Min: 4.06 / Avg: 4.24 / Max: 4.541. (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 1.2Model: resnet-v2-50123816243240SE +/- 0.13, N = 3SE +/- 0.46, N = 3SE +/- 0.72, N = 333.0032.8333.10MIN: 31.5 / MAX: 73.4MIN: 30.42 / MAX: 77.63MIN: 30.59 / MAX: 88.451. (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 1.2Model: resnet-v2-50123714212835Min: 32.74 / Avg: 33 / Max: 33.16Min: 31.93 / Avg: 32.83 / Max: 33.4Min: 32.1 / Avg: 33.1 / Max: 34.511. (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 1.2Model: SqueezeNetV1.0123246810SE +/- 0.022, N = 3SE +/- 0.128, N = 3SE +/- 0.203, N = 36.5696.7186.832MIN: 6.26 / MAX: 24.71MIN: 6.14 / MAX: 27.21MIN: 6.22 / MAX: 25.151. (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 1.2Model: SqueezeNetV1.01233691215Min: 6.53 / Avg: 6.57 / Max: 6.61Min: 6.59 / Avg: 6.72 / Max: 6.97Min: 6.58 / Avg: 6.83 / Max: 7.231. (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 1.2Model: MobileNetV2_2241230.9231.8462.7693.6924.615SE +/- 0.058, N = 3SE +/- 0.016, N = 3SE +/- 0.001, N = 34.0514.0854.102MIN: 3.87 / MAX: 20.68MIN: 3.89 / MAX: 19.54MIN: 3.96 / MAX: 20.051. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_224123246810Min: 3.94 / Avg: 4.05 / Max: 4.11Min: 4.06 / Avg: 4.09 / Max: 4.11Min: 4.1 / Avg: 4.1 / Max: 4.11. (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 1.2Model: mobilenet-v1-1.01231.09732.19463.29194.38925.4865SE +/- 0.213, N = 3SE +/- 0.417, N = 3SE +/- 0.337, N = 34.5224.7354.877MIN: 4.01 / MAX: 23.57MIN: 3.98 / MAX: 22.51MIN: 4.01 / MAX: 221. (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 1.2Model: mobilenet-v1-1.0123246810Min: 4.29 / Avg: 4.52 / Max: 4.95Min: 4.3 / Avg: 4.74 / Max: 5.57Min: 4.5 / Avg: 4.88 / Max: 5.551. (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 1.2Model: inception-v3123816243240SE +/- 0.35, N = 3SE +/- 0.85, N = 3SE +/- 1.04, N = 333.6534.2035.17MIN: 31.9 / MAX: 94.96MIN: 31.62 / MAX: 90.84MIN: 31.75 / MAX: 91.151. (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 1.2Model: inception-v3123816243240Min: 33.17 / Avg: 33.65 / Max: 34.34Min: 33.26 / Avg: 34.2 / Max: 35.89Min: 33.98 / Avg: 35.17 / Max: 37.241. (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 20210525Target: CPU - Model: mobilenet123816243240SE +/- 0.11, N = 3SE +/- 1.22, N = 12SE +/- 1.42, N = 1231.4935.3831.50MIN: 24.51 / MAX: 58.86MIN: 24.85 / MAX: 86.14MIN: 24.84 / MAX: 61.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mobilenet123816243240Min: 31.3 / Avg: 31.49 / Max: 31.67Min: 27.06 / Avg: 35.38 / Max: 41.77Min: 26.6 / Avg: 31.5 / Max: 39.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v21233691215SE +/- 1.20, N = 3SE +/- 0.17, N = 12SE +/- 0.29, N = 129.4911.8610.75MIN: 6.75 / MAX: 23.77MIN: 6.69 / MAX: 37.78MIN: 6.75 / MAX: 24.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v21233691215Min: 7.43 / Avg: 9.49 / Max: 11.59Min: 11 / Avg: 11.86 / Max: 12.9Min: 8.96 / Avg: 10.75 / Max: 12.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v31233691215SE +/- 0.38, N = 3SE +/- 0.05, N = 12SE +/- 0.09, N = 1210.8011.5211.24MIN: 5.74 / MAX: 32.52MIN: 5.7 / MAX: 33.82MIN: 5.68 / MAX: 32.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v31233691215Min: 10.07 / Avg: 10.8 / Max: 11.34Min: 11.19 / Avg: 11.52 / Max: 11.79Min: 10.78 / Avg: 11.24 / Max: 11.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v21233691215SE +/- 0.16, N = 3SE +/- 0.05, N = 12SE +/- 0.03, N = 1210.3210.6210.66MIN: 4.57 / MAX: 22.86MIN: 4.5 / MAX: 34.44MIN: 4.55 / MAX: 30.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v21233691215Min: 10.02 / Avg: 10.32 / Max: 10.57Min: 10.34 / Avg: 10.62 / Max: 10.95Min: 10.5 / Avg: 10.66 / Max: 10.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet1233691215SE +/- 0.96, N = 3SE +/- 0.16, N = 12SE +/- 0.17, N = 1210.0311.2210.72MIN: 5.25 / MAX: 25.07MIN: 5.1 / MAX: 57.06MIN: 5.09 / MAX: 31.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet1233691215Min: 8.2 / Avg: 10.03 / Max: 11.43Min: 9.92 / Avg: 11.22 / Max: 11.76Min: 9.81 / Avg: 10.72 / Max: 11.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b0123510152025SE +/- 0.22, N = 3SE +/- 0.06, N = 12SE +/- 0.12, N = 1218.2918.8818.27MIN: 9.11 / MAX: 28.87MIN: 9.06 / MAX: 52.06MIN: 9.03 / MAX: 36.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b0123510152025Min: 17.9 / Avg: 18.29 / Max: 18.65Min: 18.35 / Avg: 18.88 / Max: 19.16Min: 17.63 / Avg: 18.27 / Max: 18.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface1230.82351.6472.47053.2944.1175SE +/- 0.38, N = 3SE +/- 0.05, N = 12SE +/- 0.11, N = 123.153.663.32MIN: 1.51 / MAX: 17.82MIN: 1.48 / MAX: 14.98MIN: 1.49 / MAX: 16.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface123246810Min: 2.52 / Avg: 3.15 / Max: 3.84Min: 3.41 / Avg: 3.66 / Max: 3.9Min: 2.63 / Avg: 3.32 / Max: 3.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet1231020304050SE +/- 0.83, N = 3SE +/- 0.10, N = 12SE +/- 0.18, N = 1241.7742.5942.03MIN: 22.52 / MAX: 60.67MIN: 23.06 / MAX: 88.57MIN: 22.44 / MAX: 84.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet123918273645Min: 40.14 / Avg: 41.77 / Max: 42.8Min: 42.05 / Avg: 42.59 / Max: 43.38Min: 40.42 / Avg: 42.03 / Max: 42.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg1612320406080100SE +/- 0.25, N = 3SE +/- 0.07, N = 12SE +/- 0.10, N = 12107.54108.02107.58MIN: 105.61 / MAX: 144.21MIN: 105.44 / MAX: 160.08MIN: 104.99 / MAX: 152.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg1612320406080100Min: 107.26 / Avg: 107.54 / Max: 108.03Min: 107.68 / Avg: 108.02 / Max: 108.57Min: 107.01 / Avg: 107.58 / Max: 108.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet18123918273645SE +/- 1.86, N = 3SE +/- 0.56, N = 12SE +/- 0.42, N = 1237.1037.9535.07MIN: 22.99 / MAX: 65.11MIN: 23.18 / MAX: 80.55MIN: 23.18 / MAX: 76.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet18123816243240Min: 33.38 / Avg: 37.1 / Max: 39.01Min: 34.75 / Avg: 37.95 / Max: 41.22Min: 33 / Avg: 35.07 / Max: 37.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet123510152025SE +/- 1.25, N = 3SE +/- 0.47, N = 12SE +/- 0.35, N = 1219.2519.9119.13MIN: 16.66 / MAX: 39.01MIN: 16.61 / MAX: 47.54MIN: 16.65 / MAX: 46.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet123510152025Min: 17.2 / Avg: 19.25 / Max: 21.51Min: 17.87 / Avg: 19.91 / Max: 23.82Min: 17.65 / Avg: 19.13 / Max: 21.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet501231428425670SE +/- 1.09, N = 3SE +/- 0.38, N = 12SE +/- 0.46, N = 1260.3663.5960.45MIN: 40.93 / MAX: 108.13MIN: 40.74 / MAX: 114.13MIN: 40.51 / MAX: 104.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet501231224364860Min: 58.66 / Avg: 60.36 / Max: 62.4Min: 61.83 / Avg: 63.59 / Max: 66.33Min: 58.49 / Avg: 60.45 / Max: 63.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny1231122334455SE +/- 1.99, N = 3SE +/- 0.53, N = 12SE +/- 0.71, N = 1246.2449.9946.21MIN: 39.41 / MAX: 78.9MIN: 40.24 / MAX: 100.65MIN: 40.27 / MAX: 96.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny1231020304050Min: 43.94 / Avg: 46.24 / Max: 50.19Min: 47.05 / Avg: 49.99 / Max: 53.05Min: 42.61 / Avg: 46.21 / Max: 50.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd1231122334455SE +/- 1.59, N = 3SE +/- 0.84, N = 12SE +/- 0.54, N = 1242.2747.7042.57MIN: 35.65 / MAX: 94.42MIN: 35.39 / MAX: 100.93MIN: 35.35 / MAX: 95.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd1231020304050Min: 39.48 / Avg: 42.27 / Max: 44.99Min: 43.24 / Avg: 47.7 / Max: 51.85Min: 40.12 / Avg: 42.57 / Max: 45.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m123612182430SE +/- 0.14, N = 3SE +/- 0.06, N = 12SE +/- 0.06, N = 1223.1823.1423.25MIN: 9.46 / MAX: 65.06MIN: 9.5 / MAX: 40.51MIN: 9.5 / MAX: 84.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m123510152025Min: 22.9 / Avg: 23.18 / Max: 23.33Min: 22.83 / Avg: 23.14 / Max: 23.41Min: 22.9 / Avg: 23.25 / Max: 23.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: mobilenet123816243240SE +/- 1.66, N = 9SE +/- 1.67, N = 15SE +/- 0.91, N = 1533.2530.2328.21MIN: 25.11 / MAX: 60.73MIN: 24.85 / MAX: 82.1MIN: 24.81 / MAX: 62.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: mobilenet123714212835Min: 28.33 / Avg: 33.25 / Max: 41.41Min: 25.38 / Avg: 30.23 / Max: 41.56Min: 25.52 / Avg: 28.21 / Max: 38.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU-v2-v2 - Model: mobilenet-v21233691215SE +/- 0.24, N = 9SE +/- 0.69, N = 15SE +/- 0.64, N = 1512.399.539.18MIN: 6.79 / MAX: 30.5MIN: 6.79 / MAX: 29.13MIN: 6.77 / MAX: 31.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU-v2-v2 - Model: mobilenet-v212348121620Min: 11.07 / Avg: 12.39 / Max: 13.42Min: 7.07 / Avg: 9.53 / Max: 12.99Min: 7.07 / Avg: 9.18 / Max: 13.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU-v3-v3 - Model: mobilenet-v31233691215SE +/- 0.08, N = 9SE +/- 0.76, N = 15SE +/- 0.69, N = 1511.558.638.39MIN: 5.78 / MAX: 29.41MIN: 5.73 / MAX: 29.8MIN: 5.72 / MAX: 32.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU-v3-v3 - Model: mobilenet-v31233691215Min: 11.15 / Avg: 11.55 / Max: 11.89Min: 5.93 / Avg: 8.63 / Max: 11.82Min: 5.95 / Avg: 8.39 / Max: 11.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: shufflenet-v21233691215SE +/- 0.06, N = 9SE +/- 0.80, N = 15SE +/- 0.76, N = 1510.677.437.60MIN: 4.55 / MAX: 37.18MIN: 4.54 / MAX: 43.91MIN: 4.48 / MAX: 27.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: shufflenet-v21233691215Min: 10.33 / Avg: 10.67 / Max: 10.87Min: 4.61 / Avg: 7.43 / Max: 10.83Min: 4.64 / Avg: 7.6 / Max: 10.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: mnasnet1233691215SE +/- 0.15, N = 9SE +/- 0.80, N = 15SE +/- 0.72, N = 1511.278.287.90MIN: 5.26 / MAX: 37.14MIN: 5.1 / MAX: 45.68MIN: 5.17 / MAX: 26.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: mnasnet1233691215Min: 10.5 / Avg: 11.27 / Max: 11.73Min: 5.38 / Avg: 8.28 / Max: 11.75Min: 5.26 / Avg: 7.9 / Max: 11.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: efficientnet-b0123510152025SE +/- 0.11, N = 9SE +/- 1.28, N = 15SE +/- 1.16, N = 1518.8613.9113.68MIN: 9.2 / MAX: 67.85MIN: 9.16 / MAX: 40.01MIN: 9.06 / MAX: 30.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: efficientnet-b0123510152025Min: 18.15 / Avg: 18.86 / Max: 19.34Min: 9.31 / Avg: 13.91 / Max: 19.09Min: 9.43 / Avg: 13.68 / Max: 19.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: blazeface1230.81231.62462.43693.24924.0615SE +/- 0.06, N = 9SE +/- 0.26, N = 15SE +/- 0.23, N = 153.612.462.57MIN: 1.5 / MAX: 27.59MIN: 1.48 / MAX: 18.99MIN: 1.52 / MAX: 38.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: blazeface123246810Min: 3.27 / Avg: 3.61 / Max: 3.77Min: 1.52 / Avg: 2.46 / Max: 3.85Min: 1.6 / Avg: 2.57 / Max: 3.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: googlenet1231020304050SE +/- 0.09, N = 9SE +/- 2.58, N = 15SE +/- 2.32, N = 1542.1932.2032.43MIN: 22.69 / MAX: 66.5MIN: 22.62 / MAX: 65.3MIN: 22.43 / MAX: 79.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: googlenet123918273645Min: 41.51 / Avg: 42.19 / Max: 42.43Min: 22.85 / Avg: 32.2 / Max: 42.88Min: 23.3 / Avg: 32.43 / Max: 42.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: vgg1612320406080100SE +/- 0.13, N = 9SE +/- 0.23, N = 15SE +/- 0.11, N = 15107.88107.91107.50MIN: 104.8 / MAX: 168.16MIN: 105.33 / MAX: 157.92MIN: 105.52 / MAX: 153.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: vgg1612320406080100Min: 107.32 / Avg: 107.88 / Max: 108.59Min: 107.05 / Avg: 107.91 / Max: 109.52Min: 106.42 / Avg: 107.5 / Max: 108.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: resnet18123918273645SE +/- 0.72, N = 9SE +/- 2.05, N = 15SE +/- 1.73, N = 1537.8930.8229.26MIN: 23.05 / MAX: 68.33MIN: 23.03 / MAX: 84.28MIN: 23.11 / MAX: 61.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: resnet18123816243240Min: 34.56 / Avg: 37.89 / Max: 40.89Min: 23.29 / Avg: 30.82 / Max: 40.5Min: 23.34 / Avg: 29.26 / Max: 41.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: alexnet123510152025SE +/- 0.76, N = 9SE +/- 0.62, N = 15SE +/- 0.41, N = 1520.9519.0318.35MIN: 16.56 / MAX: 45.25MIN: 16.66 / MAX: 43.01MIN: 16.67 / MAX: 364.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: alexnet123510152025Min: 18.14 / Avg: 20.95 / Max: 25.62Min: 16.88 / Avg: 19.03 / Max: 23.68Min: 17.23 / Avg: 18.35 / Max: 22.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: resnet5012320406080100SE +/- 35.51, N = 9SE +/- 3.04, N = 15SE +/- 2.26, N = 15100.1952.4650.95MIN: 40.36 / MAX: 4154.68MIN: 40.54 / MAX: 116.09MIN: 40.68 / MAX: 95.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: resnet5012320406080100Min: 62.57 / Avg: 100.19 / Max: 384.22Min: 41.33 / Avg: 52.46 / Max: 69.08Min: 42.27 / Avg: 50.95 / Max: 66.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: yolov4-tiny1231122334455SE +/- 1.00, N = 9SE +/- 1.11, N = 15SE +/- 1.00, N = 1548.6444.4344.35MIN: 39.58 / MAX: 96.41MIN: 40.31 / MAX: 97.89MIN: 40.22 / MAX: 102.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: yolov4-tiny1231020304050Min: 44.52 / Avg: 48.64 / Max: 53.58Min: 40.83 / Avg: 44.43 / Max: 50.97Min: 41.64 / Avg: 44.35 / Max: 53.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: squeezenet_ssd12320406080100SE +/- 47.17, N = 9SE +/- 1.74, N = 15SE +/- 1.17, N = 1593.8241.4239.58MIN: 35.41 / MAX: 3029.77MIN: 35.36 / MAX: 129MIN: 35.36 / MAX: 109.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: squeezenet_ssd12320406080100Min: 42.02 / Avg: 93.82 / Max: 471.06Min: 35.86 / Avg: 41.42 / Max: 53.52Min: 35.96 / Avg: 39.58 / Max: 49.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: regnety_400m123612182430SE +/- 0.07, N = 9SE +/- 1.80, N = 15SE +/- 1.74, N = 1523.1516.0117.00MIN: 9.45 / MAX: 58.66MIN: 9.41 / MAX: 46.2MIN: 9.3 / MAX: 61.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: regnety_400m123510152025Min: 22.85 / Avg: 23.15 / Max: 23.6Min: 9.56 / Avg: 16.01 / Max: 23.47Min: 9.7 / Avg: 17 / Max: 23.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNet12310002000300040005000SE +/- 5.81, N = 3SE +/- 11.25, N = 3SE +/- 8.59, N = 34560.004509.044559.54MIN: 4366.8 / MAX: 4788.13MIN: 4263.42 / MAX: 4776.08MIN: 4387.74 / MAX: 4716.571. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNet1238001600240032004000Min: 4548.75 / Avg: 4560 / Max: 4568.16Min: 4487.19 / Avg: 4509.04 / Max: 4524.6Min: 4542.39 / Avg: 4559.54 / Max: 4568.881. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v212360120180240300SE +/- 0.27, N = 3SE +/- 1.19, N = 3SE +/- 0.58, N = 3288.91287.74289.40MIN: 280.4 / MAX: 305.18MIN: 280.35 / MAX: 307.48MIN: 281.68 / MAX: 320.441. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v212350100150200250Min: 288.59 / Avg: 288.91 / Max: 289.44Min: 285.37 / Avg: 287.74 / Max: 289.08Min: 288.73 / Avg: 289.4 / Max: 290.561. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v21231632486480SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.20, N = 372.1072.1272.33MIN: 71.64 / MAX: 72.78MIN: 71.43 / MAX: 72.62MIN: 71.7 / MAX: 73.11. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v21231428425670Min: 71.88 / Avg: 72.1 / Max: 72.4Min: 71.85 / Avg: 72.12 / Max: 72.29Min: 72 / Avg: 72.33 / Max: 72.71. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.112360120180240300SE +/- 0.29, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 3255.28255.17254.93MIN: 254.37 / MAX: 258.22MIN: 254.38 / MAX: 256.83MIN: 254.39 / MAX: 255.871. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.112350100150200250Min: 254.93 / Avg: 255.28 / Max: 255.85Min: 254.94 / Avg: 255.17 / Max: 255.37Min: 254.9 / Avg: 254.93 / Max: 254.981. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl