nn 3200u

AMD Ryzen 3 3200U testing with a MOTILE PF4PU1F (N.1.03 BIOS) and AMD Picasso 512MB 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 2106187-IB-NN3200U8193
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
  6 Hours, 6 Minutes
2
June 18
  2 Hours, 3 Minutes
3
June 18
  6 Hours, 15 Minutes
Invert Hiding All Results Option
  4 Hours, 48 Minutes

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


nn 3200uProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen Resolution123AMD Ryzen 3 3200U @ 2.60GHz (2 Cores / 4 Threads)MOTILE PF4PU1F (N.1.03 BIOS)AMD Raven/Raven23584MB128GB BIWIN SSDAMD Picasso 512MB (1200/1200MHz)AMD Raven/Raven2/FenghuangRealtek RTL8111/8168/8411 + Intel Dual Band-AC 3168NGWUbuntu 20.045.8.0-53-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.94.6 Mesa 20.0.8 (LLVM 10.0.0)GCC 9.3.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler 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: 0x8108102 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: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

123Result OverviewPhoronix Test Suite 10.6.1100%101%101%102%Mobile Neural NetworkNCNNTNN

nn 3200umnn: 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_400mtnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.11234.26312.129110.99021.58212.45718.134146.12578.9719.5216.7910.8018.2529.814.0264.82242.8861.2049.46139.80104.1584.9526.656160.911376.99586.058308.4034.27912.191109.51620.97712.61218.166146.90378.9719.0116.3810.7318.0429.833.7365.35244.3761.9350.32141.48104.884.1726.736168.371377.5985.921308.2234.35812.233118.32621.96112.62618.372152.70779.7019.8917.1411.0918.6830.423.8065.81246.1062.3550.95141.37105.2783.7526.566234.935378.74986.134308.322OpenBenchmarking.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: mobilenetV31230.98061.96122.94183.92244.903SE +/- 0.009, N = 3SE +/- 0.048, N = 34.2634.2794.358MIN: 3.72 / MAX: 4.94MIN: 3.74 / MAX: 4.74MIN: 3.79 / MAX: 6.171. (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: 4.25 / Avg: 4.26 / Max: 4.27Min: 4.26 / Avg: 4.36 / Max: 4.421. (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: squeezenetv1.11233691215SE +/- 0.02, N = 3SE +/- 0.06, N = 312.1312.1912.23MIN: 10.69 / MAX: 29.07MIN: 10.96 / MAX: 13.33MIN: 10.78 / MAX: 15.411. (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: squeezenetv1.112348121620Min: 12.09 / Avg: 12.13 / Max: 12.15Min: 12.12 / Avg: 12.23 / Max: 12.31. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-50123306090120150SE +/- 0.50, N = 3SE +/- 0.81, N = 3110.99109.52118.33MIN: 105.7 / MAX: 203.02MIN: 106.42 / MAX: 126.95MIN: 112.93 / MAX: 176.061. (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-v2-5012320406080100Min: 110.01 / Avg: 110.99 / Max: 111.63Min: 116.72 / Avg: 118.33 / Max: 119.291. (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: SqueezeNetV1.0123510152025SE +/- 0.40, N = 3SE +/- 0.55, N = 321.5820.9821.96MIN: 18.59 / MAX: 38.81MIN: 18.69 / MAX: 38.28MIN: 18.42 / MAX: 40.531. (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: SqueezeNetV1.0123510152025Min: 20.79 / Avg: 21.58 / Max: 21.99Min: 20.86 / Avg: 21.96 / Max: 22.531. (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_2241233691215SE +/- 0.01, N = 3SE +/- 0.04, N = 312.4612.6112.63MIN: 10.91 / MAX: 28.85MIN: 10.94 / MAX: 67.15MIN: 11.05 / MAX: 15.371. (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_22412348121620Min: 12.44 / Avg: 12.46 / Max: 12.47Min: 12.55 / Avg: 12.63 / Max: 12.671. (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-v1-1.0123510152025SE +/- 0.02, N = 3SE +/- 0.07, N = 318.1318.1718.37MIN: 15.89 / MAX: 35.85MIN: 15.85 / MAX: 20.15MIN: 15.92 / MAX: 21.711. (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 1.2Model: mobilenet-v1-1.0123510152025Min: 18.1 / Avg: 18.13 / Max: 18.17Min: 18.24 / Avg: 18.37 / Max: 18.461. (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-v3123306090120150SE +/- 0.11, N = 3SE +/- 0.76, N = 3146.13146.90152.71MIN: 139.84 / MAX: 217.1MIN: 142.08 / MAX: 167.66MIN: 141.37 / MAX: 209.691. (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-v3123306090120150Min: 145.91 / Avg: 146.13 / Max: 146.28Min: 151.32 / Avg: 152.71 / Max: 153.931. (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: mobilenet12320406080100SE +/- 0.73, N = 3SE +/- 0.10, N = 378.9778.9779.70MIN: 75.23 / MAX: 94.98MIN: 76.73 / MAX: 81.18MIN: 76.19 / MAX: 90.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mobilenet1231530456075Min: 77.81 / Avg: 78.97 / Max: 80.32Min: 79.53 / Avg: 79.7 / Max: 79.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v2123510152025SE +/- 0.05, N = 3SE +/- 0.29, N = 319.5219.0119.89MIN: 17.77 / MAX: 21.9MIN: 17.58 / MAX: 19.83MIN: 17.88 / MAX: 21.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v2123510152025Min: 19.42 / Avg: 19.52 / Max: 19.57Min: 19.33 / Avg: 19.89 / Max: 20.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v312348121620SE +/- 0.12, N = 3SE +/- 0.18, N = 316.7916.3817.14MIN: 15.12 / MAX: 18.46MIN: 14.95 / MAX: 17.17MIN: 15.26 / MAX: 83.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v312348121620Min: 16.58 / Avg: 16.79 / Max: 16.98Min: 16.89 / Avg: 17.14 / Max: 17.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v21233691215SE +/- 0.09, N = 3SE +/- 0.14, N = 310.8010.7311.09MIN: 9.77 / MAX: 11.84MIN: 10.02 / MAX: 12.83MIN: 10 / MAX: 14.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v21233691215Min: 10.7 / Avg: 10.8 / Max: 10.98Min: 10.81 / Avg: 11.09 / Max: 11.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet123510152025SE +/- 0.26, N = 3SE +/- 0.15, N = 318.2518.0418.68MIN: 16.95 / MAX: 20.24MIN: 16.95 / MAX: 18.78MIN: 16.92 / MAX: 33.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet123510152025Min: 17.96 / Avg: 18.25 / Max: 18.76Min: 18.49 / Avg: 18.68 / Max: 18.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b0123714212835SE +/- 0.04, N = 3SE +/- 0.11, N = 329.8129.8330.42MIN: 28 / MAX: 47.3MIN: 28.4 / MAX: 31.78MIN: 28.31 / MAX: 32.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b0123714212835Min: 29.74 / Avg: 29.81 / Max: 29.89Min: 30.21 / Avg: 30.42 / Max: 30.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface1230.90451.8092.71353.6184.5225SE +/- 0.12, N = 3SE +/- 0.01, N = 34.023.733.80MIN: 3.39 / MAX: 4.86MIN: 3.41 / MAX: 4.22MIN: 3.45 / MAX: 4.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface123246810Min: 3.78 / Avg: 4.02 / Max: 4.14Min: 3.79 / Avg: 3.8 / Max: 3.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet1231530456075SE +/- 0.11, N = 3SE +/- 0.29, N = 364.8265.3565.81MIN: 62.4 / MAX: 66.86MIN: 62.58 / MAX: 74.75MIN: 62.82 / MAX: 81.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet1231326395265Min: 64.62 / Avg: 64.82 / Max: 65.01Min: 65.23 / Avg: 65.81 / Max: 66.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg1612350100150200250SE +/- 0.55, N = 3SE +/- 0.26, N = 3242.88244.37246.10MIN: 236.84 / MAX: 258.16MIN: 239.9 / MAX: 252.6MIN: 239.46 / MAX: 257.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg161234080120160200Min: 242.27 / Avg: 242.88 / Max: 243.98Min: 245.69 / Avg: 246.1 / Max: 246.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet181231428425670SE +/- 0.08, N = 3SE +/- 0.19, N = 361.2061.9362.35MIN: 58.65 / MAX: 77.16MIN: 59.43 / MAX: 64.36MIN: 58.28 / MAX: 64.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet181231224364860Min: 61.03 / Avg: 61.2 / Max: 61.3Min: 61.98 / Avg: 62.35 / Max: 62.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet1231122334455SE +/- 0.04, N = 3SE +/- 0.24, N = 349.4650.3250.95MIN: 47.25 / MAX: 52.94MIN: 47.69 / MAX: 52.35MIN: 48.45 / MAX: 63.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet1231020304050Min: 49.37 / Avg: 49.46 / Max: 49.52Min: 50.47 / Avg: 50.95 / Max: 51.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet50123306090120150SE +/- 0.20, N = 3SE +/- 0.20, N = 3139.80141.48141.37MIN: 135.86 / MAX: 180.07MIN: 137.07 / MAX: 150.1MIN: 136.79 / MAX: 211.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet50123306090120150Min: 139.55 / Avg: 139.8 / Max: 140.19Min: 141.01 / Avg: 141.37 / Max: 141.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny12320406080100SE +/- 0.32, N = 3SE +/- 0.14, N = 3104.15104.80105.27MIN: 98.5 / MAX: 157.28MIN: 99.73 / MAX: 111.4MIN: 100.03 / MAX: 119.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny12320406080100Min: 103.8 / Avg: 104.15 / Max: 104.79Min: 105.09 / Avg: 105.27 / Max: 105.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd12320406080100SE +/- 0.57, N = 3SE +/- 0.52, N = 384.9584.1783.75MIN: 78.77 / MAX: 99.5MIN: 79.61 / MAX: 119.23MIN: 79.56 / MAX: 103.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd1231632486480Min: 83.81 / Avg: 84.95 / Max: 85.59Min: 82.72 / Avg: 83.75 / Max: 84.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m123612182430SE +/- 0.78, N = 3SE +/- 0.28, N = 326.6526.7326.56MIN: 23.84 / MAX: 32.74MIN: 24.65 / MAX: 28.56MIN: 24.63 / MAX: 29.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m123612182430Min: 25.78 / Avg: 26.65 / Max: 28.21Min: 26.27 / Avg: 26.56 / Max: 27.111. (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: DenseNet12313002600390052006500SE +/- 16.38, N = 3SE +/- 14.55, N = 36160.916168.376234.94MIN: 6048.31 / MAX: 6347.32MIN: 6081.49 / MAX: 6270.37MIN: 6092.99 / MAX: 6383.181. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNet12311002200330044005500Min: 6141.65 / Avg: 6160.91 / Max: 6193.49Min: 6208.13 / Avg: 6234.93 / Max: 6258.131. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v212380160240320400SE +/- 0.34, N = 3SE +/- 0.56, N = 3377.00377.59378.75MIN: 368.57 / MAX: 387.2MIN: 369.13 / MAX: 391.97MIN: 368.02 / MAX: 399.51. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v212370140210280350Min: 376.51 / Avg: 377 / Max: 377.64Min: 377.66 / Avg: 378.75 / Max: 379.481. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v212320406080100SE +/- 0.20, N = 3SE +/- 0.08, N = 386.0685.9286.13MIN: 85.33 / MAX: 88.22MIN: 85.7 / MAX: 86.35MIN: 85.48 / MAX: 88.531. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v21231632486480Min: 85.78 / Avg: 86.06 / Max: 86.46Min: 86.02 / Avg: 86.13 / Max: 86.291. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.112370140210280350SE +/- 0.04, N = 3SE +/- 0.11, N = 3308.40308.22308.32MIN: 307.45 / MAX: 311.92MIN: 307.99 / MAX: 308.52MIN: 307.87 / MAX: 310.121. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.112360120180240300Min: 308.32 / Avg: 308.4 / Max: 308.47Min: 308.21 / Avg: 308.32 / Max: 308.541. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl