mnn macOS

Intel Core i7-8700B testing with a Apple Mac mini and Intel UHD 630 2GB on macOS 11.2 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 2101124-HA-MNNMACOS559
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

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
January 12 2021
  25 Minutes
2
January 12 2021
  25 Minutes
3
January 12 2021
  25 Minutes
Invert Hiding All Results Option
  25 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):


mnn macOSProcessorMotherboardMemoryDiskGraphicsMonitorOSKernelOpenCLCompilerFile-SystemScreen Resolution123Intel Core i7-8700B @ 3.20GHz (6 Cores / 12 Threads)Apple Mac mini2 x 4 GB DDR4-2667MHz234GBIntel UHD 630 2GBDELL P2415QmacOS 11.220.3.0 (x86_64)OpenCL 1.2 (Dec 6 2020 11:42:32)GCC 4.2.1 + Clang 11.0.0APFS3840x2160OpenBenchmarking.orgEnvironment Details- XPC_FLAGS=0x0Processor Details- CPU Microcode: 222

123Result OverviewPhoronix Test Suite100%100%101%101%102%Mobile Neural NetworkMobile Neural NetworkMobile Neural NetworkMobile Neural NetworkMobile Neural NetworkMobileNetV2_224mobilenet-v1-1.0resnet-v2-50SqueezeNetV1.0inception-v3

mnn macOSmnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: resnet-v2-50mnn: SqueezeNetV1.012340.7944.2283.48833.4015.58240.6984.2153.45933.0565.52541.0654.2693.43533.4025.569OpenBenchmarking.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 1.1.1Model: inception-v3123918273645SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.12, N = 340.7940.7041.07MIN: 39.45 / MAX: 48.17MIN: 39.57 / MAX: 48.12MIN: 39.63 / MAX: 48.391. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: inception-v3123918273645Min: 40.66 / Avg: 40.79 / Max: 41Min: 40.51 / Avg: 40.7 / Max: 40.87Min: 40.93 / Avg: 41.07 / Max: 41.311. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: mobilenet-v1-1.01230.96051.9212.88153.8424.8025SE +/- 0.010, N = 3SE +/- 0.026, N = 3SE +/- 0.021, N = 34.2284.2154.269MIN: 4.07 / MAX: 8.75MIN: 4 / MAX: 5.28MIN: 4.16 / MAX: 8.751. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: mobilenet-v1-1.0123246810Min: 4.21 / Avg: 4.23 / Max: 4.25Min: 4.16 / Avg: 4.22 / Max: 4.25Min: 4.24 / Avg: 4.27 / Max: 4.311. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: MobileNetV2_2241230.78481.56962.35443.13923.924SE +/- 0.006, N = 3SE +/- 0.023, N = 3SE +/- 0.025, N = 33.4883.4593.435MIN: 3.3 / MAX: 4.82MIN: 3.27 / MAX: 8.65MIN: 3.2 / MAX: 5.241. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: MobileNetV2_224123246810Min: 3.48 / Avg: 3.49 / Max: 3.5Min: 3.43 / Avg: 3.46 / Max: 3.5Min: 3.4 / Avg: 3.43 / Max: 3.491. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: resnet-v2-50123816243240SE +/- 0.21, N = 3SE +/- 0.21, N = 3SE +/- 0.09, N = 333.4033.0633.40MIN: 31.49 / MAX: 89.51MIN: 31.49 / MAX: 41.78MIN: 31.59 / MAX: 41.521. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: resnet-v2-50123714212835Min: 33.18 / Avg: 33.4 / Max: 33.82Min: 32.64 / Avg: 33.06 / Max: 33.32Min: 33.31 / Avg: 33.4 / Max: 33.581. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: SqueezeNetV1.01231.2562.5123.7685.0246.28SE +/- 0.066, N = 3SE +/- 0.008, N = 3SE +/- 0.033, N = 35.5825.5255.569MIN: 5.25 / MAX: 6.91MIN: 5.23 / MAX: 7.29MIN: 5.27 / MAX: 6.971. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: SqueezeNetV1.0123246810Min: 5.5 / Avg: 5.58 / Max: 5.71Min: 5.51 / Avg: 5.53 / Max: 5.54Min: 5.53 / Avg: 5.57 / Max: 5.641. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot