nn tigerlake

Intel Core i7-1165G7 testing with a Dell 0GG9PT (1.2.5 BIOS) and Intel Xe TGL GT2 3GB 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 2106185-IB-NNTIGERLA92
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 2021
  4 Hours, 58 Minutes
2
June 18 2021
  8 Hours, 26 Minutes
3
June 18 2021
  8 Hours, 23 Minutes
Invert Hiding All Results Option
  7 Hours, 16 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):


nn tigerlakeProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen Resolution123Intel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads)Dell 0GG9PT (1.2.5 BIOS)Intel Tiger Lake-LP16GBKioxia KBG40ZNS256G NVMe 256GBIntel Xe TGL GT2 3GB (1300MHz)Realtek ALC289Intel Wi-Fi 6 AX201Ubuntu 21.045.11.0-18-generic (x86_64)GNOME Shell 3.38.4X Server + Wayland4.6 Mesa 21.0.11.2.145GCC 10.3.0ext41920x1200OpenBenchmarking.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: intel_pstate powersave - CPU Microcode: 0x6e - Thermald 2.4.3 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

123Result OverviewPhoronix Test Suite100%101%102%102%TNNNCNNMobile Neural Network

nn tigerlakemnn: 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 v1.11232.5224.88843.7067.3644.6425.06853.73624.054.834.865.275.659.512.1421.0864.9119.7017.1738.2335.3131.1812.044311.562300.65256.577271.4532.5174.93041.9237.4084.6095.04453.72723.314.784.845.636.119.162.0820.0663.3719.2316.6737.1934.3630.3511.784250.097302.07756.502271.7582.5164.90541.6167.3844.6085.04354.09423.494.795.045.676.149.222.1220.2163.4019.2916.7437.3734.4330.5211.833870.770298.90056.130272.100OpenBenchmarking.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: mobilenetV33210.56751.1351.70252.272.8375SE +/- 0.056, N = 11SE +/- 0.032, N = 12SE +/- 0.049, N = 122.5162.5172.522MIN: 1.89 / MAX: 32.26MIN: 2.08 / MAX: 18.91MIN: 1.89 / MAX: 17.891. (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 1.2Model: mobilenetV3321246810Min: 1.97 / Avg: 2.52 / Max: 2.64Min: 2.17 / Avg: 2.52 / Max: 2.57Min: 1.98 / Avg: 2.52 / Max: 2.611. (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: squeezenetv1.11321.10932.21863.32794.43725.5465SE +/- 0.092, N = 12SE +/- 0.107, N = 11SE +/- 0.090, N = 124.8884.9054.930MIN: 3.77 / MAX: 20.84MIN: 3.8 / MAX: 21.15MIN: 3.91 / MAX: 24.081. (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: squeezenetv1.1132246810Min: 3.88 / Avg: 4.89 / Max: 5Min: 3.88 / Avg: 4.91 / Max: 5.32Min: 4.04 / Avg: 4.93 / 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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-503211020304050SE +/- 0.24, N = 11SE +/- 0.20, N = 12SE +/- 1.72, N = 1241.6241.9243.71MIN: 32.18 / MAX: 85.23MIN: 39.81 / MAX: 66.78MIN: 35.18 / MAX: 213.561. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-50321918273645Min: 39.79 / Avg: 41.62 / Max: 43.32Min: 41.35 / Avg: 41.92 / Max: 43.41Min: 41.53 / Avg: 43.71 / Max: 62.511. (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: SqueezeNetV1.0132246810SE +/- 0.146, N = 12SE +/- 0.162, N = 11SE +/- 0.144, N = 127.3647.3847.408MIN: 5.37 / MAX: 23.38MIN: 5.46 / MAX: 27.35MIN: 5.34 / MAX: 24.231. (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: SqueezeNetV1.01323691215Min: 5.77 / Avg: 7.36 / Max: 7.6Min: 5.8 / Avg: 7.38 / Max: 7.85Min: 5.89 / Avg: 7.41 / Max: 7.871. (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_2243211.04452.0893.13354.1785.2225SE +/- 0.095, N = 11SE +/- 0.085, N = 12SE +/- 0.091, N = 124.6084.6094.642MIN: 3.59 / MAX: 19.15MIN: 3.5 / MAX: 20.45MIN: 3.54 / MAX: 20.571. (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_224321246810Min: 3.66 / Avg: 4.61 / Max: 4.73Min: 3.68 / Avg: 4.61 / Max: 4.73Min: 3.64 / Avg: 4.64 / Max: 4.781. (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-v1-1.03211.14032.28063.42094.56125.7015SE +/- 0.107, N = 11SE +/- 0.093, N = 12SE +/- 0.097, N = 125.0435.0445.068MIN: 3.73 / MAX: 21.64MIN: 3.84 / MAX: 21.17MIN: 3.74 / MAX: 20.371. (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: mobilenet-v1-1.0321246810Min: 3.98 / Avg: 5.04 / Max: 5.19Min: 4.03 / Avg: 5.04 / Max: 5.18Min: 4 / Avg: 5.07 / Max: 5.21. (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-v32131224364860SE +/- 1.25, N = 12SE +/- 1.39, N = 12SE +/- 1.48, N = 1153.7353.7454.09MIN: 36.93 / MAX: 98.94MIN: 35.64 / MAX: 80.38MIN: 36.84 / MAX: 88.861. (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-v32131122334455Min: 40.36 / Avg: 53.73 / Max: 56.58Min: 38.77 / Avg: 53.74 / Max: 56.8Min: 39.65 / Avg: 54.09 / Max: 56.771. (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: mobilenet231612182430SE +/- 0.30, N = 12SE +/- 0.34, N = 14SE +/- 0.25, N = 323.3123.4924.05MIN: 19.56 / MAX: 35.52MIN: 18.84 / MAX: 48.93MIN: 22.92 / MAX: 35.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mobilenet231612182430Min: 20.13 / Avg: 23.31 / Max: 24.23Min: 19.37 / Avg: 23.49 / Max: 24.48Min: 23.55 / Avg: 24.05 / Max: 24.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v22311.08682.17363.26044.34725.434SE +/- 0.01, N = 12SE +/- 0.02, N = 14SE +/- 0.10, N = 34.784.794.83MIN: 4.6 / MAX: 17.7MIN: 4.6 / MAX: 17.14MIN: 4.61 / MAX: 14.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v2231246810Min: 4.74 / Avg: 4.78 / Max: 4.91Min: 4.71 / Avg: 4.79 / Max: 5.04Min: 4.72 / Avg: 4.83 / Max: 5.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v32131.1342.2683.4024.5365.67SE +/- 0.11, N = 12SE +/- 0.39, N = 3SE +/- 0.11, N = 144.844.865.04MIN: 3.94 / MAX: 17.03MIN: 3.94 / MAX: 18.07MIN: 3.93 / MAX: 21.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v3213246810Min: 4.06 / Avg: 4.84 / Max: 5.12Min: 4.08 / Avg: 4.86 / Max: 5.27Min: 4.02 / Avg: 5.04 / Max: 61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v21231.27582.55163.82745.10326.379SE +/- 0.45, N = 3SE +/- 0.12, N = 12SE +/- 0.11, N = 145.275.635.67MIN: 4.23 / MAX: 15.19MIN: 4.21 / MAX: 16MIN: 4.17 / MAX: 17.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v2123246810Min: 4.36 / Avg: 5.27 / Max: 5.73Min: 4.37 / Avg: 5.63 / Max: 6.17Min: 4.33 / Avg: 5.67 / Max: 6.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet123246810SE +/- 0.64, N = 3SE +/- 0.16, N = 12SE +/- 0.14, N = 145.656.116.14MIN: 4.22 / MAX: 17.83MIN: 4.22 / MAX: 18.3MIN: 4.23 / MAX: 18.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet123246810Min: 4.38 / Avg: 5.65 / Max: 6.33Min: 4.41 / Avg: 6.11 / Max: 6.74Min: 4.4 / Avg: 6.14 / Max: 6.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b02313691215SE +/- 0.23, N = 12SE +/- 0.20, N = 14SE +/- 0.09, N = 39.169.229.51MIN: 6.55 / MAX: 21.3MIN: 6.55 / MAX: 23.86MIN: 8.98 / MAX: 21.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b02313691215Min: 6.66 / Avg: 9.16 / Max: 10.01Min: 6.65 / Avg: 9.22 / Max: 9.93Min: 9.37 / Avg: 9.51 / Max: 9.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface2310.48150.9631.44451.9262.4075SE +/- 0.04, N = 12SE +/- 0.04, N = 14SE +/- 0.01, N = 32.082.122.14MIN: 1.6 / MAX: 11.35MIN: 1.59 / MAX: 13.7MIN: 2 / MAX: 9.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface231246810Min: 1.62 / Avg: 2.08 / Max: 2.27Min: 1.62 / Avg: 2.12 / Max: 2.24Min: 2.13 / Avg: 2.14 / Max: 2.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet231510152025SE +/- 0.55, N = 12SE +/- 0.48, N = 14SE +/- 0.15, N = 320.0620.2121.08MIN: 13.91 / MAX: 34.72MIN: 13.9 / MAX: 41.6MIN: 18.84 / MAX: 98.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet231510152025Min: 14.1 / Avg: 20.06 / Max: 21.76Min: 14.09 / Avg: 20.21 / Max: 21.64Min: 20.8 / Avg: 21.08 / Max: 21.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg162311428425670SE +/- 1.15, N = 12SE +/- 1.00, N = 14SE +/- 0.25, N = 363.3763.4064.91MIN: 49.84 / MAX: 80.12MIN: 49.31 / MAX: 88.12MIN: 61.82 / MAX: 86.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg162311326395265Min: 51.33 / Avg: 63.37 / Max: 68.15Min: 50.48 / Avg: 63.4 / Max: 65.46Min: 64.42 / Avg: 64.91 / Max: 65.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet18231510152025SE +/- 0.49, N = 12SE +/- 0.42, N = 14SE +/- 0.03, N = 319.2319.2919.70MIN: 13.64 / MAX: 34.33MIN: 13.6 / MAX: 33.26MIN: 17.55 / MAX: 32.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet18231510152025Min: 13.96 / Avg: 19.23 / Max: 20.92Min: 13.95 / Avg: 19.29 / Max: 20.73Min: 19.66 / Avg: 19.7 / Max: 19.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet23148121620SE +/- 0.34, N = 12SE +/- 0.30, N = 14SE +/- 0.10, N = 316.6716.7417.17MIN: 12.68 / MAX: 30.48MIN: 12.65 / MAX: 29.93MIN: 15.16 / MAX: 29.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet23148121620Min: 13 / Avg: 16.67 / Max: 17.88Min: 12.95 / Avg: 16.74 / Max: 17.8Min: 16.99 / Avg: 17.17 / Max: 17.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet50231918273645SE +/- 0.78, N = 12SE +/- 0.68, N = 14SE +/- 0.10, N = 337.1937.3738.23MIN: 27.55 / MAX: 59.64MIN: 26.32 / MAX: 55.41MIN: 35.21 / MAX: 57.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet50231816243240Min: 28.57 / Avg: 37.19 / Max: 38.17Min: 28.54 / Avg: 37.37 / Max: 38.42Min: 38.06 / Avg: 38.23 / Max: 38.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny231816243240SE +/- 0.43, N = 12SE +/- 0.46, N = 14SE +/- 0.28, N = 334.3634.4335.31MIN: 28.26 / MAX: 48.04MIN: 27.61 / MAX: 48.44MIN: 33.42 / MAX: 52.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny231816243240Min: 29.75 / Avg: 34.36 / Max: 35.56Min: 28.56 / Avg: 34.43 / Max: 35.34Min: 34.79 / Avg: 35.31 / Max: 35.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd231714212835SE +/- 0.48, N = 12SE +/- 0.40, N = 14SE +/- 0.13, N = 330.3530.5231.18MIN: 23.91 / MAX: 42.52MIN: 24.67 / MAX: 43.96MIN: 29.85 / MAX: 43.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd231714212835Min: 25.1 / Avg: 30.35 / Max: 30.96Min: 25.32 / Avg: 30.52 / Max: 31.15Min: 30.94 / Avg: 31.18 / Max: 31.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m2313691215SE +/- 0.22, N = 12SE +/- 0.19, N = 14SE +/- 0.05, N = 311.7811.8312.04MIN: 9.3 / MAX: 23.65MIN: 9.31 / MAX: 23.35MIN: 11.53 / MAX: 23.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m23148121620Min: 9.47 / Avg: 11.78 / Max: 12.69Min: 9.47 / Avg: 11.83 / Max: 12.63Min: 11.96 / Avg: 12.04 / Max: 12.121. (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: DenseNet3219001800270036004500SE +/- 48.05, N = 4SE +/- 60.03, N = 9SE +/- 21.76, N = 33870.774250.104311.56MIN: 3636.2 / MAX: 3991.03MIN: 3687.92 / MAX: 4426.47MIN: 4221.28 / MAX: 4431.61. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNet3217001400210028003500Min: 3736.45 / Avg: 3870.77 / Max: 3953.42Min: 3773.83 / Avg: 4250.1 / Max: 4358.07Min: 4286.22 / Avg: 4311.56 / Max: 4354.871. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v231270140210280350SE +/- 0.54, N = 3SE +/- 0.37, N = 3SE +/- 2.68, N = 3298.90300.65302.08MIN: 295.46 / MAX: 308.71MIN: 295.95 / MAX: 307.25MIN: 295.89 / MAX: 470.741. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v231250100150200250Min: 298.11 / Avg: 298.9 / Max: 299.94Min: 300.06 / Avg: 300.65 / Max: 301.32Min: 298.94 / Avg: 302.08 / Max: 307.41. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v23211326395265SE +/- 0.18, N = 3SE +/- 0.06, N = 3SE +/- 0.26, N = 356.1356.5056.58MIN: 55.05 / MAX: 60.06MIN: 55.31 / MAX: 64.58MIN: 55.4 / MAX: 59.251. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v23211122334455Min: 55.94 / Avg: 56.13 / Max: 56.49Min: 56.43 / Avg: 56.5 / Max: 56.62Min: 56.2 / Avg: 56.58 / Max: 57.061. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.112360120180240300SE +/- 0.21, N = 3SE +/- 0.11, N = 3SE +/- 0.24, N = 3271.45271.76272.10MIN: 266.58 / MAX: 278.81MIN: 267.75 / MAX: 279.55MIN: 267.33 / MAX: 280.741. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.112350100150200250Min: 271.05 / Avg: 271.45 / Max: 271.78Min: 271.64 / Avg: 271.76 / Max: 271.99Min: 271.67 / Avg: 272.1 / Max: 272.491. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl