11900k nn

Intel Core i9-11900K testing with a ASUS ROG MAXIMUS XIII HERO (0707 BIOS) and AMD Radeon VII 16GB on Fedora 34 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 2106186-IB-11900KNN693
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
Allow Limiting Results To Certain Suite(s)

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
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
1
June 18 2021
  1 Hour, 11 Minutes
2
June 18 2021
  1 Hour, 11 Minutes
3
June 18 2021
  1 Hour, 11 Minutes
4
June 18 2021
  1 Hour, 11 Minutes
5
June 18 2021
  1 Hour, 11 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 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):

1

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x3c - Thermald 2.4.4
Security Notes: SELinux + 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

2

3

4

5

Processor: Intel Core i9-11900K @ 5.10GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG MAXIMUS XIII HERO (0707 BIOS), Chipset: Intel Tiger Lake-H, Memory: 32GB, Disk: 2000GB Corsair Force MP600 + 257GB Flash Drive, Graphics: AMD Radeon VII 16GB (1801/1000MHz), Audio: Intel Tiger Lake-H HD Audio, Monitor: ASUS MG28U, Network: 2 x Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Fedora 34, Kernel: 5.12.9-300.fc34.x86_64 (x86_64), Desktop: GNOME Shell 40.1, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 21.1.1 (LLVM 12.0.0), Compiler: GCC 11.1.1 20210531 + Clang 12.0.0, File-System: btrfs, Screen Resolution: 3840x2160

11900k nnProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen Resolution12345Intel Core i9-11900K @ 5.10GHz (8 Cores / 16 Threads)ASUS ROG MAXIMUS XIII HERO (0707 BIOS)Intel Tiger Lake-H32GB2000GB Corsair Force MP600 + 257GB Flash DriveAMD Radeon VII 16GB (1801/1000MHz)Intel Tiger Lake-H HD AudioASUS MG28U2 x Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Fedora 345.12.9-300.fc34.x86_64 (x86_64)GNOME Shell 40.1X Server + Wayland4.6 Mesa 21.1.1 (LLVM 12.0.0)GCC 11.1.1 20210531 + Clang 12.0.0btrfs3840x2160OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver Processor Details- Scaling Governor: intel_pstate powersave - CPU Microcode: 0x3c - Thermald 2.4.4 Security Details- SELinux + 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

12345Result OverviewPhoronix Test Suite100%100%101%101%101%NCNNMobile Neural NetworkTNN

11900k nnncnn: CPU - yolov4-tinyncnn: CPU - resnet18ncnn: CPU - blazefacencnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - googlenetncnn: CPU - resnet50ncnn: CPU - mobilenetmnn: SqueezeNetV1.0ncnn: CPU - regnety_400mncnn: CPU - mnasnetncnn: CPU-v3-v3 - mobilenet-v3mnn: MobileNetV2_224mnn: squeezenetv1.1mnn: mobilenet-v1-1.0ncnn: CPU - shufflenet-v2ncnn: CPU - efficientnet-b0mnn: inception-v3ncnn: CPU - squeezenet_ssdtnn: CPU - DenseNetmnn: resnet-v2-50ncnn: CPU - vgg16ncnn: CPU - alexnetmnn: mobilenetV3tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.1tnn: CPU - MobileNet v21234519.8511.551.103.6210.6219.4213.013.7146.182.582.831.9202.3091.7892.564.6025.02715.902729.91518.39655.169.921.05447.581236.356247.94619.3811.211.073.5910.3519.1812.863.6926.122.602.811.9062.2981.7852.554.6024.93515.832742.15218.43155.099.931.05447.644236.412247.98119.5411.031.083.6810.3718.9413.023.7326.142.622.821.9332.3271.7862.574.6124.99415.802732.99218.48254.959.931.05247.541236.576247.95719.0811.031.083.5810.3519.0012.883.7546.132.62.811.9292.3261.7792.574.5925.09315.802725.75118.47354.969.901.05547.651236.648247.96820.3311.241.063.5810.3818.9413.153.6996.082.582.791.9222.3161.7732.554.5824.97315.842729.31818.40154.929.941.05247.569236.689247.967OpenBenchmarking.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 20210525Target: CPU - Model: yolov4-tiny54321510152025SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.45, N = 3SE +/- 0.34, N = 3SE +/- 0.41, N = 320.3319.0819.5419.3819.85MIN: 19.92 / MAX: 28.22MIN: 18.9 / MAX: 24.61MIN: 18.94 / MAX: 23.96MIN: 18.88 / MAX: 23.58MIN: 18.93 / MAX: 25.281. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet18543213691215SE +/- 0.16, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.16, N = 3SE +/- 0.02, N = 311.2411.0311.0311.2111.55MIN: 10.97 / MAX: 15.06MIN: 10.92 / MAX: 14.53MIN: 10.91 / MAX: 14.54MIN: 10.93 / MAX: 16.12MIN: 11.44 / MAX: 15.011. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface543210.24750.4950.74250.991.2375SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 31.061.081.081.071.10MIN: 1.04 / MAX: 1.76MIN: 1.05 / MAX: 4.51MIN: 1.05 / MAX: 1.6MIN: 1.04 / MAX: 2.99MIN: 1.05 / MAX: 1.51. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v2543210.8281.6562.4843.3124.14SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 33.583.583.683.593.62MIN: 3.45 / MAX: 7.23MIN: 3.45 / MAX: 7.01MIN: 3.48 / MAX: 7.42MIN: 3.44 / MAX: 7.21MIN: 3.48 / MAX: 7.051. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet543213691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.22, N = 310.3810.3510.3710.3510.62MIN: 10.26 / MAX: 13.98MIN: 10.25 / MAX: 13.87MIN: 10.26 / MAX: 14.08MIN: 10.25 / MAX: 13.93MIN: 10.29 / MAX: 15.751. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet5054321510152025SE +/- 0.21, N = 3SE +/- 0.26, N = 3SE +/- 0.23, N = 3SE +/- 0.22, N = 3SE +/- 0.03, N = 318.9419.0018.9419.1819.42MIN: 18.56 / MAX: 23.02MIN: 18.49 / MAX: 23.09MIN: 18.52 / MAX: 22.93MIN: 18.58 / MAX: 23MIN: 19.18 / MAX: 24.091. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mobilenet543213691215SE +/- 0.14, N = 3SE +/- 0.02, N = 3SE +/- 0.16, N = 3SE +/- 0.00, N = 3SE +/- 0.16, N = 313.1512.8813.0212.8613.01MIN: 12.74 / MAX: 16.85MIN: 12.7 / MAX: 16.62MIN: 12.72 / MAX: 16.75MIN: 12.74 / MAX: 16.45MIN: 12.71 / MAX: 16.871. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

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: SqueezeNetV1.0543210.84471.68942.53413.37884.2235SE +/- 0.050, N = 3SE +/- 0.030, N = 3SE +/- 0.036, N = 3SE +/- 0.072, N = 3SE +/- 0.043, N = 33.6993.7543.7323.6923.714MIN: 3.56 / MAX: 8.16MIN: 3.66 / MAX: 7.94MIN: 3.64 / MAX: 7.94MIN: 3.51 / MAX: 11.39MIN: 3.58 / MAX: 10.871. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -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: regnety_400m54321246810SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 36.086.136.146.126.18MIN: 5.99 / MAX: 9.68MIN: 6.03 / MAX: 9.7MIN: 6.04 / MAX: 9.7MIN: 6 / MAX: 10.83MIN: 6.06 / MAX: 14.11. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet543210.58951.1791.76852.3582.9475SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 32.582.602.622.602.58MIN: 2.53 / MAX: 6.12MIN: 2.54 / MAX: 6.17MIN: 2.54 / MAX: 7.34MIN: 2.54 / MAX: 6.09MIN: 2.54 / MAX: 3.061. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v3543210.63681.27361.91042.54723.184SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 32.792.812.822.812.83MIN: 2.74 / MAX: 6.27MIN: 2.74 / MAX: 6.36MIN: 2.76 / MAX: 6.38MIN: 2.74 / MAX: 6.27MIN: 2.76 / MAX: 6.361. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

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: MobileNetV2_224543210.43490.86981.30471.73962.1745SE +/- 0.007, N = 3SE +/- 0.019, N = 3SE +/- 0.019, N = 3SE +/- 0.020, N = 3SE +/- 0.007, N = 31.9221.9291.9331.9061.920MIN: 1.86 / MAX: 6.49MIN: 1.87 / MAX: 6.18MIN: 1.88 / MAX: 6.1MIN: 1.84 / MAX: 6.13MIN: 1.86 / 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 -O2 -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.1543210.52361.04721.57082.09442.618SE +/- 0.023, N = 3SE +/- 0.010, N = 3SE +/- 0.006, N = 3SE +/- 0.016, N = 3SE +/- 0.019, N = 32.3162.3262.3272.2982.309MIN: 2.25 / MAX: 6.42MIN: 2.29 / MAX: 6.5MIN: 2.29 / MAX: 8.21MIN: 2.25 / MAX: 6.43MIN: 2.25 / MAX: 8.081. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenet-v1-1.0543210.40250.8051.20751.612.0125SE +/- 0.003, N = 3SE +/- 0.006, N = 3SE +/- 0.011, N = 3SE +/- 0.002, N = 3SE +/- 0.007, N = 31.7731.7791.7861.7851.789MIN: 1.75 / MAX: 5.97MIN: 1.75 / MAX: 5.99MIN: 1.74 / MAX: 7.77MIN: 1.75 / MAX: 5.99MIN: 1.76 / MAX: 8.171. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -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: shufflenet-v2543210.57831.15661.73492.31322.8915SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 32.552.572.572.552.56MIN: 2.5 / MAX: 6.13MIN: 2.5 / MAX: 6.11MIN: 2.52 / MAX: 6.06MIN: 2.5 / MAX: 6.12MIN: 2.51 / MAX: 6.111. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b0543211.03732.07463.11194.14925.1865SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 34.584.594.614.604.60MIN: 4.51 / MAX: 8.14MIN: 4.51 / MAX: 8.13MIN: 4.52 / MAX: 8.15MIN: 4.52 / MAX: 15.48MIN: 4.52 / MAX: 8.21. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

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: inception-v354321612182430SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.18, N = 3SE +/- 0.09, N = 324.9725.0924.9924.9425.03MIN: 24.66 / MAX: 31.87MIN: 24.64 / MAX: 30.76MIN: 24.49 / MAX: 30.91MIN: 24.2 / MAX: 32.34MIN: 24.71 / MAX: 47.271. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -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: squeezenet_ssd5432148121620SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 315.8415.8015.8015.8315.90MIN: 15.66 / MAX: 21.49MIN: 15.62 / MAX: 21.44MIN: 15.61 / MAX: 21.35MIN: 15.68 / MAX: 19.42MIN: 15.75 / MAX: 19.491. (CXX) g++ options: -O2 -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: DenseNet543216001200180024003000SE +/- 4.23, N = 3SE +/- 2.38, N = 3SE +/- 4.47, N = 3SE +/- 13.01, N = 3SE +/- 1.83, N = 32729.322725.752732.992742.152729.92MIN: 2681.16 / MAX: 2806.06MIN: 2677.6 / MAX: 2798.43MIN: 2680.56 / MAX: 3092.99MIN: 2686.2 / MAX: 4541.51MIN: 2687.25 / MAX: 2798.771. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O2 -rdynamic -ldl

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: resnet-v2-5054321510152025SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 318.4018.4718.4818.4318.40MIN: 18.16 / MAX: 23.67MIN: 18.24 / MAX: 24.7MIN: 18.32 / MAX: 25.47MIN: 18.1 / MAX: 24.51MIN: 18.12 / MAX: 22.711. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -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: vgg16543211224364860SE +/- 0.18, N = 3SE +/- 0.16, N = 3SE +/- 0.10, N = 3SE +/- 0.17, N = 3SE +/- 0.04, N = 354.9254.9654.9555.0955.16MIN: 54.42 / MAX: 61.33MIN: 54.51 / MAX: 58.77MIN: 54.46 / MAX: 58.49MIN: 54.47 / MAX: 60.23MIN: 54.78 / MAX: 61.421. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet543213691215SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 39.949.909.939.939.92MIN: 9.83 / MAX: 13.45MIN: 9.81 / MAX: 13.39MIN: 9.84 / MAX: 14.56MIN: 9.81 / MAX: 13.7MIN: 9.83 / MAX: 13.411. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread -pthread

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: mobilenetV3543210.23740.47480.71220.94961.187SE +/- 0.004, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.004, N = 3SE +/- 0.003, N = 31.0521.0551.0521.0541.054MIN: 1.03 / MAX: 5.16MIN: 1.03 / MAX: 5.16MIN: 1.03 / MAX: 3.1MIN: 1.03 / MAX: 5.12MIN: 1.03 / MAX: 5.151. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl

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: SqueezeNet v2543211122334455SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.10, N = 3SE +/- 0.20, N = 3SE +/- 0.08, N = 347.5747.6547.5447.6447.58MIN: 47.17 / MAX: 48.04MIN: 47.15 / MAX: 48.9MIN: 47.01 / MAX: 48.19MIN: 47.11 / MAX: 49.66MIN: 47.16 / MAX: 48.911. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O2 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.15432150100150200250SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3236.69236.65236.58236.41236.36MIN: 235.56 / MAX: 237.66MIN: 235.17 / MAX: 237.76MIN: 235.32 / MAX: 238.16MIN: 235.25 / MAX: 237.65MIN: 235.09 / MAX: 237.421. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O2 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v25432150100150200250SE +/- 0.12, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3247.97247.97247.96247.98247.95MIN: 246.64 / MAX: 251.21MIN: 246.44 / MAX: 251.35MIN: 246.77 / MAX: 250.93MIN: 246.76 / MAX: 250.95MIN: 246.98 / MAX: 251.871. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O2 -rdynamic -ldl

1

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x3c - Thermald 2.4.4
Security Notes: SELinux + 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

Testing initiated at 18 June 2021 07:53 by user phoronix.

2

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x3c - Thermald 2.4.4
Security Notes: SELinux + 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

Testing initiated at 18 June 2021 08:19 by user phoronix.

3

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x3c - Thermald 2.4.4
Security Notes: SELinux + 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

Testing initiated at 18 June 2021 11:42 by user phoronix.

4

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x3c - Thermald 2.4.4
Security Notes: SELinux + 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

Testing initiated at 18 June 2021 12:04 by user phoronix.

5

Processor: Intel Core i9-11900K @ 5.10GHz (8 Cores / 16 Threads), Motherboard: ASUS ROG MAXIMUS XIII HERO (0707 BIOS), Chipset: Intel Tiger Lake-H, Memory: 32GB, Disk: 2000GB Corsair Force MP600 + 257GB Flash Drive, Graphics: AMD Radeon VII 16GB (1801/1000MHz), Audio: Intel Tiger Lake-H HD Audio, Monitor: ASUS MG28U, Network: 2 x Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Fedora 34, Kernel: 5.12.9-300.fc34.x86_64 (x86_64), Desktop: GNOME Shell 40.1, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 21.1.1 (LLVM 12.0.0), Compiler: GCC 11.1.1 20210531 + Clang 12.0.0, File-System: btrfs, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x3c - Thermald 2.4.4
Security Notes: SELinux + 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

Testing initiated at 18 June 2021 12:25 by user phoronix.