tigerlake ncnn

Intel Core i7-1165G7 testing with a Dell 0GG9PT (1.0.3 BIOS) and Intel UHD 3GB on Ubuntu 20.10 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 2012186-HA-TIGERLAKE59
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
December 18 2020
  2 Hours, 47 Minutes
2
December 18 2020
  2 Hours, 23 Minutes
3
December 18 2020
  2 Hours, 22 Minutes
4
December 18 2020
  2 Hours, 23 Minutes
Invert Hiding All Results Option
  2 Hours, 29 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

Compiler Notes: --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/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-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 Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3
Security Notes: 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

Processor: Intel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads), Motherboard: Dell 0GG9PT (1.0.3 BIOS), Chipset: Intel Tiger Lake-LP, Memory: 16GB, Disk: Kioxia KBG40ZNS256G NVMe 256GB, Graphics: Intel UHD 3GB (1300MHz), Audio: Realtek ALC289, Network: Intel Wi-Fi 6 AX201

OS: Ubuntu 20.10, Kernel: 5.10.0-051000rc7daily20201213-generic (x86_64) 20201212, Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: modesetting 1.20.9, OpenGL: 4.6 Mesa 20.2.1, Vulkan: 1.2.145, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1200

tigerlake ncnnProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen Resolution1234Intel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads)Dell 0GG9PT (1.0.3 BIOS)Intel Tiger Lake-LP16GBKioxia KBG40ZNS256G NVMe 256GBIntel UHD 3GB (1300MHz)Realtek ALC289Intel Wi-Fi 6 AX201Ubuntu 20.105.10.0-051000rc7daily20201213-generic (x86_64) 20201212GNOME Shell 3.38.1X Server 1.20.9modesetting 1.20.94.6 Mesa 20.2.11.2.145GCC 10.2.0ext41920x1200OpenBenchmarking.orgCompiler 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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/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-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: 0x60 - Thermald 2.3Security 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

1234Result OverviewPhoronix Test Suite100%103%107%110%114%NCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNVulkan GPU - mnasnetVulkan GPU - efficientnet-b0CPU - googlenetVulkan GPU - blazefaceCPU - blazefaceVulkan GPU - regnety_400mVulkan GPU - googlenetCPU-v3-v3 - mobilenet-v3CPU-v2-v2 - mobilenet-v2CPU - mnasnetCPU - shufflenet-v2Vulkan GPU-v2-v2 - mobilenet-v2CPU - efficientnet-b0CPU - mobilenetVulkan GPU - shufflenet-v2CPU - regnety_400mCPU - yolov4-tinyVulkan GPU - resnet18CPU - squeezenet_ssdCPU - resnet18Vulkan GPU - alexnetCPU - vgg16CPU - alexnetVulkan GPU - resnet50Vulkan GPU - mobilenetCPU - resnet50Vulkan GPU-v3-v3 - mobilenet-v3Vulkan GPU - yolov4-tinyVulkan GPU - vgg16Vulkan GPU - squeezenet_ssd

tigerlake ncnnncnn: 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_400m123430.406.826.659.157.0310.342.4322.3568.3221.0318.0049.0239.3032.8916.7330.236.586.399.017.7311.352.6423.5068.5421.0118.0048.9539.2233.0117.6630.086.596.408.876.8310.072.5823.8268.7321.1918.1749.2839.1632.9716.4630.286.796.438.836.8010.112.3822.3668.9521.2118.2049.3739.3133.1216.3730.026.646.408.866.8510.042.3821.2468.3521.1718.0449.0339.0832.7416.4130.036.666.418.876.8110.102.3722.1268.7421.2818.1249.3839.0733.0016.4930.826.706.448.896.8010.032.3822.0369.0221.2718.1549.3539.6233.1616.4930.156.596.428.836.7910.032.3722.0468.6021.2718.1149.2739.1233.0116.38OpenBenchmarking.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 20201218Target: CPU - Model: mobilenet1234714212835SE +/- 0.36, N = 4SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.35, N = 330.4030.0830.0230.82MIN: 28.11 / MAX: 91.92MIN: 29.58 / MAX: 43.23MIN: 29.67 / MAX: 42.99MIN: 29.68 / MAX: 43.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenet1234714212835Min: 29.91 / Avg: 30.4 / Max: 31.47Min: 30.04 / Avg: 30.08 / Max: 30.13Min: 29.96 / Avg: 30.02 / Max: 30.05Min: 30.13 / Avg: 30.82 / Max: 31.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v21234246810SE +/- 0.46, N = 4SE +/- 0.57, N = 3SE +/- 0.60, N = 3SE +/- 0.60, N = 36.826.596.646.70MIN: 5.35 / MAX: 15.23MIN: 5.36 / MAX: 12.76MIN: 5.35 / MAX: 12.93MIN: 5.35 / MAX: 20.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v212343691215Min: 5.47 / Avg: 6.82 / Max: 7.41Min: 5.46 / Avg: 6.59 / Max: 7.24Min: 5.45 / Avg: 6.64 / Max: 7.36Min: 5.5 / Avg: 6.7 / Max: 7.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v31234246810SE +/- 0.67, N = 4SE +/- 0.91, N = 3SE +/- 0.90, N = 3SE +/- 0.91, N = 36.656.406.406.44MIN: 4.55 / MAX: 14.51MIN: 4.54 / MAX: 12.09MIN: 4.54 / MAX: 11.23MIN: 4.58 / MAX: 13.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v312343691215Min: 4.65 / Avg: 6.65 / Max: 7.38Min: 4.58 / Avg: 6.4 / Max: 7.32Min: 4.6 / Avg: 6.4 / Max: 7.32Min: 4.63 / Avg: 6.44 / Max: 7.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v212343691215SE +/- 0.91, N = 4SE +/- 1.20, N = 3SE +/- 1.23, N = 3SE +/- 1.22, N = 39.158.878.868.89MIN: 6.37 / MAX: 21.38MIN: 6.4 / MAX: 14.97MIN: 6.34 / MAX: 17.92MIN: 6.37 / MAX: 25.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v212343691215Min: 6.42 / Avg: 9.15 / Max: 10.07Min: 6.46 / Avg: 8.87 / Max: 10.07Min: 6.41 / Avg: 8.86 / Max: 10.13Min: 6.44 / Avg: 8.89 / Max: 10.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnet1234246810SE +/- 0.60, N = 4SE +/- 0.85, N = 3SE +/- 0.85, N = 3SE +/- 0.83, N = 37.036.836.856.80MIN: 5.07 / MAX: 14.06MIN: 5.08 / MAX: 19.65MIN: 5.07 / MAX: 20.78MIN: 5.09 / MAX: 8.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnet12343691215Min: 5.23 / Avg: 7.03 / Max: 7.64Min: 5.13 / Avg: 6.83 / Max: 7.69Min: 5.14 / Avg: 6.85 / Max: 7.73Min: 5.15 / Avg: 6.8 / Max: 7.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b012343691215SE +/- 0.94, N = 4SE +/- 1.25, N = 3SE +/- 1.28, N = 3SE +/- 1.27, N = 310.3410.0710.0410.03MIN: 7.42 / MAX: 17.72MIN: 7.45 / MAX: 17.13MIN: 7.42 / MAX: 13.73MIN: 7.44 / MAX: 13.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b012343691215Min: 7.51 / Avg: 10.34 / Max: 11.3Min: 7.57 / Avg: 10.07 / Max: 11.35Min: 7.48 / Avg: 10.04 / Max: 11.33Min: 7.5 / Avg: 10.03 / Max: 11.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazeface12340.58051.1611.74152.3222.9025SE +/- 0.19, N = 4SE +/- 0.05, N = 3SE +/- 0.27, N = 3SE +/- 0.25, N = 32.432.582.382.38MIN: 1.83 / MAX: 4.69MIN: 1.98 / MAX: 8.09MIN: 1.83 / MAX: 2.8MIN: 1.84 / MAX: 6.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazeface1234246810Min: 1.85 / Avg: 2.43 / Max: 2.63Min: 2.48 / Avg: 2.58 / Max: 2.65Min: 1.85 / Avg: 2.38 / Max: 2.66Min: 1.88 / Avg: 2.38 / Max: 2.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenet1234612182430SE +/- 1.00, N = 4SE +/- 0.33, N = 3SE +/- 2.23, N = 3SE +/- 1.46, N = 322.3523.8221.2422.03MIN: 14.76 / MAX: 38.22MIN: 21.27 / MAX: 38.57MIN: 14.74 / MAX: 36.92MIN: 14.73 / MAX: 37.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenet1234612182430Min: 19.35 / Avg: 22.35 / Max: 23.48Min: 23.44 / Avg: 23.82 / Max: 24.49Min: 16.79 / Avg: 21.24 / Max: 23.58Min: 19.12 / Avg: 22.03 / Max: 23.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg1612341530456075SE +/- 0.24, N = 4SE +/- 0.23, N = 3SE +/- 0.32, N = 3SE +/- 0.20, N = 368.3268.7368.3569.02MIN: 63.68 / MAX: 90.5MIN: 64.27 / MAX: 82.9MIN: 63.74 / MAX: 81.55MIN: 63.92 / MAX: 85.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg1612341326395265Min: 68.01 / Avg: 68.32 / Max: 69.02Min: 68.42 / Avg: 68.73 / Max: 69.19Min: 67.83 / Avg: 68.35 / Max: 68.94Min: 68.68 / Avg: 69.02 / Max: 69.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet181234510152025SE +/- 0.10, N = 4SE +/- 0.15, N = 3SE +/- 0.14, N = 3SE +/- 0.19, N = 321.0321.1921.1721.27MIN: 18.4 / MAX: 27.66MIN: 18.46 / MAX: 28.37MIN: 18.38 / MAX: 35.72MIN: 18.41 / MAX: 35.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet181234510152025Min: 20.88 / Avg: 21.03 / Max: 21.31Min: 21.04 / Avg: 21.19 / Max: 21.49Min: 21.02 / Avg: 21.17 / Max: 21.44Min: 21.04 / Avg: 21.27 / Max: 21.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnet123448121620SE +/- 0.05, N = 4SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 318.0018.1718.0418.15MIN: 16.03 / MAX: 30.98MIN: 16.03 / MAX: 32.33MIN: 15.98 / MAX: 30.89MIN: 16.07 / MAX: 29.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnet1234510152025Min: 17.88 / Avg: 18 / Max: 18.1Min: 18.04 / Avg: 18.17 / Max: 18.4Min: 17.92 / Avg: 18.04 / Max: 18.11Min: 18.02 / Avg: 18.15 / Max: 18.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet5012341122334455SE +/- 0.12, N = 4SE +/- 0.06, N = 3SE +/- 0.20, N = 3SE +/- 0.16, N = 349.0249.2849.0349.35MIN: 45.35 / MAX: 62.18MIN: 46.34 / MAX: 65.16MIN: 45.37 / MAX: 62.61MIN: 46.76 / MAX: 59.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet5012341020304050Min: 48.82 / Avg: 49.02 / Max: 49.37Min: 49.17 / Avg: 49.28 / Max: 49.39Min: 48.73 / Avg: 49.03 / Max: 49.4Min: 49.13 / Avg: 49.35 / Max: 49.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tiny1234918273645SE +/- 0.32, N = 4SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.21, N = 339.3039.1639.0839.62MIN: 37.57 / MAX: 50.85MIN: 37.71 / MAX: 50.95MIN: 37.75 / MAX: 50.24MIN: 37.77 / MAX: 50.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tiny1234816243240Min: 38.96 / Avg: 39.3 / Max: 40.26Min: 39.1 / Avg: 39.16 / Max: 39.21Min: 38.98 / Avg: 39.08 / Max: 39.15Min: 39.21 / Avg: 39.62 / Max: 39.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssd1234816243240SE +/- 0.15, N = 4SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 332.8932.9732.7433.16MIN: 32.16 / MAX: 46.07MIN: 32.08 / MAX: 45.76MIN: 32.1 / MAX: 39.45MIN: 32.16 / MAX: 45.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssd1234714212835Min: 32.65 / Avg: 32.89 / Max: 33.33Min: 32.92 / Avg: 32.97 / Max: 33.02Min: 32.59 / Avg: 32.74 / Max: 32.87Min: 32.98 / Avg: 33.16 / Max: 33.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400m123448121620SE +/- 0.92, N = 4SE +/- 1.23, N = 3SE +/- 1.28, N = 3SE +/- 1.26, N = 316.7316.4616.4116.49MIN: 13.74 / MAX: 26.09MIN: 13.73 / MAX: 23.5MIN: 13.7 / MAX: 19.59MIN: 13.73 / MAX: 23.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400m123448121620Min: 13.96 / Avg: 16.73 / Max: 17.68Min: 13.99 / Avg: 16.46 / Max: 17.7Min: 13.84 / Avg: 16.41 / Max: 17.77Min: 13.97 / Avg: 16.49 / Max: 17.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mobilenet1234714212835SE +/- 0.22, N = 3SE +/- 0.19, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 330.2330.2830.0330.15MIN: 28.87 / MAX: 39.97MIN: 29.65 / MAX: 43.55MIN: 29.63 / MAX: 43.15MIN: 29.62 / MAX: 42.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mobilenet1234714212835Min: 30 / Avg: 30.23 / Max: 30.67Min: 30.03 / Avg: 30.28 / Max: 30.64Min: 29.99 / Avg: 30.03 / Max: 30.07Min: 30.01 / Avg: 30.15 / Max: 30.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v2-v2 - Model: mobilenet-v21234246810SE +/- 0.52, N = 3SE +/- 0.65, N = 3SE +/- 0.57, N = 3SE +/- 0.55, N = 36.586.796.666.59MIN: 5.36 / MAX: 14.93MIN: 5.37 / MAX: 12.66MIN: 5.37 / MAX: 12.77MIN: 5.36 / MAX: 12.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v2-v2 - Model: mobilenet-v212343691215Min: 5.54 / Avg: 6.58 / Max: 7.2Min: 5.53 / Avg: 6.79 / Max: 7.71Min: 5.52 / Avg: 6.66 / Max: 7.31Min: 5.5 / Avg: 6.59 / Max: 7.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v3-v3 - Model: mobilenet-v31234246810SE +/- 0.90, N = 3SE +/- 0.87, N = 3SE +/- 0.89, N = 3SE +/- 0.89, N = 36.396.436.416.42MIN: 4.54 / MAX: 11.19MIN: 4.57 / MAX: 11.03MIN: 4.55 / MAX: 11.21MIN: 4.57 / MAX: 11.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v3-v3 - Model: mobilenet-v312343691215Min: 4.6 / Avg: 6.39 / Max: 7.3Min: 4.68 / Avg: 6.43 / Max: 7.31Min: 4.62 / Avg: 6.41 / Max: 7.32Min: 4.64 / Avg: 6.42 / Max: 7.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: shufflenet-v212343691215SE +/- 1.03, N = 3SE +/- 1.17, N = 3SE +/- 1.19, N = 3SE +/- 1.21, N = 39.018.838.878.83MIN: 6.36 / MAX: 16.12MIN: 6.38 / MAX: 13.74MIN: 6.38 / MAX: 16.18MIN: 6.35 / MAX: 13.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: shufflenet-v212343691215Min: 6.95 / Avg: 9.01 / Max: 10.05Min: 6.49 / Avg: 8.83 / Max: 10.03Min: 6.49 / Avg: 8.87 / Max: 10.1Min: 6.41 / Avg: 8.83 / Max: 10.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mnasnet1234246810SE +/- 0.08, N = 3SE +/- 0.81, N = 3SE +/- 0.83, N = 3SE +/- 0.82, N = 37.736.806.816.79MIN: 7.34 / MAX: 20.41MIN: 5.09 / MAX: 9.99MIN: 5.07 / MAX: 10.05MIN: 5.07 / MAX: 9.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mnasnet12343691215Min: 7.61 / Avg: 7.73 / Max: 7.88Min: 5.19 / Avg: 6.8 / Max: 7.61Min: 5.16 / Avg: 6.81 / Max: 7.65Min: 5.16 / Avg: 6.79 / Max: 7.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: efficientnet-b012343691215SE +/- 0.05, N = 3SE +/- 1.29, N = 3SE +/- 1.30, N = 3SE +/- 1.26, N = 311.3510.1110.1010.03MIN: 10.87 / MAX: 17.57MIN: 7.45 / MAX: 13.74MIN: 7.46 / MAX: 17.57MIN: 7.45 / MAX: 25.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: efficientnet-b012343691215Min: 11.28 / Avg: 11.35 / Max: 11.46Min: 7.53 / Avg: 10.11 / Max: 11.47Min: 7.51 / Avg: 10.1 / Max: 11.41Min: 7.51 / Avg: 10.03 / Max: 11.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: blazeface12340.5941.1881.7822.3762.97SE +/- 0.02, N = 3SE +/- 0.26, N = 3SE +/- 0.25, N = 3SE +/- 0.27, N = 32.642.382.372.37MIN: 2.48 / MAX: 8.71MIN: 1.84 / MAX: 4.81MIN: 1.84 / MAX: 2.77MIN: 1.82 / MAX: 4.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: blazeface1234246810Min: 2.61 / Avg: 2.64 / Max: 2.67Min: 1.86 / Avg: 2.38 / Max: 2.65Min: 1.86 / Avg: 2.37 / Max: 2.62Min: 1.84 / Avg: 2.37 / Max: 2.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: googlenet1234612182430SE +/- 0.14, N = 3SE +/- 1.32, N = 3SE +/- 1.28, N = 3SE +/- 1.40, N = 323.5022.3622.1222.04MIN: 21.26 / MAX: 36.15MIN: 14.76 / MAX: 37.73MIN: 14.75 / MAX: 28.73MIN: 14.77 / MAX: 31.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: googlenet1234510152025Min: 23.26 / Avg: 23.5 / Max: 23.75Min: 19.74 / Avg: 22.36 / Max: 23.93Min: 19.56 / Avg: 22.12 / Max: 23.43Min: 19.24 / Avg: 22.04 / Max: 23.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: vgg1612341530456075SE +/- 0.19, N = 3SE +/- 0.37, N = 3SE +/- 0.39, N = 3SE +/- 0.40, N = 368.5468.9568.7468.60MIN: 63.96 / MAX: 82.97MIN: 63.87 / MAX: 84.6MIN: 63.96 / MAX: 82.53MIN: 63.79 / MAX: 85.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: vgg1612341326395265Min: 68.25 / Avg: 68.54 / Max: 68.89Min: 68.35 / Avg: 68.95 / Max: 69.64Min: 68.33 / Avg: 68.74 / Max: 69.52Min: 68.16 / Avg: 68.6 / Max: 69.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet181234510152025SE +/- 0.04, N = 3SE +/- 0.23, N = 3SE +/- 0.26, N = 3SE +/- 0.23, N = 321.0121.2121.2821.27MIN: 18.41 / MAX: 33.62MIN: 18.37 / MAX: 28.23MIN: 18.42 / MAX: 33.68MIN: 18.36 / MAX: 35.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet181234510152025Min: 20.93 / Avg: 21.01 / Max: 21.08Min: 20.94 / Avg: 21.21 / Max: 21.66Min: 20.97 / Avg: 21.28 / Max: 21.79Min: 21.01 / Avg: 21.27 / Max: 21.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: alexnet123448121620SE +/- 0.07, N = 3SE +/- 0.13, N = 3SE +/- 0.11, N = 3SE +/- 0.13, N = 318.0018.2018.1218.11MIN: 16.01 / MAX: 23.62MIN: 16.01 / MAX: 24.53MIN: 16.02 / MAX: 30.54MIN: 16.02 / MAX: 23.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: alexnet1234510152025Min: 17.92 / Avg: 18 / Max: 18.14Min: 17.95 / Avg: 18.2 / Max: 18.38Min: 17.99 / Avg: 18.12 / Max: 18.33Min: 17.94 / Avg: 18.11 / Max: 18.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet5012341122334455SE +/- 0.01, N = 3SE +/- 0.18, N = 3SE +/- 0.11, N = 3SE +/- 0.15, N = 348.9549.3749.3849.27MIN: 46.42 / MAX: 58.97MIN: 45.9 / MAX: 63.19MIN: 46.54 / MAX: 63.38MIN: 46.92 / MAX: 63.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet5012341020304050Min: 48.92 / Avg: 48.95 / Max: 48.96Min: 49.18 / Avg: 49.37 / Max: 49.72Min: 49.16 / Avg: 49.38 / Max: 49.55Min: 49.05 / Avg: 49.27 / Max: 49.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: yolov4-tiny1234918273645SE +/- 0.20, N = 3SE +/- 0.20, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 339.2239.3139.0739.12MIN: 37.72 / MAX: 51.81MIN: 37.8 / MAX: 51.31MIN: 37.69 / MAX: 52.09MIN: 37.73 / MAX: 50.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: yolov4-tiny1234816243240Min: 39.02 / Avg: 39.22 / Max: 39.63Min: 39.11 / Avg: 39.31 / Max: 39.7Min: 39.04 / Avg: 39.07 / Max: 39.09Min: 39 / Avg: 39.12 / Max: 39.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: squeezenet_ssd1234816243240SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 333.0133.1233.0033.01MIN: 32.18 / MAX: 45.46MIN: 32.15 / MAX: 45.6MIN: 32.16 / MAX: 45.66MIN: 32.05 / MAX: 46.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: squeezenet_ssd1234714212835Min: 32.93 / Avg: 33.01 / Max: 33.16Min: 32.99 / Avg: 33.12 / Max: 33.26Min: 32.85 / Avg: 33 / Max: 33.21Min: 32.95 / Avg: 33.01 / Max: 33.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: regnety_400m123448121620SE +/- 0.10, N = 3SE +/- 1.26, N = 3SE +/- 1.31, N = 3SE +/- 1.28, N = 317.6616.3716.4916.38MIN: 17.3 / MAX: 23.73MIN: 13.72 / MAX: 20.92MIN: 13.75 / MAX: 29.67MIN: 13.71 / MAX: 23.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: regnety_400m123448121620Min: 17.53 / Avg: 17.66 / Max: 17.85Min: 13.86 / Avg: 16.37 / Max: 17.74Min: 13.86 / Avg: 16.49 / Max: 17.84Min: 13.82 / Avg: 16.38 / Max: 17.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

1

Compiler Notes: --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/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-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 Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3
Security Notes: 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 December 2020 10:08 by user phoronix.

2

Compiler Notes: --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/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-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 Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3
Security Notes: 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 December 2020 10:21 by user phoronix.

3

Compiler Notes: --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/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-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 Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3
Security Notes: 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 December 2020 10:42 by user phoronix.

4

Processor: Intel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads), Motherboard: Dell 0GG9PT (1.0.3 BIOS), Chipset: Intel Tiger Lake-LP, Memory: 16GB, Disk: Kioxia KBG40ZNS256G NVMe 256GB, Graphics: Intel UHD 3GB (1300MHz), Audio: Realtek ALC289, Network: Intel Wi-Fi 6 AX201

OS: Ubuntu 20.10, Kernel: 5.10.0-051000rc7daily20201213-generic (x86_64) 20201212, Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: modesetting 1.20.9, OpenGL: 4.6 Mesa 20.2.1, Vulkan: 1.2.145, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1200

Compiler Notes: --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/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-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 Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3
Security Notes: 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 December 2020 10:56 by user phoronix.