vulkan-benchmarks

AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS) and NVIDIA GeForce RTX 4090 24GB on Ubuntu 23.04 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 2308069-PTS-VULKANBE16
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

Limit displaying results to tests within:

NVIDIA GPU Compute 4 Tests
Vulkan Compute 4 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
Disable Color Branding
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
Performance Per
Dollar
Date
Run
  Test
  Duration
a
August 01 2023
  3 Hours, 11 Minutes
b
August 01 2023
  1 Hour, 30 Minutes
c
August 01 2023
  1 Hour, 32 Minutes
d
August 01 2023
  3 Hours, 45 Minutes
e
August 01 2023
  3 Hours, 16 Minutes
f
August 02 2023
  1 Hour, 53 Minutes
g
August 02 2023
  2 Hours, 9 Minutes
h
August 02 2023
  47 Minutes
i
August 02 2023
  1 Hour, 50 Minutes
4080
August 02 2023
  2 Hours, 4 Minutes
4080 rep
August 02 2023
  2 Hours, 7 Minutes
4080 xxx
August 02 2023
  2 Hours, 8 Minutes
4080 zzz
August 02 2023
  2 Hours, 9 Minutes
3090
August 03 2023
  2 Hours, 44 Minutes
3090 rep
August 03 2023
  2 Hours, 54 Minutes
3070
August 03 2023
  4 Hours, 56 Minutes
RTX 3070 Ti
August 04 2023
  1 Day, 7 Hours, 27 Minutes
4090
August 06 2023
  2 Hours, 52 Minutes
4090 rep
August 06 2023
  2 Hours, 54 Minutes
nv 4090
August 06 2023
  2 Hours, 52 Minutes
Invert Hiding All Results Option
  3 Hours, 57 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):


vulkan-benchmarks ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionDisplay Driverabcdefghi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090AMD Ryzen 9 7950X 16-Core @ 4.50GHz (16 Cores / 32 Threads)ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS)AMD Device 14d832GBWestern Digital WD_BLACK SN850X 1000GB + 4001GBAMD Radeon RX 6700 XT (2855/1000MHz)AMD Navi 21/23ASUS MG28UIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 23.046.4.6-060406-generic (x86_64)GNOME Shell 44.2X Server 1.21.1.7 + Wayland4.6 Mesa 23.3~git2307260600.87109c~oibaf~l (git-87109c3 2023-07-26 lunar-oibaf-ppa) (LLVM 15.0.7 DRM 3.52)GCC 12.2.0ext43840x2160MSI NVIDIA GeForce RTX 4060 8GBNVIDIA Device 22beX Server 1.21.1.7NVIDIA 535.86.054.6.0eVGA NVIDIA GeForce RTX 3060 12GBNVIDIA GA106 HD AudioNVIDIA GeForce RTX 3060 Ti 8GBNVIDIA GA104 HD Audio2560x1440NVIDIA GeForce RTX 4080 16GBNVIDIA Device 22bb3840x2160NVIDIA GeForce RTX 3090 24GBNVIDIA GA102 HD AudioNVIDIA GeForce RTX 3070 8GBNVIDIA GA104 HD Audio2560x1440NVIDIA GeForce RTX 3070 Ti 8GBNVIDIA GeForce RTX 4090 24GBNVIDIA AD102 HD Audio3840x2160OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Pa930Z/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Pa930Z/gcc-12-12.2.0/debian/tmp-gcn/usr --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- a: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203- b: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203- c: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203- d: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- e: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- f: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- g: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- h: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- i: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- 4080: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- 4080 rep: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- 4080 xxx: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- 4080 zzz: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- 3090: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- 3090 rep: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- 3070: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- RTX 3070 Ti: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- 4090: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- 4090 rep: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- nv 4090: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203Graphics Details- a: BAR1 / Visible vRAM Size: 12272 MB - vBIOS Version: 113-D5121100-101- b: BAR1 / Visible vRAM Size: 12272 MB - vBIOS Version: 113-D5121100-101- c: BAR1 / Visible vRAM Size: 12272 MB - vBIOS Version: 113-D5121100-101- d: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 95.07.31.00.e3- e: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 95.07.31.00.e3- f: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 94.06.14.40.46- g: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 94.06.14.40.46- h: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 94.06.14.40.46- i: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 94.04.25.00.2c- 4080: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.0e.00.04- 4080 rep: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.0e.00.04- 4080 xxx: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.0e.00.04- 4080 zzz: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.0e.00.04- 3090: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 94.02.27.00.02- 3090 rep: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 94.02.27.00.02- 3070: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 94.04.25.00.2b- RTX 3070 Ti: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 94.04.5b.00.02- 4090: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.01- 4090 rep: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.01- nv 4090: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.01Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

vulkan-benchmarks vkpeak: fp16-vec4vkpeak: int32-scalarvkpeak: int16-vec4vkpeak: int32-vec4vkpeak: int16-scalarvkpeak: fp16-scalarvkpeak: fp32-vec4vkpeak: fp32-scalarvkpeak: fp64-scalarvkpeak: fp64-vec4ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenet-v3ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - FastestDetncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - vision_transformerncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - regnety_400mncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - squeezenet_ssdncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - yolov4-tinyncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - resnet50ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - alexnetncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - resnet18ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - vgg16ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - googlenetncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - blazefacencnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - efficientnet-b0ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mnasnetncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - shufflenet-v2ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenetvkfft: FFT + iFFT C2C Bluestein benchmark in double precisionvkresample: 2x - Doublencnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - FastestDetncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - vision_transformerncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - regnety_400mncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - squeezenet_ssdncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - yolov4-tinyncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - resnet50ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - alexnetncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - resnet18ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - vgg16ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - googlenetncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - blazefacencnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - efficientnet-b0ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mnasnetncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - shufflenet-v2ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenetvkfft: FFT + iFFT C2C 1D batched in double precisionncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenet-v3vkfft: FFT + iFFT C2C Bluestein in single precisionncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - yolov4-tinyncnn: CPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - FastestDetncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - vision_transformerncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - regnety_400mncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - squeezenet_ssdncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - resnet50ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - alexnetncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - resnet18ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - vgg16ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - googlenetncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - blazefacencnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - efficientnet-b0ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - mnasnetncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - shufflenet-v2ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3-v3-v3-v3-v3 - mobilenetncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetncnn: CPU - FastestDetncnn: CPU - blazefacencnn: Vulkan GPU-v3-v3-v3-v3-v3 - mobilenet-v3ncnn: CPU-v3-v3-v3-v3-v3 - mobilenet-v3ncnn: CPU - vision_transformerncnn: CPU - regnety_400mncnn: CPU - squeezenet_ssdncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - googlenetncnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetncnn: CPU-v3-v3-v3 - FastestDetncnn: CPU-v3-v3-v3 - vision_transformerncnn: CPU-v3-v3-v3 - regnety_400mncnn: CPU-v3-v3-v3 - squeezenet_ssdncnn: CPU-v3-v3-v3 - yolov4-tinyncnn: CPU-v3-v3-v3 - resnet50ncnn: CPU-v3-v3-v3 - alexnetncnn: CPU-v3-v3-v3 - resnet18ncnn: CPU-v3-v3-v3 - vgg16ncnn: CPU-v3-v3-v3 - googlenetncnn: CPU-v3-v3-v3 - blazefacencnn: CPU-v3-v3-v3 - efficientnet-b0ncnn: CPU-v3-v3-v3 - mnasnetncnn: CPU-v3-v3-v3 - shufflenet-v2ncnn: CPU-v3-v3-v3-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3-v3 - mobilenetncnn: Vulkan GPU-v3-v3-v3 - regnety_400mncnn: Vulkan GPU-v3-v3-v3 - FastestDetncnn: Vulkan GPU-v3-v3-v3 - vision_transformerncnn: Vulkan GPU-v3-v3-v3 - squeezenet_ssdncnn: Vulkan GPU-v3-v3-v3 - yolov4-tinyncnn: Vulkan GPU-v3-v3-v3 - resnet50ncnn: Vulkan GPU-v3-v3-v3 - alexnetncnn: Vulkan GPU-v3-v3-v3 - resnet18ncnn: Vulkan GPU-v3-v3-v3 - vgg16ncnn: Vulkan GPU-v3-v3-v3 - googlenetncnn: Vulkan GPU-v3-v3-v3 - blazefacencnn: Vulkan GPU-v3-v3-v3 - efficientnet-b0ncnn: Vulkan GPU-v3-v3-v3 - mnasnetncnn: Vulkan GPU-v3-v3-v3 - shufflenet-v2ncnn: Vulkan GPU-v3-v3-v3-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3-v3 - mobilenetvkfft: FFT + iFFT C2C 1D batched in single precisionncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - FastestDetncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - vision_transformerncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - regnety_400mncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - squeezenet_ssdncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - yolov4-tinyncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - resnet50ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - alexnetncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - resnet18ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - vgg16ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - googlenetncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - blazefacencnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - efficientnet-b0ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mnasnetncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - shufflenet-v2ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenet-v3ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenetncnn: CPU-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenet-v3vkfft: FFT + iFFT C2C 1D batched in single precision, no reshufflingncnn: CPU-v3-v3-v3-v3-v3-v3 - FastestDetncnn: CPU-v3-v3-v3-v3-v3-v3 - vision_transformerncnn: CPU-v3-v3-v3-v3-v3-v3 - regnety_400mncnn: CPU-v3-v3-v3-v3-v3-v3 - squeezenet_ssdncnn: CPU-v3-v3-v3-v3-v3-v3 - yolov4-tinyncnn: CPU-v3-v3-v3-v3-v3-v3 - resnet50ncnn: CPU-v3-v3-v3-v3-v3-v3 - alexnetncnn: CPU-v3-v3-v3-v3-v3-v3 - resnet18ncnn: CPU-v3-v3-v3-v3-v3-v3 - vgg16ncnn: CPU-v3-v3-v3-v3-v3-v3 - googlenetncnn: CPU-v3-v3-v3-v3-v3-v3 - blazefacencnn: CPU-v3-v3-v3-v3-v3-v3 - efficientnet-b0ncnn: CPU-v3-v3-v3-v3-v3-v3 - mnasnetncnn: CPU-v3-v3-v3-v3-v3-v3 - shufflenet-v2ncnn: CPU-v3-v3-v3-v3-v3-v3-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3-v3-v3-v3-v3 - mobilenetvkfft: FFT + iFFT C2C 1D batched in half precisionvkfft: FFT + iFFT C2C multidimensional in single precisionvkfft: FFT + iFFT R2C / C2Rvkresample: 2x - Singleabcdefghi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409023232.422272.6223123.772658.7313102.7513154.1512730.0813190.09841.40841.8047173.1720816113403.184.131.888.167.0912.8410.014.315.2823.517.901.383.862.983.353.178.053.621.3832.498.187.0712.9010.204.415.2923.757.943.902.973.343.168.05478875050491597330014210511.68623390.442269.2523396.592640.0813070.8113145.1912808.5912807.06839.2836.55469520822112734.0731.858.217.0712.87104.335.2323.567.851.373.822.953.333.148.044.051.383.163.1631.958.187.0612.7410.014.325.223.497.823.852.973.343.167.974.0731.658.057.0312.9810.014.295.2123.57.841.373.822.973.333.158.018.274.0631.717.1412.779.874.425.4223.427.971.373.852.963.333.158479485064391812327514216311.6923387.262269.0623385.442638.6913063.8613136.7912822.0112860.56839.01836.1646703.220847113113.174.0931.7987.0612.81104.335.2123.547.81.373.832.963.323.138.034.111.393.173.1631.778.277.112.8110.114.315.2423.457.933.882.993.353.188.024.0831.788.147.0412.8910.334.285.2623.997.881.383.892.973.343.1487.983.6931.667.0712.8610.034.35.2323.547.831.363.822.963.333.157.95479715059691744328124302111.68816864.478520.027352.858465.825676.028412.3311251.178531.96267.43267.742346500.0143.1712143107193.174.1132.128.177.0812.8510.104.315.2323.567.851.383.872.973.353.168.024.081.3832.438.237.0912.9510.004.305.2323.517.853.852.983.353.178.10426454336585181363283539932.85516865.298505.207336.258465.715675.998397.8011231.728515.58267.41267.252343500.0163.1812168105604.0831.938.107.0512.8710.104.315.2223.607.851.383.842.963.333.148.04426514336585191370903530432.85013440.976827.925959.756800.174480.596812.529006.576837.94214.17214.231814500.013.141056175714.2432.928.347.0813.1710.264.645.4824.558.151.383.862.973.43.138.274.221.373.153.1533.568.087.2313.3211.054.365.6924.197.923.872.973.553.158.453.8533.478.346.9713.0711.054.836.1324.458.071.434.043.123.43.168.568.54.233.367.0914.3410.254.355.324.127.941.373.852.963.333.168.655647657110104146262382659326.73813438.46824.215956.246795.394478.416810.559003.126832.74213.96213.951818500.011105483.16757413.143.143.9233.328.387.1410.334.355.2824.047.961.383.842.973.343.178.54.0732.428.367.113.6410.344.876.2224.28.961.413.862.983.353.188.172.571.383.153.1632.738.37.1317.2310.724.325.5523.787.983.9133.593.1622.743.9733.398.077.2613.0811.254.715.4824.929.151.374.143.053.383.158.987.994.0632.387.1912.8910.184.355.323.827.941.373.852.953.333.148.045645557094104171265412663826.76913490.246800.65978.386772.984495.986838.329036.176810.73213.37210.9610572762256431104298265242417500.0064.87147803.261006113.773.263.8338.018.467.2113.15.15.8827.4310.471.414.193.073.433.2910.025.1436.429.887.4615.1612.966.535.8227.838.751.45.883.23.493.2910.42.661.43.263.2937.89.948.9614.6512.095.35.630.9610.34.052.745.033.528.375.6936.558.218.1615.1114.055.015.8629.1210.171.284.683.393.523.310.087.994.4338.338.3315.4311.154.995.8529.0710.191.254.212.993.363.289.056973871163132270346863372720.935579288.2014.1935.68.677.7113.9311.484.985.9225.678.791.444.043.13.483.263.298.43349741712113.863.244.2834.918.617.6611.44.615.6125.488.41.434.063.063.463.288.844.235.568.397.5813.7910.814.625.67258.421.414.013.073.433.268.444.421.43.273.2835.078.247.7313.8511.164.755.6925.378.423.993.053.413.288.734.234.28.337.6413.8111.114.665.725.18.451.444.023.083.463.318.438.454.234.137.6613.7910.954.695.6525.048.491.424.053.093.443.298.43104556106210211076658696647313.1365583288.1664.1733.938.357.6213.7311.074.645.6725.568.421.424.013.063.443.313.278.38350383.241728713.553.264.1434.18.247.5510.84.725.6125.058.491.413.983.033.393.278.44.2135.078.567.6413.6710.844.655.6125.048.41.414.053.083.443.298.574.341.423.2735.288.677.8614.0311.764.675.6826.118.524.093.063.433.288.414.1834.278.577.5913.5510.794.655.6324.918.521.424.023.093.433.278.488.444.0934.297.6313.6810.844.695.6925.048.581.454.043.073.443.38.461044913.281062054.234.228.727.6713.7110.864.685.6425.018.521.434.073.093.473.38.45211058700686827913.1365587288.0393.7533.98.257.2713.5211.224.715.6525.338.261.313.972.983.343.053.148.31350713.261734313.623.274.1734.238.527.6710.914.675.6725.48.431.424.023.053.433.278.464.234.198.567.6213.6510.944.685.6225.018.421.424.043.073.53.268.374.171.423.333.3134.278.457.6213.610.824.685.5625.038.384.043.063.453.288.374.1934.378.757.6413.6910.914.655.66258.51.424.063.073.473.38.448.584.3135.47.713.9511.55.215.8926.088.991.424.223.133.513.48.881045283.081060993.834.148.387.2713.6311.264.695.7825.448.321.324.0133.43.28.34210713678876906813.1375584288.0283.284.6135.368.378.0615.2612.54.75.7426.098.551.414.053.083.443.263.289.19350583.241718513.613.244.234.18.497.6210.914.685.625.168.421.424.013.083.433.288.464.7934.328.587.6313.811.074.685.5925.828.411.424.043.063.463.298.474.161.43.23.2734.18.377.5513.6311.14.695.6325.48.43.993.043.423.258.384.0434.478.477.3513.8311.214.675.7125.458.551.414.033.063.433.288.48.14.1234.057.5113.6211.094.655.5925.268.371.393.953.013.373.238.381045433.061059263.8234.478.347.2513.4211.14.665.7725.268.291.313.952.963.363.168.25210991700406768913.12641149.120909.0216886.6620820.0913710.8820845.0927797.821269.72653.13653.153.164.0832.168.27.0512.8610.034.35.223.57.831.393.862.973.363.158.014282371.6993.193.8331.948.337.0512.9710.074.325.2123.517.841.383.882.943.323.133.128.03309453.161440613.13.184.0333.227.997.0410.384.315.1923.557.861.363.832.963.333.158.114.1131.948.387.1612.8810.14.355.2723.557.871.393.882.993.393.188.074.211.383.1533.018.257.5214.2610.34.35.2123.437.863.872.993.343.178.64.0431.897.957.0412.8710.054.315.1923.57.831.363.832.953.323.148.068.014.0431.867.0412.889.974.35.2323.57.821.363.852.973.343.1681413571439694.132.18.227.1212.8210.034.335.223.587.91.393.882.983.363.168.07255207510055534710.39940876.1220613.4116878.220517.4513606.7920640.6727393.220708.84648.714.132.138.197.0712.8910.044.35.223.477.821.383.852.983.363.178.054289371.4223.164.0731.978.077.0812.99.984.35.223.387.861.373.852.973.343.183.178.05311221444912.863.194.0832.098.347.0910.044.315.2223.527.891.393.872.993.373.198.044.0831.918.027.0612.8310.064.315.223.487.821.373.862.973.363.178.034.081.383.153.1531.88.247.1212.779.954.315.2923.437.93.862.973.353.178.014.1131.938.097.0912.8210.074.35.223.547.851.373.852.963.333.178.038.254.132.117.0812.8410.014.35.2423.437.851.383.852.973.363.178.011414374.0731.948.067.0712.9210.274.315.2723.727.861.383.842.963.323.193.158.033.171439564.0731.858.037.0912.8110.064.315.323.47.911.383.852.973.333.168.06265171548145443210.4285.974.4869.4818.2415.4626.3323.5410.6913.3451.2818.663.579.538.156.35.4918.5424.7456.66.7170.2917.6118.8328.7323.4411.8911.349.716.972.999.816.065.595.995.4617.096.5629.87.526.9371.0817.8815.423.5910.0812.1455.4818.61.778.414.5988.3518.398.4170.7616.2215.8228.5923.4810.8812.6848.2919.493.988.995.097.077.8121.118.652.988.065.3875.341813.227.6621.59.6214.0356.6418.259.236.886.829.6717.819.1881.7719.6617.7529.3424.071111.1449.75173.039.016.878.139.1917.8217.238.6373.5116.1529.4923.119.8613.3855.4220.723.187.816.024.897.2416.347.2370.5317.0215.3229.3822.1511.4312.1353.4818.82.696.638.555.897.345.9217.066.437.1265.4118.2514.2728.4122.1910.5912.6450.3219.22.539.196.077.817.2216.5222.0643.524.2538.329.108.3115.5612.525.416.6928.539.581.514.553.253.923.699.9824.8053.644.3238.279.058.6515.0012.425.346.4028.539.901.344.373.103.893.443.669.523.6215.213.614.4137.889.198.2812.735.536.5728.639.841.494.603.343.753.669.624.2638.039.078.4715.5412.605.256.2829.069.871.604.533.403.983.569.353.941.603.653.7637.918.838.1315.2012.735.496.0828.369.694.723.263.773.769.434.3337.869.028.3915.4212.115.556.1828.409.651.794.783.114.093.419.628.894.2638.298.2915.4412.355.676.2328.409.861.714.733.373.953.669.624.1438.509.147.4514.6413.156.255.9427.869.971.404.173.123.483.243.8310.023.704.1838.048.427.5714.5712.816.176.2227.989.682.484.743.244.023.9110.0327.1833.362.8238.8210.057.415.6912.984.947.7827.318.911.454.143.193.475.258.468039172.8833.284.4538.629.879.8115.9512.44.677.5227.449.051.424.154.933.523.623.489.16552143.342037315.553.534.1339.0610.19.2811.534.725.7829.0511.31.434.243.15.173.418.964.3938.768.647.8313.9714.134.645.6928.8210.621.394.343.183.453.310.555.481.273.123.2538.258.137.8613.6814.15.14627.7510.274.233.123.553.310.082.9338.798.139.3215.311.394.945.8128.559.971.174.093.195.183.468.969.63.9439.017.9315.4414.586.115.9728.218.871.334.1833.344.998.811538964.6239.3510.117.4316.05135.146.9627.328.551.354.633.233.563.364.7510.563.331526562.8538.7610.099.5115.8511.724.997.7430.168.381.34.475.193.483.369.0429034281406843519.2843.443.9138.698.459.3416.611.245.165.8429.3510.181.384.443.285.183.68.838119173.0433.34.1139.0310.699.4615.411.515.255.929.1710.391.414.414.993.483.343.369.02553833.332040415.453.313.9638.178.649.1612.175.336.0529.1210.381.464.043.135.273.348.374.5937.598.488.2215.7213.086.796.0127.0410.651.44.093.153.493.3110.235.271.454.93.5337.058.787.9816.7913.735.236.7729.2410.864.33.183.473.310.754.1639.1217.159.315.3413.825.277.7527.259.291.344.343.233.593.458.7410.344.1638.737.8116.3913.576.585.8127.598.91.416.283.13.43.319.541539394.5938.658.79.4415.4110.965.345.8729.8510.471.424.13.125.233.353.388.223.31559363.1238.7910.239.3813.8812.475.458.1430.748.971.424.355.113.423.4410.6128765180999813298.9624.814.0138.588.377.7215.6713.466.545.9729.48.852.915.883.13.373.2710.158132172.8873.362.6438.4610.037.0215.5513.134.697.3828.148.351.264.13.073.53.173.428.93549503.262060117.33.472.8139.1810.099.2113.635.148.1627.898.611.184.123.163.515.19.413.9339.049.819.1115.2612.455.27.4429.298.71.44.14.73.513.438.454.511.332.613.3538.910.179.1115.411.415.187.8229.548.934.374.773.453.68.154.0638.999.559.3715.6213.684.677.6127.049.021.164.044.613.463.398.917.735.9238.587.7216.6113.136.115.8427.7710.011.075.262.543.174.4510.541521705.8637.138.348.2616.313.256.325.5827.2510.141.45.823.13.434.963.2910.644.971551483.9338.958.257.4817.6713.296.626.0727.6110.751.425.943.123.323.2912.1229276882875848878.967OpenBenchmarking.org

vkpeak

Vkpeak is a Vulkan compute benchmark inspired by OpenCL's clpeak. Vkpeak provides Vulkan compute performance measurements for FP16 / FP32 / FP64 / INT16 / INT32 scalar and vec4 performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp16-vec4abcdefgh30903090 rep9K18K27K36K45KSE +/- 5.96, N = 3SE +/- 0.37, N = 3SE +/- 0.36, N = 323232.4223390.4423387.2616864.4716865.2913440.9713438.4713490.2441149.1041188.02

fp16-vec4

i: The test quit with a non-zero exit status.

4080: The test quit with a non-zero exit status.

4080 rep: The test quit with a non-zero exit status.

4080 xxx: The test quit with a non-zero exit status.

4080 zzz: The test quit with a non-zero exit status.

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

4090: The test quit with a non-zero exit status.

4090 rep: The test quit with a non-zero exit status.

nv 4090: The test quit with a non-zero exit status.

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int32-scalarabcdefgh30903090 rep4K8K12K16K20KSE +/- 0.34, N = 3SE +/- 15.02, N = 3SE +/- 0.03, N = 32272.622269.252269.068520.028505.206827.926824.296800.6020909.0220767.64

int32-scalar

i: The test quit with a non-zero exit status.

4080: The test quit with a non-zero exit status.

4080 rep: The test quit with a non-zero exit status.

4080 xxx: The test quit with a non-zero exit status.

4080 zzz: The test quit with a non-zero exit status.

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

4090: The test quit with a non-zero exit status.

4090 rep: The test quit with a non-zero exit status.

nv 4090: The test quit with a non-zero exit status.

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int16-vec4abcdefgh30903090 rep5K10K15K20K25KSE +/- 21.55, N = 3SE +/- 17.33, N = 3SE +/- 0.31, N = 323123.7723396.5923385.447352.857336.255959.755956.385978.3816886.6616881.47

int16-vec4

i: The test quit with a non-zero exit status.

4080: The test quit with a non-zero exit status.

4080 rep: The test quit with a non-zero exit status.

4080 xxx: The test quit with a non-zero exit status.

4080 zzz: The test quit with a non-zero exit status.

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

4090: The test quit with a non-zero exit status.

4090 rep: The test quit with a non-zero exit status.

nv 4090: The test quit with a non-zero exit status.

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int32-vec4abcdefgh30903090 rep4K8K12K16K20KSE +/- 0.26, N = 3SE +/- 0.19, N = 3SE +/- 0.05, N = 32658.732640.082638.698465.828465.716800.176794.926772.9820820.0920517.68

int32-vec4

i: The test quit with a non-zero exit status.

4080: The test quit with a non-zero exit status.

4080 rep: The test quit with a non-zero exit status.

4080 xxx: The test quit with a non-zero exit status.

4080 zzz: The test quit with a non-zero exit status.

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

4090: The test quit with a non-zero exit status.

4090 rep: The test quit with a non-zero exit status.

nv 4090: The test quit with a non-zero exit status.

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int16-scalarabcdefgh30903090 rep3K6K9K12K15KSE +/- 1.30, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 313102.7513070.8113063.865676.025675.994480.594479.224495.9813710.8813608.57

int16-scalar

i: The test quit with a non-zero exit status.

4080: The test quit with a non-zero exit status.

4080 rep: The test quit with a non-zero exit status.

4080 xxx: The test quit with a non-zero exit status.

4080 zzz: The test quit with a non-zero exit status.

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

4090: The test quit with a non-zero exit status.

4090 rep: The test quit with a non-zero exit status.

nv 4090: The test quit with a non-zero exit status.

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp16-scalarabcdefgh30903090 rep4K8K12K16K20KSE +/- 4.01, N = 3SE +/- 13.46, N = 3SE +/- 5.09, N = 313154.1513145.1913136.798412.338397.806812.526811.356838.3220845.0920953.30

fp16-scalar

i: The test quit with a non-zero exit status.

4080: The test quit with a non-zero exit status.

4080 rep: The test quit with a non-zero exit status.

4080 xxx: The test quit with a non-zero exit status.

4080 zzz: The test quit with a non-zero exit status.

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

4090: The test quit with a non-zero exit status.

4090 rep: The test quit with a non-zero exit status.

nv 4090: The test quit with a non-zero exit status.

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp32-vec4abcdefgh30903090 rep6K12K18K24K30KSE +/- 1.81, N = 3SE +/- 19.37, N = 3SE +/- 2.57, N = 312730.0812808.5912822.0111251.1711231.729006.579002.599036.1727797.8027807.58

fp32-vec4

i: The test quit with a non-zero exit status.

4080: The test quit with a non-zero exit status.

4080 rep: The test quit with a non-zero exit status.

4080 xxx: The test quit with a non-zero exit status.

4080 zzz: The test quit with a non-zero exit status.

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

4090: The test quit with a non-zero exit status.

4090 rep: The test quit with a non-zero exit status.

nv 4090: The test quit with a non-zero exit status.

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp32-scalarabcdefgh30903090 rep5K10K15K20K25KSE +/- 4.18, N = 3SE +/- 16.18, N = 3SE +/- 0.30, N = 313190.0912807.0612860.568531.968515.586837.946812.996810.7321269.7220925.30

fp32-scalar

i: The test quit with a non-zero exit status.

4080: The test quit with a non-zero exit status.

4080 rep: The test quit with a non-zero exit status.

4080 xxx: The test quit with a non-zero exit status.

4080 zzz: The test quit with a non-zero exit status.

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

4090: The test quit with a non-zero exit status.

4090 rep: The test quit with a non-zero exit status.

nv 4090: The test quit with a non-zero exit status.

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp64-scalarabcdefgh30903090 rep2004006008001000SE +/- 0.22, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3841.40839.20839.01267.43267.41214.17213.96213.37653.13653.63

fp64-scalar

i: The test quit with a non-zero exit status.

4080: The test quit with a non-zero exit status.

4080 rep: The test quit with a non-zero exit status.

4080 xxx: The test quit with a non-zero exit status.

4080 zzz: The test quit with a non-zero exit status.

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

4090: The test quit with a non-zero exit status.

4090 rep: The test quit with a non-zero exit status.

nv 4090: The test quit with a non-zero exit status.

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp64-vec4abcdefgh30902004006008001000SE +/- 0.32, N = 3SE +/- 0.48, N = 3SE +/- 0.00, N = 3841.80836.55836.16267.74267.25214.23213.95210.96653.15

fp64-vec4

i: The test quit with a non-zero exit status.

4080: The test quit with a non-zero exit status.

4080 rep: The test quit with a non-zero exit status.

4080 xxx: The test quit with a non-zero exit status.

4080 zzz: The test quit with a non-zero exit status.

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

4090: The test quit with a non-zero exit status.

4090 rep: The test quit with a non-zero exit status.

nv 4090: The test quit with a non-zero exit status.

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 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mobilenet-v330903070RTX 3070 Ti40904090 repnv 40901.34332.68664.02995.37326.7165SE +/- 0.17, N = 153.165.973.523.363.444.81MIN: 3.12 / MAX: 3.67MIN: 2.84 / MAX: 111.8MIN: 2.95 / MAX: 536.1MIN: 3.21 / MAX: 4.83MIN: 3.3 / MAX: 4.34MIN: 3.13 / MAX: 149.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: FastestDet30903090 rep3070RTX 3070 Ti40904090 repnv 40901.0082.0163.0244.0325.04SE +/- 0.29, N = 154.084.104.484.252.823.914.01MIN: 4.04 / MAX: 4.2MIN: 4.06 / MAX: 4.2MIN: 2.2 / MAX: 27.6MIN: 2.46 / MAX: 526.3MIN: 2.69 / MAX: 3.5MIN: 3.77 / MAX: 5.87MIN: 3.87 / MAX: 5.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: vision_transformer30903090 rep3070RTX 3070 Ti40904090 repnv 40901530456075SE +/- 0.12, N = 1532.1632.1369.4838.3238.8238.6938.58MIN: 31.94 / MAX: 33.7MIN: 31.95 / MAX: 32.87MIN: 39.08 / MAX: 374.31MIN: 32.26 / MAX: 477.15MIN: 33.83 / MAX: 435.6MIN: 33.32 / MAX: 390.07MIN: 33.06 / MAX: 464.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: regnety_400m30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.20, N = 158.208.1918.249.1010.058.458.37MIN: 8.14 / MAX: 8.74MIN: 8.12 / MAX: 8.98MIN: 7.5 / MAX: 201.09MIN: 7.61 / MAX: 454.62MIN: 8.13 / MAX: 173.18MIN: 8.05 / MAX: 12.64MIN: 8.08 / MAX: 10.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: squeezenet_ssd30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.22, N = 157.057.0715.468.317.409.347.72MIN: 6.98 / MAX: 7.81MIN: 6.99 / MAX: 7.81MIN: 7.08 / MAX: 147.31MIN: 6.35 / MAX: 364.95MIN: 6.81 / MAX: 8.46MIN: 6.88 / MAX: 268.7MIN: 7.13 / MAX: 8.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: yolov4-tiny30903090 rep3070RTX 3070 Ti40904090 repnv 4090612182430SE +/- 0.25, N = 1512.8612.8926.3315.5615.6916.6015.67MIN: 12.74 / MAX: 13.68MIN: 12.79 / MAX: 13.77MIN: 12.62 / MAX: 127.32MIN: 12.24 / MAX: 459.8MIN: 13.13 / MAX: 187.93MIN: 12.98 / MAX: 103.04MIN: 12.91 / MAX: 334.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: resnet5030903090 rep3070RTX 3070 Ti40904090 repnv 4090612182430SE +/- 0.24, N = 1510.0310.0423.5412.5212.9811.2413.46MIN: 9.88 / MAX: 10.86MIN: 9.94 / MAX: 10.91MIN: 10.3 / MAX: 149.49MIN: 9.95 / MAX: 459.05MIN: 10.26 / MAX: 145.62MIN: 10.22 / MAX: 29.96MIN: 10.6 / MAX: 340.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: alexnet30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.21, N = 154.304.3010.695.414.945.166.54MIN: 4.25 / MAX: 4.63MIN: 4.24 / MAX: 4.85MIN: 4.32 / MAX: 148.92MIN: 4.23 / MAX: 364.66MIN: 4.52 / MAX: 6.23MIN: 4.73 / MAX: 6.38MIN: 4.56 / MAX: 110.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: resnet1830903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.24, N = 155.205.2013.346.697.785.845.97MIN: 5.1 / MAX: 6.05MIN: 5.08 / MAX: 6.05MIN: 5.43 / MAX: 279.86MIN: 5.06 / MAX: 462.37MIN: 5.4 / MAX: 168.29MIN: 5.35 / MAX: 8.28MIN: 5.4 / MAX: 8.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: vgg1630903090 rep3070RTX 3070 Ti40904090 repnv 40901224364860SE +/- 0.26, N = 1523.5023.4751.2828.5327.3129.3529.40MIN: 23.26 / MAX: 24.34MIN: 23.25 / MAX: 24.24MIN: 24.83 / MAX: 242.12MIN: 24.21 / MAX: 515.3MIN: 24.27 / MAX: 230.86MIN: 24.55 / MAX: 485.35MIN: 26.17 / MAX: 411.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: googlenet30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.22, N = 157.837.8218.669.588.9110.188.85MIN: 7.73 / MAX: 8.6MIN: 7.72 / MAX: 8.6MIN: 7.42 / MAX: 326.73MIN: 7.62 / MAX: 396.9MIN: 8.3 / MAX: 10.96MIN: 7.81 / MAX: 204.67MIN: 8.16 / MAX: 10.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: blazeface30903090 rep3070RTX 3070 Ti40904090 repnv 40900.80331.60662.40993.21324.0165SE +/- 0.14, N = 151.391.383.571.511.451.382.91MIN: 1.36 / MAX: 3.12MIN: 1.35 / MAX: 1.88MIN: 1.08 / MAX: 141.04MIN: 1.11 / MAX: 380.46MIN: 1.38 / MAX: 2.98MIN: 1.33 / MAX: 1.98MIN: 1.29 / MAX: 113.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: efficientnet-b030903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.16, N = 153.863.859.534.554.144.445.88MIN: 3.82 / MAX: 4.82MIN: 3.81 / MAX: 4.6MIN: 3.77 / MAX: 182.53MIN: 3.84 / MAX: 379.07MIN: 3.93 / MAX: 5.94MIN: 4.24 / MAX: 5.18MIN: 3.96 / MAX: 194.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mnasnet30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.11, N = 152.972.988.153.253.193.283.10MIN: 2.93 / MAX: 3.45MIN: 2.94 / MAX: 3.36MIN: 2.67 / MAX: 317.68MIN: 2.68 / MAX: 277.21MIN: 3.04 / MAX: 3.98MIN: 3.15 / MAX: 4.32MIN: 2.97 / MAX: 3.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: shufflenet-v230903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.20, N = 153.363.366.303.923.475.183.37MIN: 3.32 / MAX: 3.82MIN: 3.33 / MAX: 3.83MIN: 3.28 / MAX: 147.57MIN: 3.12 / MAX: 496.78MIN: 3.33 / MAX: 5.01MIN: 3.45 / MAX: 200.36MIN: 3.25 / MAX: 5.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v2-v2 - Model: mobilenet-v230903090 rep3070RTX 3070 Ti40904090 repnv 40901.23532.47063.70594.94126.1765SE +/- 0.20, N = 153.153.175.493.695.253.603.27MIN: 3.11 / MAX: 3.78MIN: 3.12 / MAX: 3.78MIN: 2.97 / MAX: 152.08MIN: 3.07 / MAX: 544.13MIN: 3.11 / MAX: 367.53MIN: 3.44 / MAX: 4.27MIN: 3.11 / MAX: 4.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mobilenet30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.24, N = 158.018.0518.549.988.468.8310.15MIN: 7.96 / MAX: 8.47MIN: 7.98 / MAX: 8.94MIN: 8.01 / MAX: 164.45MIN: 7.79 / MAX: 434.9MIN: 8.12 / MAX: 10.14MIN: 8.29 / MAX: 10.15MIN: 8.08 / MAX: 193.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

VkFFT

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C Bluestein benchmark in double precisionabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep40904090 repnv 40902K4K6K8K10KSE +/- 0.33, N = 3SE +/- 4.37, N = 3SE +/- 11.20, N = 3471746954670234623431814181824175579558355875584428242898039811981321. (CXX) g++ options: -O3

Test: FFT + iFFT C2C Bluestein benchmark in double precision

3070: The test quit with a non-zero exit status. E: VkFFT System: 2909x2909x1 Buffer: 129 MB avg_time_per_step: 72.294 ms std_error: 0.046 num_iter: 31 benchmark: 1828 bandwidth: 27.9

RTX 3070 Ti: The test quit with a non-zero exit status. E: VkFFT System: 2909x2909x1 Buffer: 129 MB avg_time_per_step: 66.798 ms std_error: 0.291 num_iter: 31 benchmark: 1979 bandwidth: 30.2

VkResample

VkResample is a Vulkan-based image upscaling library based on VkFFT. The sample input file is upscaling a 4K image to 8K using Vulkan-based GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Doubledefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090110220330440550SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3500.01500.02500.01500.01500.01288.20288.17288.04288.03371.70371.4224.7524.81172.88173.04172.891. (CXX) g++ options: -O3

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 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3acdefi4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.02, N = 3SE +/- 0.00, N = 2SE +/- 0.02, N = 3SE +/- 0.20, N = 143.173.203.173.183.144.873.283.193.166.603.643.283.303.36MIN: 3.11 / MAX: 3.73MIN: 3.16 / MAX: 3.68MIN: 3.1 / MAX: 3.83MIN: 3.11 / MAX: 3.78MIN: 3.09 / MAX: 3.54MIN: 3.14 / MAX: 278.98MIN: 3.13 / MAX: 4.65MIN: 3.14 / MAX: 3.48MIN: 3.11 / MAX: 3.62MIN: 2.98 / MAX: 166.19MIN: 2.87 / MAX: 429.02MIN: 3.15 / MAX: 3.9MIN: 3.15 / MAX: 3.92MIN: 3.21 / MAX: 4.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: FastestDet40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.27, N = 154.194.173.754.613.834.076.714.324.454.112.64MIN: 4.06 / MAX: 7.41MIN: 4.02 / MAX: 4.75MIN: 3.63 / MAX: 5.24MIN: 4.45 / MAX: 5.92MIN: 3.79 / MAX: 4.09MIN: 4.03 / MAX: 4.18MIN: 2.73 / MAX: 109.52MIN: 2.51 / MAX: 398.91MIN: 4.29 / MAX: 5.05MIN: 3.98 / MAX: 4.73MIN: 2.52 / MAX: 4.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: vision_transformer40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901632486480SE +/- 0.11, N = 1535.6033.9333.9035.3631.9431.9770.2938.2738.6239.0338.46MIN: 34.13 / MAX: 38.49MIN: 32.77 / MAX: 36.2MIN: 32.72 / MAX: 37.77MIN: 33.87 / MAX: 42.41MIN: 31.72 / MAX: 34.34MIN: 31.71 / MAX: 33.78MIN: 39.39 / MAX: 250.19MIN: 32.29 / MAX: 507.7MIN: 33.33 / MAX: 465MIN: 33.61 / MAX: 343.67MIN: 32.39 / MAX: 435.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: regnety_400m40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.24, N = 158.678.358.258.378.338.0717.619.059.8710.6910.03MIN: 8.3 / MAX: 14.66MIN: 8.05 / MAX: 9.76MIN: 7.93 / MAX: 9.88MIN: 8.04 / MAX: 10.13MIN: 8.25 / MAX: 9.32MIN: 7.99 / MAX: 8.88MIN: 7.85 / MAX: 165.34MIN: 7.52 / MAX: 417.33MIN: 7.81 / MAX: 243.06MIN: 8.17 / MAX: 339.6MIN: 7.81 / MAX: 171.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: squeezenet_ssd40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.24, N = 157.717.627.278.067.057.0818.838.659.819.467.02MIN: 7.15 / MAX: 9.1MIN: 7.01 / MAX: 14.37MIN: 6.74 / MAX: 8.84MIN: 7.42 / MAX: 9.25MIN: 6.97 / MAX: 7.95MIN: 7 / MAX: 7.94MIN: 6.71 / MAX: 206.11MIN: 6.64 / MAX: 544.17MIN: 7.16 / MAX: 389.1MIN: 7.03 / MAX: 160.39MIN: 6.38 / MAX: 9.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: yolov4-tiny40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090714212835SE +/- 0.19, N = 1513.9313.7313.5215.2612.9712.9028.7315.0015.9515.4015.55MIN: 13.08 / MAX: 15.68MIN: 12.78 / MAX: 20.99MIN: 12.72 / MAX: 21.19MIN: 14.19 / MAX: 17.06MIN: 12.83 / MAX: 13.8MIN: 12.77 / MAX: 13.92MIN: 12.83 / MAX: 264.49MIN: 12.75 / MAX: 401.37MIN: 13.38 / MAX: 245.18MIN: 13 / MAX: 245.79MIN: 12.87 / MAX: 342.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: resnet5040804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090612182430SE +/- 0.25, N = 1511.4811.0711.2212.5010.079.9823.4412.4212.4011.5113.13MIN: 10.56 / MAX: 12.93MIN: 10.16 / MAX: 13.16MIN: 10.33 / MAX: 12.81MIN: 11.47 / MAX: 14.56MIN: 9.95 / MAX: 10.88MIN: 9.85 / MAX: 11.35MIN: 10.17 / MAX: 219.36MIN: 10.23 / MAX: 444.76MIN: 11.44 / MAX: 14.43MIN: 10.56 / MAX: 13.22MIN: 10.18 / MAX: 247.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: alexnet40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.16, N = 154.984.644.714.704.324.3011.895.344.675.254.69MIN: 4.59 / MAX: 7.15MIN: 4.24 / MAX: 6MIN: 4.26 / MAX: 7.21MIN: 4.28 / MAX: 5.92MIN: 4.25 / MAX: 5.33MIN: 4.24 / MAX: 5.11MIN: 4.34 / MAX: 229.18MIN: 4.25 / MAX: 221.78MIN: 4.28 / MAX: 6MIN: 4.86 / MAX: 6.33MIN: 4.28 / MAX: 6.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: resnet1840804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.20, N = 155.925.675.655.745.215.2011.306.407.525.907.38MIN: 5.37 / MAX: 8.24MIN: 5.19 / MAX: 7.38MIN: 5.18 / MAX: 6.76MIN: 5.18 / MAX: 8.08MIN: 5.09 / MAX: 6.13MIN: 5.1 / MAX: 6.09MIN: 5.3 / MAX: 181.7MIN: 5.1 / MAX: 457.07MIN: 5.45 / MAX: 290.49MIN: 5.43 / MAX: 7.49MIN: 5.15 / MAX: 138.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: vgg1640804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901122334455SE +/- 0.28, N = 1525.6725.5625.3326.0923.5123.3849.7028.5327.4429.1728.14MIN: 24.46 / MAX: 27.34MIN: 24.24 / MAX: 27.92MIN: 24.26 / MAX: 34.98MIN: 24.58 / MAX: 30.18MIN: 23.27 / MAX: 24.38MIN: 23.19 / MAX: 24.27MIN: 25.55 / MAX: 421.44MIN: 23.95 / MAX: 473.83MIN: 24.06 / MAX: 264.59MIN: 24.61 / MAX: 264.85MIN: 24.24 / MAX: 221.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: googlenet40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.19, N = 158.798.428.268.557.847.8616.979.909.0510.398.35MIN: 8.08 / MAX: 10.27MIN: 7.77 / MAX: 10.52MIN: 7.62 / MAX: 10.47MIN: 7.86 / MAX: 10.08MIN: 7.74 / MAX: 8.72MIN: 7.75 / MAX: 8.71MIN: 7.44 / MAX: 229.93MIN: 7.76 / MAX: 396.66MIN: 8.26 / MAX: 13.34MIN: 7.87 / MAX: 391.66MIN: 7.7 / MAX: 10.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: blazeface40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40900.67281.34562.01842.69123.364SE +/- 0.03, N = 151.441.421.311.411.381.372.991.341.421.411.26MIN: 1.37 / MAX: 2.07MIN: 1.35 / MAX: 2.89MIN: 1.25 / MAX: 3.14MIN: 1.34 / MAX: 1.88MIN: 1.36 / MAX: 1.53MIN: 1.35 / MAX: 1.48MIN: 1.22 / MAX: 149.55MIN: 1.06 / MAX: 2.66MIN: 1.36 / MAX: 1.92MIN: 1.35 / MAX: 1.91MIN: 1.2 / MAX: 1.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: efficientnet-b040804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.13, N = 154.044.013.974.053.883.859.814.374.154.414.10MIN: 3.84 / MAX: 4.83MIN: 3.81 / MAX: 6.04MIN: 3.79 / MAX: 5.93MIN: 3.83 / MAX: 5.42MIN: 3.83 / MAX: 4.72MIN: 3.78 / MAX: 4.83MIN: 3.87 / MAX: 165.38MIN: 3.85 / MAX: 366.28MIN: 3.93 / MAX: 5.94MIN: 4.21 / MAX: 5.82MIN: 3.87 / MAX: 6.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mnasnet40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.04, N = 153.103.062.983.082.942.976.063.104.934.993.07MIN: 2.95 / MAX: 4.05MIN: 2.93 / MAX: 5.02MIN: 2.86 / MAX: 4.47MIN: 2.95 / MAX: 3.88MIN: 2.9 / MAX: 3.34MIN: 2.94 / MAX: 3.45MIN: 2.96 / MAX: 42.7MIN: 2.61 / MAX: 4.75MIN: 2.97 / MAX: 124.96MIN: 3.02 / MAX: 235.56MIN: 2.93 / MAX: 4.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: shufflenet-v240804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901.25782.51563.77345.03126.289SE +/- 0.20, N = 153.483.443.343.443.323.345.593.893.523.483.50MIN: 3.34 / MAX: 4.88MIN: 3.31 / MAX: 4.32MIN: 3.22 / MAX: 3.97MIN: 3.31 / MAX: 4.85MIN: 3.29 / MAX: 3.79MIN: 3.3 / MAX: 3.79MIN: 3.32 / MAX: 42.33MIN: 3.08 / MAX: 345.39MIN: 3.38 / MAX: 4.23MIN: 3.34 / MAX: 4.1MIN: 3.37 / MAX: 4.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mobilenet-v340804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901.34782.69564.04345.39126.739SE +/- 0.13, N = 133.263.313.053.263.133.185.993.443.623.343.17MIN: 3.13 / MAX: 4.7MIN: 3.16 / MAX: 3.93MIN: 2.94 / MAX: 3.56MIN: 3.12 / MAX: 4.74MIN: 3.09 / MAX: 3.68MIN: 3.13 / MAX: 3.61MIN: 3.05 / MAX: 26.81MIN: 2.65 / MAX: 361.91MIN: 3.47 / MAX: 4.24MIN: 3.19 / MAX: 3.99MIN: 3.04 / MAX: 4.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v2-v2 - Model: mobilenet-v240804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901.22852.4573.68554.9146.1425SE +/- 0.18, N = 153.293.273.143.283.123.175.463.663.483.363.42MIN: 3.12 / MAX: 3.99MIN: 3.08 / MAX: 4.68MIN: 3 / MAX: 3.85MIN: 3.11 / MAX: 4.26MIN: 3.07 / MAX: 3.62MIN: 3.12 / MAX: 3.89MIN: 3.27 / MAX: 38.65MIN: 2.73 / MAX: 398.42MIN: 3.32 / MAX: 4.99MIN: 3.17 / MAX: 4.8MIN: 3.15 / MAX: 25.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mobilenet40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.25, N = 158.438.388.319.198.038.0517.099.529.169.028.93MIN: 8.03 / MAX: 9.64MIN: 7.94 / MAX: 10.07MIN: 7.85 / MAX: 10.21MIN: 8.51 / MAX: 11.04MIN: 7.96 / MAX: 8.83MIN: 7.96 / MAX: 9.04MIN: 7.89 / MAX: 121.53MIN: 7.97 / MAX: 420.29MIN: 8.5 / MAX: 10.51MIN: 8.42 / MAX: 11.17MIN: 8.33 / MAX: 11.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

VkFFT

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in double precisionabcdefghi40804080 rep4080 xxx4080 zzz30903090 rep40904090 repnv 409012K24K36K48K60KSE +/- 11.67, N = 3SE +/- 10.58, N = 3SE +/- 12.42, N = 3SE +/- 14.62, N = 32081620822208471214312168105611054810572147803497435038350713505830945311225521455383549501. (CXX) g++ options: -O3

Test: FFT + iFFT C2C 1D batched in double precision

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

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 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mobilenet-v3gi4080 rep4080 xxx4080 zzz30903070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.18, N = 153.163.263.243.263.243.166.563.623.303.333.26MIN: 3.12 / MAX: 3.58MIN: 3.11 / MAX: 4.7MIN: 3.11 / MAX: 4.37MIN: 3.13 / MAX: 4.08MIN: 3.1 / MAX: 3.88MIN: 3.11 / MAX: 3.77MIN: 3.07 / MAX: 110.87MIN: 3 / MAX: 469.9MIN: 3.14 / MAX: 4.82MIN: 3.19 / MAX: 4.79MIN: 3.13 / MAX: 3.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

VkFFT

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C Bluestein in single precisionabcdefghi40804080 rep4080 xxx4080 zzz30903090 rep40904090 repnv 40904K8K12K16K20KSE +/- 62.67, N = 3SE +/- 72.34, N = 3SE +/- 75.16, N = 15SE +/- 83.38, N = 31134011273113111071910560757175747622100611712117287173431718514406144492037320404206011. (CXX) g++ options: -O3

Test: FFT + iFFT C2C Bluestein in single precision

3070: The test quit with a non-zero exit status. E: VkFFT System: 4241x4241x1 Buffer: 137 MB avg_time_per_step: 16.022 ms std_error: 0.041 num_iter: 29 benchmark: 8770 bandwidth: 133.8

RTX 3070 Ti: The test quit with a non-zero exit status. E: VkFFT System: 4241x4241x1 Buffer: 137 MB avg_time_per_step: 10.602 ms std_error: 0.177 num_iter: 29 benchmark: 13253 bandwidth: 202.2

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 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: yolov4-tinygi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090714212835SE +/- 0.28, N = 1513.1413.7713.8613.5513.6213.6113.1012.8629.8015.2115.5515.4517.30MIN: 13 / MAX: 14.02MIN: 12.96 / MAX: 14.66MIN: 13.04 / MAX: 15.04MIN: 12.72 / MAX: 15.51MIN: 12.71 / MAX: 15.65MIN: 12.67 / MAX: 19.72MIN: 13.01 / MAX: 14.17MIN: 12.76 / MAX: 13.73MIN: 12.85 / MAX: 216.34MIN: 12.34 / MAX: 380.51MIN: 13.11 / MAX: 307.2MIN: 12.65 / MAX: 445.76MIN: 14.66 / MAX: 441.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3acdgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.00, N = 2SE +/- 0.00, N = 3SE +/- 0.21, N = 143.183.173.173.143.263.243.263.273.243.183.197.523.613.533.413.47MIN: 3.14 / MAX: 3.82MIN: 3.15 / MAX: 3.74MIN: 3.12 / MAX: 3.96MIN: 3.1 / MAX: 3.81MIN: 3.14 / MAX: 3.9MIN: 3.09 / MAX: 4.73MIN: 3.09 / MAX: 3.96MIN: 3.13 / MAX: 3.85MIN: 3.11 / MAX: 4.47MIN: 3.14 / MAX: 4.14MIN: 3.15 / MAX: 3.72MIN: 2.94 / MAX: 215MIN: 2.51 / MAX: 502.85MIN: 3.39 / MAX: 4.31MIN: 3.27 / MAX: 5.24MIN: 3.32 / MAX: 4.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: FastestDetgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.20, N = 153.923.834.284.144.174.204.034.086.934.414.033.962.81MIN: 3.88 / MAX: 4.72MIN: 3.7 / MAX: 4.57MIN: 4.13 / MAX: 4.85MIN: 4 / MAX: 5.6MIN: 4.03 / MAX: 5.63MIN: 4.01 / MAX: 11.47MIN: 3.99 / MAX: 4.22MIN: 4.04 / MAX: 4.29MIN: 2.57 / MAX: 163.84MIN: 2.06 / MAX: 295.24MIN: 3.89 / MAX: 4.63MIN: 3.79 / MAX: 11.36MIN: 2.68 / MAX: 4.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: vision_transformergi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901632486480SE +/- 0.20, N = 1533.3238.0134.9134.1034.2334.1033.2232.0971.0837.8838.3838.1739.18MIN: 31.83 / MAX: 104.12MIN: 32.96 / MAX: 388.09MIN: 33.72 / MAX: 36.82MIN: 32.43 / MAX: 38.75MIN: 33.08 / MAX: 37.43MIN: 32.32 / MAX: 38.54MIN: 33.04 / MAX: 36.99MIN: 31.84 / MAX: 32.77MIN: 38.84 / MAX: 374.68MIN: 32.46 / MAX: 518.57MIN: 33.53 / MAX: 477.38MIN: 32.97 / MAX: 462.63MIN: 33.74 / MAX: 520.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: regnety_400mgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.21, N = 158.388.468.618.248.528.497.998.3417.889.198.108.6410.09MIN: 8.05 / MAX: 27.34MIN: 8.08 / MAX: 10.33MIN: 8.21 / MAX: 10.07MIN: 7.91 / MAX: 9.53MIN: 8.13 / MAX: 9.73MIN: 8.08 / MAX: 9.72MIN: 7.92 / MAX: 8.78MIN: 8.26 / MAX: 9.09MIN: 7.38 / MAX: 190.77MIN: 7.44 / MAX: 524.66MIN: 7.65 / MAX: 10.05MIN: 8.3 / MAX: 10.51MIN: 7.84 / MAX: 366.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: squeezenet_ssdgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.25, N = 147.147.217.667.557.677.627.047.0915.408.287.579.169.21MIN: 7.03 / MAX: 7.99MIN: 6.73 / MAX: 8.82MIN: 7.09 / MAX: 8.97MIN: 6.99 / MAX: 9.08MIN: 7.04 / MAX: 9.1MIN: 7 / MAX: 9.93MIN: 6.96 / MAX: 7.7MIN: 7.01 / MAX: 7.97MIN: 6.64 / MAX: 132.68MIN: 6.38 / MAX: 381.81MIN: 7.02 / MAX: 9MIN: 6.73 / MAX: 423.75MIN: 6.83 / MAX: 203.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: resnet50gi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090612182430SE +/- 0.23, N = 1510.3313.1011.4010.8010.9110.9110.3810.0423.5912.7314.0812.1713.63MIN: 10.2 / MAX: 11.18MIN: 10.59 / MAX: 267.95MIN: 10.5 / MAX: 13.51MIN: 9.89 / MAX: 12.54MIN: 9.91 / MAX: 13.07MIN: 9.94 / MAX: 14.83MIN: 9.88 / MAX: 18.75MIN: 9.94 / MAX: 10.89MIN: 9.96 / MAX: 177.63MIN: 9.84 / MAX: 518.97MIN: 10.29 / MAX: 247.29MIN: 11.25 / MAX: 13.79MIN: 10.52 / MAX: 488.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: alexnetgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.22, N = 154.355.104.614.724.674.684.314.3110.085.535.145.335.14MIN: 4.28 / MAX: 5.1MIN: 4.75 / MAX: 6.12MIN: 4.24 / MAX: 7.25MIN: 4.25 / MAX: 7.3MIN: 4.27 / MAX: 6.36MIN: 4.26 / MAX: 6.8MIN: 4.25 / MAX: 4.94MIN: 4.26 / MAX: 5.07MIN: 4.36 / MAX: 225.66MIN: 4.22 / MAX: 362.62MIN: 4.76 / MAX: 6.16MIN: 4.83 / MAX: 6.6MIN: 4.65 / MAX: 6.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: resnet18gi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.23, N = 155.285.885.615.615.675.605.195.2212.146.576.586.058.16MIN: 5.16 / MAX: 6.09MIN: 5.36 / MAX: 8.2MIN: 5.09 / MAX: 7.91MIN: 5.07 / MAX: 7.08MIN: 5.1 / MAX: 8.06MIN: 5.09 / MAX: 7.51MIN: 5.09 / MAX: 6MIN: 5.13 / MAX: 6.1MIN: 5.28 / MAX: 151.53MIN: 4.91 / MAX: 391.33MIN: 6.04 / MAX: 7.81MIN: 5.53 / MAX: 7.66MIN: 5.39 / MAX: 397.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: vgg16gi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901224364860SE +/- 0.30, N = 1524.0427.4325.4825.0525.4025.1623.5523.5255.4828.6331.5729.1227.89MIN: 23.48 / MAX: 73.3MIN: 24.65 / MAX: 251.37MIN: 23.88 / MAX: 51.68MIN: 23.78 / MAX: 26.95MIN: 24.05 / MAX: 27.09MIN: 23.97 / MAX: 27.81MIN: 23.31 / MAX: 24.48MIN: 23.33 / MAX: 25.08MIN: 25.94 / MAX: 298.67MIN: 24.13 / MAX: 500.18MIN: 26.09 / MAX: 318.58MIN: 24.62 / MAX: 266.39MIN: 24.5 / MAX: 463.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: googlenetgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.24, N = 157.9610.478.408.498.438.427.867.8918.609.8410.8710.388.61MIN: 7.81 / MAX: 9.05MIN: 8.21 / MAX: 350.07MIN: 7.71 / MAX: 10.64MIN: 7.74 / MAX: 10.76MIN: 7.77 / MAX: 10.4MIN: 7.78 / MAX: 10.7MIN: 7.74 / MAX: 8.62MIN: 7.79 / MAX: 8.84MIN: 8.02 / MAX: 292.16MIN: 7.3 / MAX: 438.04MIN: 8.37 / MAX: 194.11MIN: 7.96 / MAX: 255.68MIN: 7.95 / MAX: 10.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: blazefacegi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40900.39830.79661.19491.59321.9915SE +/- 0.12, N = 141.381.411.431.411.421.421.361.391.771.491.161.461.18MIN: 1.35 / MAX: 2.09MIN: 1.35 / MAX: 2.02MIN: 1.36 / MAX: 2.06MIN: 1.34 / MAX: 2.1MIN: 1.35 / MAX: 2MIN: 1.34 / MAX: 2.84MIN: 1.34 / MAX: 1.46MIN: 1.37 / MAX: 1.52MIN: 1.08 / MAX: 12.53MIN: 1.05 / MAX: 379.08MIN: 1.1 / MAX: 2MIN: 1.39 / MAX: 2.91MIN: 1.11 / MAX: 1.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: efficientnet-b0gi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.19, N = 153.844.194.063.984.024.013.833.878.414.604.364.044.12MIN: 3.78 / MAX: 4.57MIN: 4.01 / MAX: 5.09MIN: 3.85 / MAX: 4.97MIN: 3.77 / MAX: 5.44MIN: 3.8 / MAX: 5.14MIN: 3.79 / MAX: 5.39MIN: 3.78 / MAX: 4.4MIN: 3.81 / MAX: 4.62MIN: 3.76 / MAX: 67.73MIN: 3.79 / MAX: 336.2MIN: 4.14 / MAX: 5.24MIN: 3.85 / MAX: 4.9MIN: 3.86 / MAX: 5.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: mnasnetgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901.03282.06563.09844.13125.164SE +/- 0.14, N = 152.973.073.063.033.053.082.962.994.593.343.173.133.16MIN: 2.93 / MAX: 3.88MIN: 2.93 / MAX: 3.84MIN: 2.94 / MAX: 3.67MIN: 2.91 / MAX: 4.45MIN: 2.91 / MAX: 3.67MIN: 2.93 / MAX: 4.42MIN: 2.93 / MAX: 3.31MIN: 2.96 / MAX: 3.32MIN: 2.88 / MAX: 20.12MIN: 2.68 / MAX: 393.6MIN: 3.03 / MAX: 3.66MIN: 3.01 / MAX: 3.62MIN: 3.02 / MAX: 4.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: shufflenet-v2gi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.16, N = 153.343.433.463.393.433.433.333.378.003.755.095.273.51MIN: 3.31 / MAX: 4.05MIN: 3.3 / MAX: 4.89MIN: 3.3 / MAX: 5.74MIN: 3.26 / MAX: 3.91MIN: 3.31 / MAX: 3.95MIN: 3.29 / MAX: 3.87MIN: 3.29 / MAX: 3.67MIN: 3.33 / MAX: 3.8MIN: 3.16 / MAX: 190.15MIN: 3.2 / MAX: 361.52MIN: 3.33 / MAX: 161.5MIN: 3.27 / MAX: 191.55MIN: 3.38 / MAX: 4.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3-v2-v2 - Model: mobilenet-v2gi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.15, N = 153.173.293.283.273.273.283.153.198.353.663.323.345.10MIN: 3.1 / MAX: 5.03MIN: 3.1 / MAX: 3.96MIN: 3.11 / MAX: 4.16MIN: 3.08 / MAX: 5.18MIN: 3.11 / MAX: 4.73MIN: 3.09 / MAX: 4.98MIN: 3.1 / MAX: 3.68MIN: 3.13 / MAX: 4MIN: 3.08 / MAX: 103.38MIN: 3.01 / MAX: 311.25MIN: 3.12 / MAX: 4.24MIN: 3.14 / MAX: 4.45MIN: 3.14 / MAX: 138.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3-v3 - Model: mobilenetgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.27, N = 158.5010.028.848.408.468.468.118.0418.399.6210.188.379.41MIN: 8.42 / MAX: 9.29MIN: 8.07 / MAX: 266.25MIN: 8.31 / MAX: 10.98MIN: 7.93 / MAX: 15.25MIN: 7.95 / MAX: 10.34MIN: 7.97 / MAX: 10.56MIN: 8.02 / MAX: 14.2MIN: 7.96 / MAX: 9.01MIN: 7.92 / MAX: 173.39MIN: 7.71 / MAX: 449.11MIN: 8.18 / MAX: 235.56MIN: 7.98 / MAX: 10.71MIN: 8.98 / MAX: 11.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDetabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.29, N = 154.104.074.094.114.084.244.075.144.204.214.204.794.114.088.414.264.394.593.93MIN: 4.06 / MAX: 4.81MIN: 4.04 / MAX: 4.53MIN: 4.05 / MAX: 5.5MIN: 4.01 / MAX: 9.72MIN: 4.03 / MAX: 5.29MIN: 3.88 / MAX: 24.21MIN: 4.02 / MAX: 4.82MIN: 3.7 / MAX: 81.79MIN: 4.02 / MAX: 4.97MIN: 4.04 / MAX: 4.97MIN: 4.03 / MAX: 6.49MIN: 4.64 / MAX: 6.21MIN: 4.07 / MAX: 4.29MIN: 4.04 / MAX: 4.35MIN: 2.89 / MAX: 487.78MIN: 2.5 / MAX: 396.93MIN: 4.25 / MAX: 5.86MIN: 2.62 / MAX: 232.18MIN: 3.8 / MAX: 5.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901632486480SE +/- 0.09, N = 3SE +/- 0.21, N = 3SE +/- 0.07, N = 3SE +/- 0.16, N = 1531.8831.8531.7932.1231.9332.9232.4236.4235.5635.0734.1934.3231.9431.9170.7638.0338.7637.5939.04MIN: 31.55 / MAX: 37.47MIN: 31.69 / MAX: 33.06MIN: 31.63 / MAX: 35.57MIN: 31.66 / MAX: 46.9MIN: 31.62 / MAX: 35.85MIN: 32.67 / MAX: 36.93MIN: 31.89 / MAX: 65.47MIN: 33.49 / MAX: 224.86MIN: 33.19 / MAX: 40.43MIN: 33.66 / MAX: 39.36MIN: 32.72 / MAX: 36.79MIN: 32.58 / MAX: 41.88MIN: 31.73 / MAX: 34.21MIN: 31.74 / MAX: 34.28MIN: 38.81 / MAX: 250.01MIN: 32.66 / MAX: 467.28MIN: 33.12 / MAX: 539.58MIN: 34.45 / MAX: 457.98MIN: 33.83 / MAX: 463.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.21, N = 158.168.218.008.178.108.348.369.888.398.568.568.588.388.0216.229.078.648.489.81MIN: 7.9 / MAX: 8.99MIN: 8.14 / MAX: 8.84MIN: 7.94 / MAX: 8.88MIN: 7.99 / MAX: 8.97MIN: 7.98 / MAX: 8.84MIN: 7.99 / MAX: 26.72MIN: 8.27 / MAX: 9.08MIN: 8.14 / MAX: 251.77MIN: 8 / MAX: 10.29MIN: 8.17 / MAX: 10.28MIN: 8.15 / MAX: 9.8MIN: 8.13 / MAX: 9.78MIN: 8.31 / MAX: 8.86MIN: 7.95 / MAX: 8.63MIN: 7.74 / MAX: 314.84MIN: 7.61 / MAX: 402.49MIN: 8.28 / MAX: 10.42MIN: 8.09 / MAX: 9.64MIN: 7.82 / MAX: 241.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.26, N = 157.097.077.067.087.057.087.107.467.587.647.627.637.167.0615.828.477.838.229.11MIN: 6.98 / MAX: 7.95MIN: 7 / MAX: 8.07MIN: 7 / MAX: 8.03MIN: 6.97 / MAX: 7.99MIN: 6.95 / MAX: 8MIN: 6.98 / MAX: 8.07MIN: 6.99 / MAX: 8.59MIN: 6.9 / MAX: 8.9MIN: 6.98 / MAX: 9.05MIN: 7.05 / MAX: 9.12MIN: 7.01 / MAX: 9.28MIN: 7 / MAX: 9.17MIN: 7.05 / MAX: 13.55MIN: 7 / MAX: 7.82MIN: 6.99 / MAX: 82.57MIN: 6.29 / MAX: 533.92MIN: 7.21 / MAX: 9.32MIN: 7.56 / MAX: 9.8MIN: 6.35 / MAX: 130.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinyabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090714212835SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.18, N = 1512.8412.8712.8112.8512.8713.1713.6415.1613.7913.6713.6513.8012.8812.8328.5915.5413.9715.7215.26MIN: 12.69 / MAX: 15.33MIN: 12.76 / MAX: 13.73MIN: 12.73 / MAX: 13.08MIN: 12.72 / MAX: 13.93MIN: 12.68 / MAX: 13.84MIN: 13.03 / MAX: 14.1MIN: 13.04 / MAX: 76.32MIN: 12.86 / MAX: 248.64MIN: 12.75 / MAX: 19.63MIN: 12.71 / MAX: 14.88MIN: 12.71 / MAX: 14.99MIN: 12.76 / MAX: 15.76MIN: 12.76 / MAX: 13.67MIN: 12.74 / MAX: 13.59MIN: 12.87 / MAX: 325.37MIN: 12.15 / MAX: 492.01MIN: 13.11 / MAX: 16.15MIN: 13.2 / MAX: 301.81MIN: 12.87 / MAX: 132.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50abcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090612182430SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.26, N = 1510.0110.0010.0010.1010.1010.2610.3412.9610.8110.8410.9411.0710.1010.0623.4812.6014.1313.0812.45MIN: 9.88 / MAX: 11.4MIN: 9.92 / MAX: 12.35MIN: 9.91 / MAX: 11.15MIN: 9.86 / MAX: 11.08MIN: 9.84 / MAX: 11.72MIN: 10.09 / MAX: 11.22MIN: 10.14 / MAX: 11.37MIN: 10.23 / MAX: 424.46MIN: 9.95 / MAX: 12.78MIN: 9.93 / MAX: 12.81MIN: 9.95 / MAX: 12.7MIN: 10.1 / MAX: 13.23MIN: 9.97 / MAX: 11.42MIN: 9.95 / MAX: 11.04MIN: 10.06 / MAX: 112.91MIN: 9.82 / MAX: 418.4MIN: 10.63 / MAX: 167.28MIN: 10.11 / MAX: 444.45MIN: 11.55 / MAX: 14.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.18, N = 154.314.334.334.314.314.644.876.534.624.654.684.684.354.3110.885.254.646.795.20MIN: 4.24 / MAX: 5.2MIN: 4.28 / MAX: 5.16MIN: 4.26 / MAX: 10.59MIN: 4.25 / MAX: 5.28MIN: 4.23 / MAX: 11.03MIN: 4.57 / MAX: 5.49MIN: 4.8 / MAX: 5.62MIN: 4.57 / MAX: 242.16MIN: 4.26 / MAX: 6.15MIN: 4.26 / MAX: 6.53MIN: 4.26 / MAX: 6.61MIN: 4.26 / MAX: 6.23MIN: 4.28 / MAX: 7.49MIN: 4.26 / MAX: 5.26MIN: 4.38 / MAX: 52.99MIN: 4.23 / MAX: 375.94MIN: 4.26 / MAX: 5.98MIN: 4.23 / MAX: 262.43MIN: 4.82 / MAX: 7.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18abcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.20, N = 155.285.235.215.235.225.486.225.825.675.615.625.595.275.2012.686.285.696.017.44MIN: 5.17 / MAX: 6.16MIN: 5.13 / MAX: 6.18MIN: 5.11 / MAX: 6.04MIN: 5.08 / MAX: 6.28MIN: 5.09 / MAX: 11.15MIN: 5.33 / MAX: 6.16MIN: 6.11 / MAX: 7MIN: 5.28 / MAX: 7.02MIN: 5.18 / MAX: 7.22MIN: 5.11 / MAX: 7.44MIN: 5.1 / MAX: 7.65MIN: 5.06 / MAX: 6.95MIN: 5.15 / MAX: 6.19MIN: 5.09 / MAX: 5.98MIN: 5.39 / MAX: 262.62MIN: 4.94 / MAX: 298.06MIN: 5.16 / MAX: 8.22MIN: 5.44 / MAX: 8.18MIN: 5.29 / MAX: 320.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16abcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901122334455SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.14, N = 3SE +/- 0.24, N = 1523.5123.5623.5423.5623.6024.5524.2027.8325.0025.0425.0125.8223.5523.4848.2929.0628.8227.0429.29MIN: 23.29 / MAX: 24.68MIN: 23.34 / MAX: 24.72MIN: 23.33 / MAX: 24.61MIN: 23.24 / MAX: 24.78MIN: 23.17 / MAX: 24.71MIN: 23.62 / MAX: 97.69MIN: 23.56 / MAX: 58.31MIN: 24.98 / MAX: 262.23MIN: 23.93 / MAX: 26.69MIN: 24.06 / MAX: 27.35MIN: 23.8 / MAX: 26.41MIN: 24.35 / MAX: 62.94MIN: 23.3 / MAX: 24.45MIN: 23.24 / MAX: 29.21MIN: 24.97 / MAX: 183.12MIN: 24.11 / MAX: 541.55MIN: 24.35 / MAX: 214.1MIN: 24.22 / MAX: 296.13MIN: 24.63 / MAX: 296.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.22, N = 157.907.857.807.857.858.158.968.758.428.408.428.417.877.8219.499.8710.6210.658.70MIN: 7.74 / MAX: 9.54MIN: 7.76 / MAX: 8.76MIN: 7.72 / MAX: 8.74MIN: 7.71 / MAX: 8.85MIN: 7.71 / MAX: 8.76MIN: 8.02 / MAX: 9.02MIN: 8.82 / MAX: 9.87MIN: 8.08 / MAX: 16.01MIN: 7.79 / MAX: 10.01MIN: 7.77 / MAX: 9.78MIN: 7.73 / MAX: 10.06MIN: 7.72 / MAX: 9.9MIN: 7.76 / MAX: 10.36MIN: 7.69 / MAX: 8.61MIN: 7.4 / MAX: 200.01MIN: 7.33 / MAX: 399.24MIN: 7.83 / MAX: 323.31MIN: 8.29 / MAX: 236.11MIN: 7.96 / MAX: 10.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefaceabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40900.89551.7912.68653.5824.4775SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.16, N = 151.381.371.371.381.381.381.411.401.411.411.421.421.391.373.981.601.391.401.40MIN: 1.34 / MAX: 1.85MIN: 1.35 / MAX: 1.75MIN: 1.35 / MAX: 1.82MIN: 1.34 / MAX: 2.25MIN: 1.34 / MAX: 1.88MIN: 1.35 / MAX: 2.08MIN: 1.38 / MAX: 2.09MIN: 1.33 / MAX: 2MIN: 1.35 / MAX: 2.01MIN: 1.35 / MAX: 1.9MIN: 1.36 / MAX: 1.93MIN: 1.36 / MAX: 2.01MIN: 1.37 / MAX: 1.82MIN: 1.36 / MAX: 1.46MIN: 1.31 / MAX: 228.4MIN: 1.11 / MAX: 436.01MIN: 1.33 / MAX: 1.94MIN: 1.33 / MAX: 1.93MIN: 1.34 / MAX: 1.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0abcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.18, N = 153.863.823.833.873.843.863.865.884.014.054.044.043.883.868.994.534.344.094.10MIN: 3.8 / MAX: 4.6MIN: 3.78 / MAX: 4.39MIN: 3.79 / MAX: 4.61MIN: 3.77 / MAX: 9.91MIN: 3.79 / MAX: 4.76MIN: 3.78 / MAX: 10.45MIN: 3.82 / MAX: 4.22MIN: 4.04 / MAX: 364.21MIN: 3.78 / MAX: 5.34MIN: 3.83 / MAX: 6.11MIN: 3.82 / MAX: 5.33MIN: 3.8 / MAX: 5.31MIN: 3.84 / MAX: 4.39MIN: 3.82 / MAX: 4.34MIN: 3.71 / MAX: 129.99MIN: 3.75 / MAX: 396.62MIN: 4.14 / MAX: 5.84MIN: 3.87 / MAX: 5.46MIN: 3.86 / MAX: 5.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901.14532.29063.43594.58125.7265SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.16, N = 152.982.952.962.972.962.972.983.203.073.083.073.062.992.975.093.403.183.154.70MIN: 2.92 / MAX: 4.03MIN: 2.92 / MAX: 3.42MIN: 2.93 / MAX: 3.41MIN: 2.92 / MAX: 3.34MIN: 2.91 / MAX: 5.9MIN: 2.93 / MAX: 3.66MIN: 2.94 / MAX: 3.65MIN: 3.07 / MAX: 3.86MIN: 2.93 / MAX: 4.63MIN: 2.94 / MAX: 3.67MIN: 2.95 / MAX: 4.19MIN: 2.92 / MAX: 3.73MIN: 2.96 / MAX: 3.14MIN: 2.94 / MAX: 3.28MIN: 2.86 / MAX: 53.75MIN: 2.72 / MAX: 432.18MIN: 3.05 / MAX: 4.64MIN: 3 / MAX: 4.54MIN: 3 / MAX: 188.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2abcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.20, N = 153.353.333.323.353.333.403.353.493.433.443.503.463.393.367.073.983.453.493.51MIN: 3.29 / MAX: 3.85MIN: 3.3 / MAX: 3.59MIN: 3.29 / MAX: 4.19MIN: 3.3 / MAX: 3.82MIN: 3.28 / MAX: 4.14MIN: 3.35 / MAX: 5.89MIN: 3.3 / MAX: 4.02MIN: 3.35 / MAX: 4.24MIN: 3.3 / MAX: 4.22MIN: 3.3 / MAX: 5.36MIN: 3.37 / MAX: 4.85MIN: 3.32 / MAX: 5.24MIN: 3.35 / MAX: 3.69MIN: 3.32 / MAX: 4.06MIN: 3.25 / MAX: 243.32MIN: 3.14 / MAX: 529.82MIN: 3.32 / MAX: 3.99MIN: 3.36 / MAX: 4.33MIN: 3.37 / MAX: 41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2abcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.14, N = 153.173.143.133.163.143.133.183.293.263.293.263.293.183.177.813.563.303.313.43MIN: 3.09 / MAX: 3.78MIN: 3.1 / MAX: 3.73MIN: 3.08 / MAX: 3.85MIN: 3.09 / MAX: 3.92MIN: 3.08 / MAX: 4.06MIN: 3.07 / MAX: 3.82MIN: 3.13 / MAX: 3.9MIN: 3.12 / MAX: 3.93MIN: 3.1 / MAX: 4.12MIN: 3.12 / MAX: 4.14MIN: 3.1 / MAX: 3.87MIN: 3.11 / MAX: 3.98MIN: 3.14 / MAX: 3.63MIN: 3.12 / MAX: 3.64MIN: 3.07 / MAX: 154.75MIN: 3.09 / MAX: 345.01MIN: 3.12 / MAX: 4.82MIN: 3.14 / MAX: 4.92MIN: 3.25 / MAX: 4.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.25, N = 158.058.048.038.028.048.278.1710.408.448.578.378.478.078.0321.119.3510.5510.238.45MIN: 7.95 / MAX: 8.89MIN: 7.95 / MAX: 14.33MIN: 7.98 / MAX: 8.84MIN: 7.95 / MAX: 9.81MIN: 7.95 / MAX: 9.09MIN: 8.17 / MAX: 9.04MIN: 8.08 / MAX: 9.37MIN: 7.97 / MAX: 455.46MIN: 7.98 / MAX: 10.55MIN: 7.98 / MAX: 10MIN: 7.97 / MAX: 16.09MIN: 8.04 / MAX: 10.17MIN: 7.99 / MAX: 8.8MIN: 7.96 / MAX: 8.77MIN: 7.98 / MAX: 322.43MIN: 7.49 / MAX: 474.12MIN: 8.22 / MAX: 303.1MIN: 8.13 / MAX: 386.42MIN: 8.03 / MAX: 12.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDetabcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.45, N = 3SE +/- 0.01, N = 3SE +/- 0.23, N = 153.624.054.114.084.222.572.664.424.344.174.164.214.088.653.945.485.274.51MIN: 2.7 / MAX: 4.54MIN: 4.02 / MAX: 4.35MIN: 4.08 / MAX: 4.4MIN: 4.02 / MAX: 4.28MIN: 4.18 / MAX: 4.97MIN: 2.53 / MAX: 3.21MIN: 2.54 / MAX: 3.41MIN: 4.25 / MAX: 6.71MIN: 4.19 / MAX: 5.77MIN: 4.05 / MAX: 4.74MIN: 4 / MAX: 4.69MIN: 4.19 / MAX: 4.41MIN: 4.05 / MAX: 4.84MIN: 3.94 / MAX: 185.21MIN: 2.43 / MAX: 267.02MIN: 2.67 / MAX: 259.34MIN: 4.05 / MAX: 247.02MIN: 4.34 / MAX: 5.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefaceabcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40900.67051.3412.01152.6823.3525SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.14, N = 151.381.381.391.381.371.381.401.401.421.421.401.381.382.981.601.271.451.33MIN: 1.35 / MAX: 2.06MIN: 1.35 / MAX: 1.67MIN: 1.36 / MAX: 1.53MIN: 1.35 / MAX: 2.05MIN: 1.34 / MAX: 2.11MIN: 1.36 / MAX: 1.62MIN: 1.34 / MAX: 2MIN: 1.34 / MAX: 2.15MIN: 1.35 / MAX: 1.88MIN: 1.36 / MAX: 2.02MIN: 1.34 / MAX: 2.1MIN: 1.35 / MAX: 2.23MIN: 1.36 / MAX: 1.71MIN: 1.29 / MAX: 144.96MIN: 0.95 / MAX: 433.24MIN: 1.21 / MAX: 1.95MIN: 1.38 / MAX: 2.96MIN: 1.27 / MAX: 1.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v3-v3 - Model: mobilenet-v3bcfgi40804080 rep4080 xxx4080 zzz3090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.18, N = 153.163.173.153.153.263.273.273.333.203.158.063.653.124.902.61MIN: 3.11 / MAX: 3.75MIN: 3.11 / MAX: 8.89MIN: 3.1 / MAX: 3.8MIN: 3.1 / MAX: 3.87MIN: 3.12 / MAX: 4.19MIN: 3.12 / MAX: 5.24MIN: 3.14 / MAX: 3.99MIN: 3.19 / MAX: 4.2MIN: 3.06 / MAX: 3.84MIN: 3.11 / MAX: 3.83MIN: 2.96 / MAX: 219.87MIN: 2.87 / MAX: 347.75MIN: 2.99 / MAX: 5.09MIN: 3.17 / MAX: 120.84MIN: 2.5 / MAX: 3.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3 - Model: mobilenet-v3bcfgi40804080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901.21052.4213.63154.8426.0525SE +/- 0.22, N = 143.163.163.153.163.293.283.313.273.153.155.383.763.253.533.35MIN: 3.12 / MAX: 3.69MIN: 3.12 / MAX: 3.7MIN: 3.11 / MAX: 3.48MIN: 3.11 / MAX: 3.93MIN: 3.15 / MAX: 4.32MIN: 3.14 / MAX: 3.89MIN: 3.16 / MAX: 5.3MIN: 3.14 / MAX: 4.63MIN: 3.11 / MAX: 3.71MIN: 3.11 / MAX: 3.6MIN: 2.74 / MAX: 121.29MIN: 2.89 / MAX: 366.04MIN: 3.11 / MAX: 4.74MIN: 3.2 / MAX: 40.81MIN: 3.21 / MAX: 5.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformerabcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409020406080100SE +/- 0.29, N = 3SE +/- 0.39, N = 3SE +/- 0.12, N = 1532.4931.9531.7732.4333.5632.7337.8035.0735.2834.2734.1033.0131.8075.3437.9138.2537.8138.90MIN: 31.67 / MAX: 40.11MIN: 31.79 / MAX: 32.33MIN: 31.61 / MAX: 35.68MIN: 31.56 / MAX: 37.69MIN: 32.98 / MAX: 51.93MIN: 31.44 / MAX: 81.32MIN: 33.74 / MAX: 321.51MIN: 33.14 / MAX: 43.26MIN: 33.9 / MAX: 38.67MIN: 32.82 / MAX: 39.79MIN: 32.65 / MAX: 37.64MIN: 32.88 / MAX: 33.42MIN: 31.66 / MAX: 32.23MIN: 38.72 / MAX: 418.01MIN: 32.08 / MAX: 541.11MIN: 33.04 / MAX: 447.7MIN: 32.66 / MAX: 453.44MIN: 34.2 / MAX: 300.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400mabcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.19, N = 158.188.188.278.238.088.309.948.248.678.458.378.258.2418.008.838.139.6610.17MIN: 8.07 / MAX: 9.68MIN: 8.12 / MAX: 8.86MIN: 8.22 / MAX: 9.18MIN: 8.03 / MAX: 8.9MIN: 7.98 / MAX: 10.87MIN: 8.22 / MAX: 9.1MIN: 7.43 / MAX: 166.02MIN: 7.89 / MAX: 9.52MIN: 8.22 / MAX: 15.29MIN: 8.12 / MAX: 9.68MIN: 8.05 / MAX: 10.19MIN: 8.17 / MAX: 8.9MIN: 8.17 / MAX: 8.84MIN: 7.91 / MAX: 176.28MIN: 7.65 / MAX: 351.08MIN: 7.78 / MAX: 9.98MIN: 7.78 / MAX: 95.3MIN: 8.12 / MAX: 209.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssdabcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.24, N = 157.077.067.107.097.237.138.967.737.867.627.557.527.1213.208.137.867.319.11MIN: 7.01 / MAX: 8.07MIN: 7.01 / MAX: 7.55MIN: 7.05 / MAX: 7.65MIN: 6.99 / MAX: 9.39MIN: 7.15 / MAX: 8.02MIN: 7.04 / MAX: 8.43MIN: 6.92 / MAX: 244.02MIN: 7.13 / MAX: 9.7MIN: 7.22 / MAX: 10.84MIN: 7.01 / MAX: 8.84MIN: 7 / MAX: 8.72MIN: 7.45 / MAX: 7.74MIN: 7.05 / MAX: 7.63MIN: 6.9 / MAX: 68.61MIN: 6.37 / MAX: 399.11MIN: 7.25 / MAX: 8.98MIN: 6.71 / MAX: 9.3MIN: 6.77 / MAX: 101.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tinyabcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090714212835SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.18, N = 1512.9012.7412.8112.9513.3217.2314.6513.8514.0313.6013.6314.2612.7727.6615.2013.6815.3815.40MIN: 12.69 / MAX: 15.88MIN: 12.66 / MAX: 13.28MIN: 12.74 / MAX: 13.2MIN: 12.75 / MAX: 18.88MIN: 12.95 / MAX: 35.49MIN: 12.99 / MAX: 196.66MIN: 12.44 / MAX: 202.68MIN: 12.84 / MAX: 16.75MIN: 13.15 / MAX: 15.97MIN: 12.8 / MAX: 16.23MIN: 12.77 / MAX: 15.36MIN: 14.17 / MAX: 14.53MIN: 12.7 / MAX: 13.02MIN: 12.74 / MAX: 294.9MIN: 12.69 / MAX: 431.37MIN: 12.83 / MAX: 14.63MIN: 12.32 / MAX: 188.07MIN: 12.35 / MAX: 321.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50abcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.23, N = 3SE +/- 0.01, N = 3SE +/- 0.26, N = 1510.2010.0110.1110.0011.0510.7212.0911.1611.7610.8211.1010.309.9521.5012.7314.1012.7311.41MIN: 9.84 / MAX: 12.48MIN: 9.85 / MAX: 11.06MIN: 9.95 / MAX: 16.18MIN: 9.86 / MAX: 11.02MIN: 10.14 / MAX: 162.88MIN: 10.1 / MAX: 108.3MIN: 11.16 / MAX: 13.48MIN: 10.29 / MAX: 15.03MIN: 10.68 / MAX: 44.94MIN: 9.9 / MAX: 12.26MIN: 10.2 / MAX: 13.06MIN: 9.82 / MAX: 17.56MIN: 9.85 / MAX: 10.72MIN: 10.24 / MAX: 116.85MIN: 10.18 / MAX: 541.92MIN: 10.27 / MAX: 287MIN: 10.22 / MAX: 181.72MIN: 10.57 / MAX: 12.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnetabcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.11, N = 3SE +/- 0.01, N = 3SE +/- 0.21, N = 144.414.324.314.304.364.325.304.754.674.684.694.304.319.625.495.145.145.18MIN: 4.24 / MAX: 5.16MIN: 4.26 / MAX: 5.15MIN: 4.26 / MAX: 4.98MIN: 4.23 / MAX: 5.32MIN: 4.29 / MAX: 5.7MIN: 4.25 / MAX: 5.17MIN: 4.92 / MAX: 7.18MIN: 4.31 / MAX: 13.88MIN: 4.27 / MAX: 5.88MIN: 4.28 / MAX: 6.37MIN: 4.29 / MAX: 5.78MIN: 4.25 / MAX: 4.83MIN: 4.26 / MAX: 5.18MIN: 4.31 / MAX: 147.6MIN: 4.26 / MAX: 363.39MIN: 4.73 / MAX: 6.32MIN: 4.76 / MAX: 6.26MIN: 4.75 / MAX: 7.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18abcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.17, N = 155.295.205.245.235.695.555.605.695.685.565.635.215.2914.036.086.008.077.82MIN: 5.09 / MAX: 6.29MIN: 5.1 / MAX: 5.9MIN: 5.15 / MAX: 6.09MIN: 5.1 / MAX: 6.28MIN: 5.22 / MAX: 92.59MIN: 5.19 / MAX: 25.4MIN: 5.13 / MAX: 6.83MIN: 5.16 / MAX: 7.68MIN: 5.17 / MAX: 7.45MIN: 5.09 / MAX: 6.84MIN: 5.08 / MAX: 7.55MIN: 5.09 / MAX: 6.04MIN: 5.18 / MAX: 6.19MIN: 5 / MAX: 303.38MIN: 4.97 / MAX: 245.95MIN: 5.47 / MAX: 7.29MIN: 5.86 / MAX: 121.03MIN: 5.54 / MAX: 303.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16abcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901326395265SE +/- 0.30, N = 3SE +/- 0.05, N = 3SE +/- 0.23, N = 1523.7523.4923.4523.5124.1923.7830.9625.3726.1125.0325.4023.4323.4356.6428.3627.7528.1929.54MIN: 23.31 / MAX: 25.12MIN: 23.36 / MAX: 24.62MIN: 23.26 / MAX: 24.51MIN: 23.19 / MAX: 24.68MIN: 23.99 / MAX: 30.98MIN: 23.52 / MAX: 24.89MIN: 25.92 / MAX: 328.63MIN: 24.26 / MAX: 36.52MIN: 24.54 / MAX: 30.29MIN: 23.85 / MAX: 28.9MIN: 24.09 / MAX: 32.86MIN: 23.2 / MAX: 24.1MIN: 23.23 / MAX: 24.39MIN: 25.75 / MAX: 367.74MIN: 24.13 / MAX: 449.57MIN: 24.58 / MAX: 282.59MIN: 24.69 / MAX: 205.72MIN: 24.77 / MAX: 364.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenetabcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.11, N = 3SE +/- 0.01, N = 3SE +/- 0.22, N = 157.947.827.937.857.927.9810.308.428.528.388.407.867.9018.259.6910.279.538.93MIN: 7.71 / MAX: 8.73MIN: 7.73 / MAX: 8.65MIN: 7.82 / MAX: 8.91MIN: 7.71 / MAX: 8.83MIN: 7.8 / MAX: 8.96MIN: 7.86 / MAX: 8.78MIN: 8.19 / MAX: 349.57MIN: 7.75 / MAX: 9.96MIN: 7.84 / MAX: 10.21MIN: 7.72 / MAX: 10.05MIN: 7.72 / MAX: 10.5MIN: 7.76 / MAX: 8.74MIN: 7.79 / MAX: 8.74MIN: 7.5 / MAX: 267.89MIN: 7.29 / MAX: 407.61MIN: 7.95 / MAX: 115.68MIN: 8.86 / MAX: 11.44MIN: 8.27 / MAX: 10.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0abcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.19, N = 153.903.853.883.853.873.914.053.994.094.043.993.873.869.234.724.234.034.37MIN: 3.82 / MAX: 4.51MIN: 3.81 / MAX: 4.42MIN: 3.84 / MAX: 4.41MIN: 3.81 / MAX: 4.46MIN: 3.81 / MAX: 4.97MIN: 3.85 / MAX: 4.64MIN: 3.78 / MAX: 5.45MIN: 3.79 / MAX: 5.83MIN: 3.86 / MAX: 5.59MIN: 3.83 / MAX: 5.71MIN: 3.8 / MAX: 5.69MIN: 3.83 / MAX: 4.69MIN: 3.81 / MAX: 4.75MIN: 3.43 / MAX: 156.19MIN: 3.37 / MAX: 486.93MIN: 3.98 / MAX: 12.23MIN: 3.86 / MAX: 4.82MIN: 4.15 / MAX: 5.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnetabcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.14, N = 152.972.972.992.982.973.002.743.053.063.063.042.992.976.883.263.123.224.77MIN: 2.92 / MAX: 3.48MIN: 2.93 / MAX: 3.45MIN: 2.96 / MAX: 3.44MIN: 2.94 / MAX: 3.83MIN: 2.93 / MAX: 3.95MIN: 2.96 / MAX: 3.68MIN: 2.62 / MAX: 4.22MIN: 2.92 / MAX: 3.82MIN: 2.94 / MAX: 4.51MIN: 2.94 / MAX: 4.45MIN: 2.91 / MAX: 4.47MIN: 2.95 / MAX: 3.88MIN: 2.93 / MAX: 3.28MIN: 3.05 / MAX: 110.25MIN: 2.46 / MAX: 277.54MIN: 2.98 / MAX: 3.79MIN: 3.11 / MAX: 3.71MIN: 3.07 / MAX: 97.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2abcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.19, N = 153.343.343.353.353.553.595.033.413.433.453.423.343.356.823.773.553.513.45MIN: 3.3 / MAX: 3.85MIN: 3.31 / MAX: 3.77MIN: 3.31 / MAX: 3.8MIN: 3.3 / MAX: 3.82MIN: 3.27 / MAX: 22.86MIN: 3.3 / MAX: 25.28MIN: 3.07 / MAX: 228.55MIN: 3.28 / MAX: 4.87MIN: 3.3 / MAX: 4.15MIN: 3.32 / MAX: 3.85MIN: 3.28 / MAX: 4.19MIN: 3.3 / MAX: 4.19MIN: 3.31 / MAX: 3.68MIN: 3.16 / MAX: 64.72MIN: 3.02 / MAX: 511.95MIN: 3.39 / MAX: 5.48MIN: 3.38 / MAX: 5.4MIN: 3.32 / MAX: 4.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2abcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.17, N = 153.163.163.183.173.153.163.523.283.283.283.253.173.179.673.763.304.743.60MIN: 3.1 / MAX: 3.8MIN: 3.11 / MAX: 3.61MIN: 3.13 / MAX: 3.84MIN: 3.1 / MAX: 8.86MIN: 3.1 / MAX: 3.65MIN: 3.11 / MAX: 3.83MIN: 3.29 / MAX: 19.18MIN: 3.11 / MAX: 3.88MIN: 3.11 / MAX: 4MIN: 3.1 / MAX: 4.05MIN: 3.09 / MAX: 4.51MIN: 3.12 / MAX: 4.05MIN: 3.11 / MAX: 4.94MIN: 3.19 / MAX: 225.84MIN: 2.6 / MAX: 364.73MIN: 3.11 / MAX: 4.81MIN: 3.09 / MAX: 140.79MIN: 3.43 / MAX: 4.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenetabcdfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.22, N = 158.057.978.028.108.4522.748.378.738.418.378.388.608.0117.819.4310.088.438.15MIN: 7.97 / MAX: 9.07MIN: 7.94 / MAX: 8.26MIN: 7.98 / MAX: 8.33MIN: 7.94 / MAX: 14.4MIN: 8.37 / MAX: 9.44MIN: 8.24 / MAX: 1264.67MIN: 8.15 / MAX: 9.75MIN: 8.15 / MAX: 10.96MIN: 8.14 / MAX: 11.03MIN: 7.96 / MAX: 9.72MIN: 7.94 / MAX: 10.16MIN: 8.5 / MAX: 13.72MIN: 7.96 / MAX: 9.85MIN: 8.05 / MAX: 159.41MIN: 7.95 / MAX: 398.1MIN: 8.1 / MAX: 118.32MIN: 8.04 / MAX: 18.04MIN: 7.73 / MAX: 9.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: FastestDetbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.27, N = 144.074.083.853.975.694.204.184.194.044.044.119.184.332.934.164.06MIN: 4.03 / MAX: 5.83MIN: 4.05 / MAX: 4.36MIN: 3.8 / MAX: 4.65MIN: 3.92 / MAX: 4.75MIN: 3.69 / MAX: 261.71MIN: 4.06 / MAX: 4.86MIN: 4.03 / MAX: 5.07MIN: 4.04 / MAX: 5.47MIN: 3.89 / MAX: 5.01MIN: 4.01 / MAX: 4.15MIN: 4.07 / MAX: 4.21MIN: 3.64 / MAX: 122.65MIN: 2.59 / MAX: 433.58MIN: 2.84 / MAX: 3.38MIN: 4 / MAX: 5.58MIN: 3.91 / MAX: 5.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: vision_transformerbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409020406080100SE +/- 0.18, N = 1531.6531.7833.4733.3936.5534.2034.2734.3734.4731.8931.9381.7737.8638.7939.1238.99MIN: 31.53 / MAX: 32.23MIN: 31.64 / MAX: 34.51MIN: 32.89 / MAX: 74.09MIN: 32.73 / MAX: 88.83MIN: 33 / MAX: 209.38MIN: 32.92 / MAX: 36.19MIN: 33.07 / MAX: 37.01MIN: 33.01 / MAX: 38.7MIN: 33.32 / MAX: 37.42MIN: 31.66 / MAX: 39.97MIN: 31.76 / MAX: 33.09MIN: 44.4 / MAX: 460.28MIN: 32.9 / MAX: 463.9MIN: 33.95 / MAX: 457.41MIN: 33.92 / MAX: 465.83MIN: 34.17 / MAX: 473.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: regnety_400mbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.21, N = 158.058.148.348.078.218.338.578.758.477.958.0919.669.028.1317.159.55MIN: 8 / MAX: 8.58MIN: 8.08 / MAX: 8.69MIN: 8.26 / MAX: 9.3MIN: 7.97 / MAX: 8.81MIN: 7.9 / MAX: 9.99MIN: 8.02 / MAX: 9.64MIN: 8.21 / MAX: 10.39MIN: 8.35 / MAX: 10.08MIN: 8.13 / MAX: 10.27MIN: 7.88 / MAX: 8.67MIN: 7.99 / MAX: 14.25MIN: 7.5 / MAX: 235.36MIN: 7.69 / MAX: 501.76MIN: 7.75 / MAX: 10.05MIN: 8.02 / MAX: 773.45MIN: 7.5 / MAX: 193.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: squeezenet_ssdbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.24, N = 157.037.046.977.268.167.647.597.647.357.047.0917.758.399.329.309.37MIN: 6.97 / MAX: 7.88MIN: 6.96 / MAX: 7.83MIN: 6.83 / MAX: 13.87MIN: 7.14 / MAX: 8.59MIN: 7.51 / MAX: 9.94MIN: 7.05 / MAX: 9.9MIN: 7.02 / MAX: 8.87MIN: 7.03 / MAX: 9.19MIN: 6.79 / MAX: 9.82MIN: 6.96 / MAX: 7.74MIN: 7.02 / MAX: 7.99MIN: 6.47 / MAX: 272.11MIN: 6.53 / MAX: 436.05MIN: 7.1 / MAX: 172.56MIN: 6.92 / MAX: 310.91MIN: 7.07 / MAX: 281.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: yolov4-tinybcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090714212835SE +/- 0.14, N = 1512.9812.8913.0713.0815.1113.8113.5513.6913.8312.8712.8229.3415.4215.3015.3415.62MIN: 12.73 / MAX: 35.55MIN: 12.84 / MAX: 13.19MIN: 12.95 / MAX: 14.55MIN: 12.96 / MAX: 13.83MIN: 12.93 / MAX: 151.45MIN: 12.84 / MAX: 15.1MIN: 12.75 / MAX: 14.74MIN: 12.73 / MAX: 15.68MIN: 12.89 / MAX: 15.4MIN: 12.75 / MAX: 13.58MIN: 12.72 / MAX: 13.48MIN: 12.17 / MAX: 245.34MIN: 12.21 / MAX: 414.81MIN: 12.87 / MAX: 144.73MIN: 12.94 / MAX: 157.95MIN: 12.99 / MAX: 1841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: resnet50bcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090612182430SE +/- 0.22, N = 1510.0110.3311.0511.2514.0511.1110.7910.9111.2110.0510.0724.0712.1111.3913.8213.68MIN: 9.89 / MAX: 10.86MIN: 10.16 / MAX: 13.97MIN: 10.46 / MAX: 112.6MIN: 10.55 / MAX: 118.12MIN: 11.69 / MAX: 252.21MIN: 10.19 / MAX: 13.03MIN: 9.91 / MAX: 12.75MIN: 9.91 / MAX: 13.1MIN: 10.3 / MAX: 13.25MIN: 9.85 / MAX: 12.64MIN: 9.94 / MAX: 11.06MIN: 10.02 / MAX: 218.35MIN: 10.16 / MAX: 382.56MIN: 10.48 / MAX: 13.29MIN: 10.34 / MAX: 245.6MIN: 10.25 / MAX: 566.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: alexnetbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.23, N = 154.294.284.834.715.014.664.654.654.674.314.3011.005.554.945.274.67MIN: 4.24 / MAX: 5.64MIN: 4.24 / MAX: 5.12MIN: 4.76 / MAX: 5.74MIN: 4.65 / MAX: 5.57MIN: 4.6 / MAX: 6.68MIN: 4.29 / MAX: 6.1MIN: 4.26 / MAX: 6.13MIN: 4.28 / MAX: 6.42MIN: 4.28 / MAX: 6.29MIN: 4.25 / MAX: 5.13MIN: 4.24 / MAX: 4.99MIN: 4.33 / MAX: 199.92MIN: 4.2 / MAX: 281.58MIN: 4.51 / MAX: 6.64MIN: 4.78 / MAX: 7.7MIN: 4.28 / MAX: 5.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: resnet18bcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.19, N = 155.215.266.135.485.865.705.635.665.715.195.2011.146.185.817.757.61MIN: 5.12 / MAX: 6.22MIN: 5.18 / MAX: 6.27MIN: 5.41 / MAX: 151.51MIN: 5.37 / MAX: 6.51MIN: 5.35 / MAX: 7.79MIN: 5.15 / MAX: 7.9MIN: 5.09 / MAX: 7.75MIN: 5.14 / MAX: 7.49MIN: 5.12 / MAX: 8.19MIN: 5.09 / MAX: 6.13MIN: 5.1 / MAX: 5.97MIN: 4.79 / MAX: 65.12MIN: 5.17 / MAX: 262.79MIN: 5.27 / MAX: 7.16MIN: 5.57 / MAX: 125.43MIN: 5.23 / MAX: 90.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: vgg16bcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901122334455SE +/- 0.24, N = 1523.5023.9924.4524.9229.1225.1024.9125.0025.4523.5023.5449.7528.4028.5527.2527.04MIN: 23.3 / MAX: 24.41MIN: 23.72 / MAX: 24.98MIN: 24.26 / MAX: 25.26MIN: 24.58 / MAX: 31.89MIN: 26.33 / MAX: 310.23MIN: 24.12 / MAX: 27.57MIN: 23.8 / MAX: 26.87MIN: 23.91 / MAX: 27.99MIN: 24.22 / MAX: 27.73MIN: 23.17 / MAX: 24.44MIN: 23.33 / MAX: 24.41MIN: 25.45 / MAX: 273.86MIN: 24.12 / MAX: 509.06MIN: 24.05 / MAX: 201.8MIN: 24.14 / MAX: 379.93MIN: 24.33 / MAX: 215.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: googlenetbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.24, N = 157.847.888.079.1510.178.458.528.508.557.837.8517.009.659.979.299.02MIN: 7.74 / MAX: 8.7MIN: 7.79 / MAX: 8.78MIN: 7.92 / MAX: 8.86MIN: 7.84 / MAX: 198.46MIN: 7.94 / MAX: 150.01MIN: 7.79 / MAX: 10.32MIN: 7.81 / MAX: 10.78MIN: 7.79 / MAX: 9.94MIN: 7.85 / MAX: 10.35MIN: 7.71 / MAX: 8.8MIN: 7.75 / MAX: 8.69MIN: 7.35 / MAX: 277.79MIN: 7.59 / MAX: 472.81MIN: 7.67 / MAX: 258.52MIN: 7.98 / MAX: 83.03MIN: 8.41 / MAX: 11.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: blazefacebcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40900.68181.36362.04542.72723.409SE +/- 0.19, N = 151.371.381.431.371.281.441.421.421.411.361.373.031.791.171.341.16MIN: 1.35 / MAX: 1.52MIN: 1.36 / MAX: 1.58MIN: 1.4 / MAX: 1.77MIN: 1.34 / MAX: 2.07MIN: 1.23 / MAX: 1.73MIN: 1.37 / MAX: 3.45MIN: 1.36 / MAX: 2.2MIN: 1.36 / MAX: 1.92MIN: 1.34 / MAX: 1.91MIN: 1.34 / MAX: 1.46MIN: 1.35 / MAX: 1.46MIN: 1.28 / MAX: 96.94MIN: 1.13 / MAX: 312.12MIN: 1.11 / MAX: 1.9MIN: 1.27 / MAX: 1.95MIN: 1.11 / MAX: 1.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: efficientnet-b0bcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.22, N = 153.823.894.044.144.684.024.024.064.033.833.859.014.784.094.344.04MIN: 3.79 / MAX: 4.34MIN: 3.83 / MAX: 9.72MIN: 3.99 / MAX: 4.82MIN: 4.09 / MAX: 5.13MIN: 4.48 / MAX: 6.02MIN: 3.82 / MAX: 5.66MIN: 3.82 / MAX: 5.39MIN: 3.83 / MAX: 5.55MIN: 3.82 / MAX: 5.43MIN: 3.78 / MAX: 4.41MIN: 3.81 / MAX: 4.53MIN: 3.98 / MAX: 188.57MIN: 3.82 / MAX: 411.19MIN: 3.86 / MAX: 4.83MIN: 4.16 / MAX: 5.28MIN: 3.78 / MAX: 4.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: mnasnetbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.04, N = 152.972.973.123.053.393.083.093.073.062.952.966.873.113.193.234.61MIN: 2.94 / MAX: 3.43MIN: 2.94 / MAX: 3.43MIN: 3.08 / MAX: 3.86MIN: 3.01 / MAX: 3.88MIN: 3.26 / MAX: 4.86MIN: 2.94 / MAX: 4.52MIN: 2.95 / MAX: 4.52MIN: 2.94 / MAX: 3.6MIN: 2.93 / MAX: 3.64MIN: 2.92 / MAX: 3.29MIN: 2.94 / MAX: 3.38MIN: 2.93 / MAX: 216.41MIN: 2.8 / MAX: 4.98MIN: 3.06 / MAX: 3.75MIN: 3.1 / MAX: 3.75MIN: 2.78 / MAX: 222.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: shufflenet-v2bcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.21, N = 153.333.343.403.383.523.463.433.473.433.323.338.134.095.183.593.46MIN: 3.3 / MAX: 3.79MIN: 3.32 / MAX: 3.79MIN: 3.35 / MAX: 4.17MIN: 3.34 / MAX: 4.15MIN: 3.39 / MAX: 4.05MIN: 3.34 / MAX: 3.93MIN: 3.3 / MAX: 4.03MIN: 3.33 / MAX: 5.01MIN: 3.31 / MAX: 3.94MIN: 3.28 / MAX: 3.66MIN: 3.3 / MAX: 3.67MIN: 3.09 / MAX: 147.21MIN: 3.12 / MAX: 435.28MIN: 3.34 / MAX: 283.54MIN: 3.46 / MAX: 4.09MIN: 3.32 / MAX: 5.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v2-v2 - Model: mobilenet-v2bcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.10, N = 153.153.143.163.153.303.313.273.303.283.143.179.193.413.463.453.39MIN: 3.1 / MAX: 3.68MIN: 3.1 / MAX: 3.67MIN: 3.09 / MAX: 3.89MIN: 3.1 / MAX: 3.63MIN: 3.14 / MAX: 4.82MIN: 3.12 / MAX: 4.76MIN: 3.1 / MAX: 4.34MIN: 3.12 / MAX: 4.03MIN: 3.1 / MAX: 4MIN: 3.08 / MAX: 3.7MIN: 3.11 / MAX: 4.5MIN: 3.04 / MAX: 232.12MIN: 2.99 / MAX: 184.91MIN: 3.29 / MAX: 4.38MIN: 3.23 / MAX: 4.55MIN: 3.21 / MAX: 4.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3 - Model: mobilenetbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.23, N = 158.018.008.568.9810.088.438.488.448.408.068.0317.829.628.968.748.91MIN: 7.95 / MAX: 8.95MIN: 7.96 / MAX: 8.63MIN: 8.04 / MAX: 75.44MIN: 8.1 / MAX: 124.43MIN: 8.08 / MAX: 286.28MIN: 7.99 / MAX: 10.44MIN: 7.96 / MAX: 10.32MIN: 7.97 / MAX: 10.71MIN: 8.12 / MAX: 10.11MIN: 7.94 / MAX: 13.92MIN: 7.98 / MAX: 8.77MIN: 7.57 / MAX: 211.62MIN: 7.76 / MAX: 454.91MIN: 8.39 / MAX: 10.77MIN: 8.25 / MAX: 10.5MIN: 8.33 / MAX: 10.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: regnety_400mbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.25, N = 148.277.988.507.997.998.458.448.588.108.018.2517.238.899.6010.347.73MIN: 8.22 / MAX: 9.01MIN: 7.93 / MAX: 8.65MIN: 8.04 / MAX: 30.12MIN: 7.91 / MAX: 8.8MIN: 7.62 / MAX: 9.27MIN: 8.05 / MAX: 10.3MIN: 8.04 / MAX: 10.17MIN: 8.23 / MAX: 10.39MIN: 7.77 / MAX: 15.42MIN: 7.93 / MAX: 8.35MIN: 8.12 / MAX: 14MIN: 7.8 / MAX: 193.14MIN: 7.74 / MAX: 476.28MIN: 7.66 / MAX: 210.23MIN: 8.21 / MAX: 214.16MIN: 7.43 / MAX: 9.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: FastestDetbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.15, N = 154.063.694.203.974.434.204.094.314.124.044.108.634.263.944.165.92MIN: 4.03 / MAX: 4.3MIN: 3.66 / MAX: 3.92MIN: 4.15 / MAX: 4.92MIN: 3.93 / MAX: 4.73MIN: 4.28 / MAX: 5.01MIN: 4.04 / MAX: 5.82MIN: 3.92 / MAX: 5.5MIN: 4.14 / MAX: 6.11MIN: 3.97 / MAX: 6.99MIN: 4 / MAX: 4.15MIN: 4.06 / MAX: 4.21MIN: 4.27 / MAX: 144.3MIN: 2.71 / MAX: 347.03MIN: 3.8 / MAX: 5.41MIN: 4.03 / MAX: 4.73MIN: 4.25 / MAX: 103.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: vision_transformerbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901632486480SE +/- 0.13, N = 1531.7131.6633.3632.6838.3334.1334.2935.4034.0531.8632.1173.5138.2939.0138.7338.58MIN: 31.56 / MAX: 33.03MIN: 31.52 / MAX: 32.14MIN: 32.83 / MAX: 76.21MIN: 32.02 / MAX: 87.72MIN: 34.14 / MAX: 246.43MIN: 32.98 / MAX: 36.11MIN: 33.11 / MAX: 40.12MIN: 33.93 / MAX: 39.3MIN: 32.83 / MAX: 38.57MIN: 31.58 / MAX: 35.84MIN: 31.94 / MAX: 33.01MIN: 39.27 / MAX: 288.2MIN: 32.31 / MAX: 557.38MIN: 33.91 / MAX: 411.66MIN: 33.81 / MAX: 362.17MIN: 33.77 / MAX: 476.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: squeezenet_ssdbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.19, N = 157.147.077.097.318.337.667.637.707.517.047.0816.158.297.937.817.72MIN: 7.06 / MAX: 7.95MIN: 7.01 / MAX: 7.75MIN: 6.98 / MAX: 8.01MIN: 6.96 / MAX: 30.1MIN: 6.32 / MAX: 222.03MIN: 7.02 / MAX: 9.08MIN: 7.02 / MAX: 9.71MIN: 7.11 / MAX: 9.19MIN: 6.94 / MAX: 9.51MIN: 6.97 / MAX: 7.76MIN: 7.01 / MAX: 7.93MIN: 7.25 / MAX: 210.69MIN: 6.37 / MAX: 448.22MIN: 7.31 / MAX: 9.45MIN: 7.24 / MAX: 9.04MIN: 7.12 / MAX: 23.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: yolov4-tinybcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090714212835SE +/- 0.23, N = 1512.7712.8614.3413.3515.4313.7913.6813.9513.6212.8812.8429.4915.4415.4416.3916.61MIN: 12.69 / MAX: 13.71MIN: 12.76 / MAX: 13.98MIN: 14.23 / MAX: 15.12MIN: 12.87 / MAX: 58.52MIN: 13.1 / MAX: 210.2MIN: 12.79 / MAX: 15.92MIN: 12.77 / MAX: 15.57MIN: 13.03 / MAX: 15.9MIN: 12.75 / MAX: 15.79MIN: 12.75 / MAX: 13.79MIN: 12.76 / MAX: 13.7MIN: 13.03 / MAX: 182.99MIN: 12.61 / MAX: 387.62MIN: 12.92 / MAX: 211.43MIN: 12.97 / MAX: 369.64MIN: 12.32 / MAX: 375.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: resnet50bcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090612182430SE +/- 0.27, N = 159.8710.0310.2510.4311.1510.9510.8411.5011.099.9710.0123.1112.3514.5813.5713.13MIN: 9.79 / MAX: 10.73MIN: 9.93 / MAX: 10.96MIN: 10.05 / MAX: 11.08MIN: 10.19 / MAX: 11.32MIN: 10.31 / MAX: 12.97MIN: 9.91 / MAX: 17.11MIN: 9.93 / MAX: 12.83MIN: 10.5 / MAX: 13.47MIN: 10.18 / MAX: 13.12MIN: 9.86 / MAX: 10.84MIN: 9.91 / MAX: 10.74MIN: 10.22 / MAX: 140.41MIN: 9.83 / MAX: 424.28MIN: 10.67 / MAX: 324.82MIN: 10.45 / MAX: 199.55MIN: 10.56 / MAX: 323.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: alexnetbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.23, N = 154.424.304.354.864.994.694.695.214.654.304.309.865.676.116.586.11MIN: 4.32 / MAX: 5.1MIN: 4.26 / MAX: 5.16MIN: 4.27 / MAX: 5.16MIN: 4.8 / MAX: 6.37MIN: 4.59 / MAX: 6.56MIN: 4.26 / MAX: 6.15MIN: 4.26 / MAX: 7.17MIN: 4.79 / MAX: 6.66MIN: 4.26 / MAX: 5.97MIN: 4.25 / MAX: 5.08MIN: 4.25 / MAX: 4.7MIN: 4.25 / MAX: 157.02MIN: 4.21 / MAX: 365.75MIN: 4.73 / MAX: 81.72MIN: 4.61 / MAX: 91.07MIN: 4.83 / MAX: 124.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: resnet18bcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.16, N = 155.425.235.305.505.855.655.695.895.595.235.2413.386.235.975.815.84MIN: 5.36 / MAX: 6.27MIN: 5.11 / MAX: 6.03MIN: 5.17 / MAX: 5.93MIN: 5.4 / MAX: 6.38MIN: 5.3 / MAX: 8.27MIN: 5.14 / MAX: 6.93MIN: 5.11 / MAX: 6.94MIN: 5.36 / MAX: 7.53MIN: 5.09 / MAX: 7.7MIN: 5.1 / MAX: 6.07MIN: 5.14 / MAX: 5.99MIN: 5.43 / MAX: 208.42MIN: 4.99 / MAX: 309.18MIN: 5.46 / MAX: 7.02MIN: 5.3 / MAX: 6.82MIN: 5.35 / MAX: 7.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: vgg16bcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901224364860SE +/- 0.27, N = 1523.4223.5424.1224.7129.0725.0425.0426.0825.2623.5023.4355.4228.4028.2127.5927.77MIN: 23.27 / MAX: 24.32MIN: 23.32 / MAX: 24.54MIN: 23.57 / MAX: 46.44MIN: 23.88 / MAX: 119.23MIN: 24.45 / MAX: 263.33MIN: 23.87 / MAX: 28.04MIN: 23.81 / MAX: 27.15MIN: 24.52 / MAX: 27.73MIN: 24.14 / MAX: 27.73MIN: 23.23 / MAX: 24.26MIN: 23.26 / MAX: 24.3MIN: 25.32 / MAX: 281.46MIN: 23.98 / MAX: 456MIN: 24.57 / MAX: 270.76MIN: 24.34 / MAX: 396.09MIN: 24.82 / MAX: 264.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: googlenetbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.21, N = 157.977.837.948.3510.198.498.588.998.377.827.8520.729.868.878.9010.01MIN: 7.89 / MAX: 8.7MIN: 7.74 / MAX: 8.61MIN: 7.8 / MAX: 8.78MIN: 8.2 / MAX: 9.39MIN: 7.73 / MAX: 212.36MIN: 7.82 / MAX: 11.98MIN: 7.79 / MAX: 10.48MIN: 8.25 / MAX: 10.27MIN: 7.76 / MAX: 10.31MIN: 7.69 / MAX: 8.6MIN: 7.75 / MAX: 8.64MIN: 7.49 / MAX: 355.33MIN: 7.54 / MAX: 396.21MIN: 8.18 / MAX: 11.09MIN: 8.22 / MAX: 11.07MIN: 7.29 / MAX: 259.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: blazefacebcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40900.71551.4312.14652.8623.5775SE +/- 0.18, N = 151.371.361.371.381.251.421.451.421.391.361.383.181.711.331.411.07MIN: 1.35 / MAX: 1.39MIN: 1.34 / MAX: 1.44MIN: 1.35 / MAX: 1.62MIN: 1.36 / MAX: 1.76MIN: 1.19 / MAX: 2.61MIN: 1.35 / MAX: 2.15MIN: 1.36 / MAX: 8.73MIN: 1.36 / MAX: 1.92MIN: 1.34 / MAX: 1.89MIN: 1.34 / MAX: 1.61MIN: 1.36 / MAX: 1.9MIN: 1.31 / MAX: 185.03MIN: 1.09 / MAX: 448.17MIN: 1.27 / MAX: 1.98MIN: 1.35 / MAX: 1.89MIN: 1.02 / MAX: 1.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: efficientnet-b0bcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.18, N = 153.853.823.854.634.214.054.044.223.953.853.857.814.734.186.285.26MIN: 3.82 / MAX: 4.48MIN: 3.78 / MAX: 4.53MIN: 3.8 / MAX: 4.6MIN: 3.8 / MAX: 159.43MIN: 3.96 / MAX: 4.94MIN: 3.83 / MAX: 5MIN: 3.81 / MAX: 5.08MIN: 4 / MAX: 5.58MIN: 3.76 / MAX: 4.84MIN: 3.8 / MAX: 4.43MIN: 3.81 / MAX: 4.62MIN: 3.73 / MAX: 159.47MIN: 3.79 / MAX: 418.72MIN: 4 / MAX: 5.25MIN: 3.91 / MAX: 337.73MIN: 3.48 / MAX: 250.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: mnasnetbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.16, N = 142.962.962.962.982.993.093.073.133.012.972.976.023.373.003.102.54MIN: 2.93 / MAX: 3.4MIN: 2.93 / MAX: 3.41MIN: 2.92 / MAX: 3.81MIN: 2.95 / MAX: 3.63MIN: 2.86 / MAX: 4.38MIN: 2.94 / MAX: 3.79MIN: 2.94 / MAX: 3.72MIN: 3 / MAX: 5.1MIN: 2.91 / MAX: 3.6MIN: 2.92 / MAX: 3.28MIN: 2.94 / MAX: 3.39MIN: 2.79 / MAX: 50.49MIN: 2.86 / MAX: 278.87MIN: 2.89 / MAX: 3.46MIN: 2.97 / MAX: 3.72MIN: 2.44 / MAX: 3.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: shufflenet-v2bcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901.10032.20063.30094.40125.5015SE +/- 0.22, N = 153.333.333.333.353.363.443.443.513.373.343.364.893.953.343.403.17MIN: 3.3 / MAX: 3.77MIN: 3.31 / MAX: 3.81MIN: 3.29 / MAX: 3.99MIN: 3.31 / MAX: 4.01MIN: 3.25 / MAX: 4.02MIN: 3.31 / MAX: 4.88MIN: 3.32 / MAX: 4.16MIN: 3.37 / MAX: 4.26MIN: 3.25 / MAX: 3.95MIN: 3.31 / MAX: 3.6MIN: 3.32 / MAX: 3.7MIN: 3.04 / MAX: 18.32MIN: 3.19 / MAX: 410.41MIN: 3.23 / MAX: 4.78MIN: 3.26 / MAX: 4.84MIN: 3.04 / MAX: 3.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3-v2-v2 - Model: mobilenet-v2bcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.18, N = 153.153.153.163.173.283.293.303.403.233.163.177.243.664.993.314.45MIN: 3.11 / MAX: 3.88MIN: 3.11 / MAX: 3.85MIN: 3.1 / MAX: 3.71MIN: 3.13 / MAX: 3.58MIN: 3.09 / MAX: 5.28MIN: 3.12 / MAX: 4.64MIN: 3.12 / MAX: 4.7MIN: 3.23 / MAX: 4.8MIN: 3.06 / MAX: 4.66MIN: 3.11 / MAX: 3.51MIN: 3.12 / MAX: 4.03MIN: 3.04 / MAX: 261.68MIN: 3.01 / MAX: 437.59MIN: 3.1 / MAX: 201.8MIN: 3.12 / MAX: 4.6MIN: 2.65 / MAX: 216.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3-v3 - Model: mobilenetbcfgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.26, N = 158.007.958.658.209.058.438.468.888.388.008.0116.349.628.819.5410.54MIN: 7.95 / MAX: 8.99MIN: 7.89 / MAX: 8.79MIN: 8.55 / MAX: 9.53MIN: 8.12 / MAX: 9.4MIN: 8.48 / MAX: 11.28MIN: 7.99 / MAX: 10.66MIN: 7.99 / MAX: 10.62MIN: 8.31 / MAX: 10.01MIN: 7.95 / MAX: 10.41MIN: 7.94 / MAX: 8.78MIN: 7.95 / MAX: 8.35MIN: 8.13 / MAX: 80.69MIN: 7.76 / MAX: 502.83MIN: 8.32 / MAX: 10.7MIN: 8.94 / MAX: 10.54MIN: 8.41 / MAX: 134.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

VkFFT

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in single precisionabcdefghi40804080 rep4080 xxx4080 zzz30903090 rep40904090 repnv 409030K60K90K120K150KSE +/- 9.54, N = 3SE +/- 2.73, N = 3SE +/- 1.67, N = 3SE +/- 25.50, N = 34788747948479714264542651564765645556431697381045561044911045281045431413571414371538961539391521701. (CXX) g++ options: -O3

Test: FFT + iFFT C2C 1D batched in single precision

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

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 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: FastestDet3090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.15, N = 34.077.234.144.624.595.86MIN: 4.04 / MAX: 4.25MIN: 3.75 / MAX: 121.71MIN: 3.73 / MAX: 5.07MIN: 4.48 / MAX: 5.16MIN: 4.44 / MAX: 5.2MIN: 3.9 / MAX: 190.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: vision_transformer3090 rep3070RTX 3070 Ti40904090 repnv 40901632486480SE +/- 0.10, N = 331.9470.5338.5039.3538.6537.13MIN: 31.73 / MAX: 32.75MIN: 39.2 / MAX: 276.33MIN: 33.7 / MAX: 418.06MIN: 34.22 / MAX: 466.65MIN: 33.07 / MAX: 476.08MIN: 33.97 / MAX: 443.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: regnety_400m3090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.54, N = 38.0617.029.1410.118.708.34MIN: 7.98 / MAX: 8.6MIN: 7.65 / MAX: 216.63MIN: 8.14 / MAX: 400.02MIN: 8.03 / MAX: 259.38MIN: 8.29 / MAX: 12.6MIN: 8.01 / MAX: 12.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: squeezenet_ssd3090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.14, N = 37.0715.327.457.439.448.26MIN: 6.98 / MAX: 9.71MIN: 6.66 / MAX: 139.17MIN: 6.59 / MAX: 9.11MIN: 6.84 / MAX: 8.82MIN: 7.17 / MAX: 94.63MIN: 7.64 / MAX: 11.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: yolov4-tiny3090 rep3070RTX 3070 Ti40904090 repnv 4090714212835SE +/- 0.94, N = 312.9229.3814.6416.0515.4116.30MIN: 12.79 / MAX: 18.5MIN: 12.95 / MAX: 201.31MIN: 12.77 / MAX: 383.28MIN: 12.93 / MAX: 474.03MIN: 12.75 / MAX: 226.87MIN: 14.11 / MAX: 184.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: resnet503090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.30, N = 310.2722.1513.1513.0010.9613.25MIN: 10.12 / MAX: 11.19MIN: 10.11 / MAX: 123.04MIN: 10.26 / MAX: 349.93MIN: 10.34 / MAX: 397.57MIN: 10.09 / MAX: 12.99MIN: 10.61 / MAX: 154.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: alexnet3090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.57, N = 34.3111.436.255.145.346.32MIN: 4.26 / MAX: 4.83MIN: 4.24 / MAX: 178.83MIN: 4.27 / MAX: 334.55MIN: 4.75 / MAX: 7.34MIN: 4.87 / MAX: 6.57MIN: 4.26 / MAX: 195.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: resnet183090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.05, N = 35.2712.135.946.965.875.58MIN: 5.15 / MAX: 6.11MIN: 5.32 / MAX: 123.4MIN: 5.32 / MAX: 8.32MIN: 5.3 / MAX: 242.18MIN: 5.41 / MAX: 7.58MIN: 5.09 / MAX: 6.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: vgg163090 rep3070RTX 3070 Ti40904090 repnv 40901224364860SE +/- 0.28, N = 323.7253.4827.8627.3229.8527.25MIN: 23.56 / MAX: 24.59MIN: 25.52 / MAX: 296.52MIN: 24.17 / MAX: 416.36MIN: 24.36 / MAX: 262.38MIN: 24.25 / MAX: 400.86MIN: 24.12 / MAX: 252.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: googlenet3090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.55, N = 37.8618.809.978.5510.4710.14MIN: 7.75 / MAX: 8.57MIN: 7.78 / MAX: 141.46MIN: 8.16 / MAX: 381.49MIN: 7.85 / MAX: 11.39MIN: 7.86 / MAX: 191.94MIN: 7.85 / MAX: 257.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: blazeface3090 rep3070RTX 3070 Ti40904090 repnv 40900.60531.21061.81592.42123.0265SE +/- 0.04, N = 31.382.691.401.351.421.40MIN: 1.36 / MAX: 1.73MIN: 1.35 / MAX: 48.81MIN: 1.28 / MAX: 1.91MIN: 1.28 / MAX: 1.84MIN: 1.36 / MAX: 2.03MIN: 1.34 / MAX: 1.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: efficientnet-b03090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.08, N = 33.846.634.174.634.105.82MIN: 3.8 / MAX: 4.67MIN: 3.75 / MAX: 22.34MIN: 3.86 / MAX: 5.52MIN: 4.38 / MAX: 6.01MIN: 3.88 / MAX: 5.04MIN: 3.98 / MAX: 197.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mnasnet3090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.02, N = 32.968.553.123.233.123.10MIN: 2.92 / MAX: 3.27MIN: 2.99 / MAX: 185.5MIN: 2.97 / MAX: 4.65MIN: 3.08 / MAX: 4.73MIN: 3 / MAX: 4.1MIN: 2.97 / MAX: 3.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: shufflenet-v23090 rep3070RTX 3070 Ti40904090 repnv 40901.32532.65063.97595.30126.6265SE +/- 0.02, N = 33.325.893.483.565.233.43MIN: 3.29 / MAX: 3.62MIN: 3.19 / MAX: 97.88MIN: 3.33 / MAX: 5.22MIN: 3.43 / MAX: 4.24MIN: 3.34 / MAX: 185.57MIN: 3.29 / MAX: 5.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mobilenet-v33090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.04, N = 33.197.343.243.363.354.96MIN: 3.13 / MAX: 3.61MIN: 3.09 / MAX: 155.33MIN: 3.05 / MAX: 5.14MIN: 3.22 / MAX: 4.62MIN: 3.22 / MAX: 3.99MIN: 3.14 / MAX: 189.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v2-v2 - Model: mobilenet-v23090 rep3070RTX 3070 Ti40904090 repnv 40901.3322.6643.9965.3286.66SE +/- 0.53, N = 33.155.923.834.753.383.29MIN: 3.1 / MAX: 3.75MIN: 3.16 / MAX: 103.24MIN: 3.11 / MAX: 343.21MIN: 2.93 / MAX: 147.66MIN: 3.2 / MAX: 4MIN: 3.12 / MAX: 4.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mobilenet3090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.13, N = 38.0317.0610.0210.568.2210.64MIN: 7.97 / MAX: 8.91MIN: 8 / MAX: 101.45MIN: 7.8 / MAX: 372.36MIN: 8.32 / MAX: 239.95MIN: 7.75 / MAX: 9.41MIN: 8.4 / MAX: 127.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v3-v3 - Model: mobilenet-v34080 rep4080 xxx4080 zzz3090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.53, N = 33.283.083.063.176.433.703.333.304.97MIN: 3.13 / MAX: 4.78MIN: 2.97 / MAX: 3.67MIN: 2.94 / MAX: 3.94MIN: 3.12 / MAX: 3.75MIN: 2.85 / MAX: 164.91MIN: 2.98 / MAX: 261.6MIN: 3.2 / MAX: 4.4MIN: 3.15 / MAX: 3.91MIN: 3.15 / MAX: 291.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

VkFFT

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in single precision, no reshufflingabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep40904090 repnv 409030K60K90K120K150KSE +/- 8.89, N = 3SE +/- 2.33, N = 3SE +/- 2.08, N = 350504506435059643365433655711057094711631062101062051060991059261439691439561526561559361551481. (CXX) g++ options: -O3

Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

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 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: FastestDet4080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.87, N = 34.203.803.824.104.077.124.182.853.123.93MIN: 4.04 / MAX: 5.63MIN: 3.65 / MAX: 6.08MIN: 3.65 / MAX: 9.77MIN: 4.07 / MAX: 4.34MIN: 4.03 / MAX: 4.2MIN: 3.72 / MAX: 188.7MIN: 2.53 / MAX: 295.11MIN: 2.74 / MAX: 4.36MIN: 2.97 / MAX: 4.42MIN: 3.76 / MAX: 11.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: vision_transformer4080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901530456075SE +/- 0.11, N = 334.2234.1434.4732.1031.8565.4138.0438.7638.7938.95MIN: 33.01 / MAX: 37.09MIN: 32.5 / MAX: 37.13MIN: 33.05 / MAX: 39.69MIN: 31.9 / MAX: 33.03MIN: 31.67 / MAX: 35.74MIN: 39.08 / MAX: 230.59MIN: 33.11 / MAX: 346.94MIN: 33.38 / MAX: 423.24MIN: 34.02 / MAX: 460.15MIN: 34.04 / MAX: 486.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: regnety_400m4080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.29, N = 38.728.388.348.228.0318.258.4210.0910.238.25MIN: 8.32 / MAX: 10.48MIN: 8.04 / MAX: 9.63MIN: 8.03 / MAX: 10.23MIN: 8.14 / MAX: 8.67MIN: 7.97 / MAX: 8.65MIN: 7.8 / MAX: 238.29MIN: 7.66 / MAX: 10.74MIN: 8.01 / MAX: 418.58MIN: 8.22 / MAX: 197.1MIN: 7.87 / MAX: 10.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: squeezenet_ssd4080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.23, N = 37.677.277.257.127.0914.277.579.519.387.48MIN: 7.06 / MAX: 9.96MIN: 6.73 / MAX: 8.77MIN: 6.72 / MAX: 8.05MIN: 7.04 / MAX: 7.97MIN: 7.02 / MAX: 7.86MIN: 7.01 / MAX: 51.13MIN: 6.69 / MAX: 10MIN: 7.11 / MAX: 307.17MIN: 6.77 / MAX: 224.11MIN: 6.85 / MAX: 9.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: yolov4-tiny4080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090714212835SE +/- 0.81, N = 313.7113.6313.4212.8212.8128.4114.5715.8513.8817.67MIN: 12.78 / MAX: 15.62MIN: 12.77 / MAX: 16.93MIN: 12.65 / MAX: 16.19MIN: 12.72 / MAX: 13.66MIN: 12.7 / MAX: 13.69MIN: 12.49 / MAX: 151.04MIN: 12.33 / MAX: 312.42MIN: 13.26 / MAX: 253.23MIN: 13.09 / MAX: 14.77MIN: 14.92 / MAX: 343.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: resnet504080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.04, N = 310.8611.2611.1010.0310.0622.1912.8111.7212.4713.29MIN: 9.98 / MAX: 12.46MIN: 10.32 / MAX: 13.29MIN: 10.19 / MAX: 18.3MIN: 9.93 / MAX: 10.87MIN: 9.86 / MAX: 11.9MIN: 10.16 / MAX: 181.74MIN: 10.06 / MAX: 349.03MIN: 10.8 / MAX: 12.8MIN: 11.5 / MAX: 14.68MIN: 10.54 / MAX: 456.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: alexnet4080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.43, N = 34.684.694.664.334.3110.596.174.995.456.62MIN: 4.27 / MAX: 6.08MIN: 4.26 / MAX: 6.07MIN: 4.24 / MAX: 5.97MIN: 4.26 / MAX: 5.19MIN: 4.26 / MAX: 5.07MIN: 4.3 / MAX: 177.68MIN: 4.5 / MAX: 261.75MIN: 4.56 / MAX: 6.91MIN: 4.93 / MAX: 7.98MIN: 4.28 / MAX: 339.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: resnet184080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.30, N = 35.645.785.775.205.3012.646.227.748.146.07MIN: 5.11 / MAX: 7.51MIN: 5.21 / MAX: 6.97MIN: 5.22 / MAX: 7.06MIN: 5.1 / MAX: 6.16MIN: 5.21 / MAX: 6.24MIN: 5.3 / MAX: 53.81MIN: 5.3 / MAX: 8.22MIN: 5.25 / MAX: 312.09MIN: 5.39 / MAX: 122.47MIN: 5.49 / MAX: 15.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: vgg164080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40901122334455SE +/- 0.54, N = 325.0125.4425.2623.5823.4050.3227.9830.1630.7427.61MIN: 23.88 / MAX: 26.66MIN: 24.27 / MAX: 27.68MIN: 24.29 / MAX: 27.75MIN: 23.35 / MAX: 24.43MIN: 23.2 / MAX: 24.07MIN: 25.92 / MAX: 281.06MIN: 24.35 / MAX: 423.63MIN: 24.66 / MAX: 332.49MIN: 25.36 / MAX: 428.68MIN: 24.67 / MAX: 401.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: googlenet4080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090510152025SE +/- 0.80, N = 38.528.328.297.907.9119.209.688.388.9710.75MIN: 7.85 / MAX: 10.56MIN: 7.71 / MAX: 10.39MIN: 7.63 / MAX: 9.87MIN: 7.8 / MAX: 8.73MIN: 7.81 / MAX: 8.62MIN: 7.84 / MAX: 193.36MIN: 8.16 / MAX: 382.41MIN: 7.78 / MAX: 10.43MIN: 8.22 / MAX: 10.51MIN: 7.92 / MAX: 447.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: blazeface4080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40900.56931.13861.70792.27722.8465SE +/- 0.48, N = 31.431.321.311.391.382.532.481.301.421.42MIN: 1.36 / MAX: 2.02MIN: 1.26 / MAX: 2.03MIN: 1.25 / MAX: 1.76MIN: 1.37 / MAX: 1.48MIN: 1.35 / MAX: 1.64MIN: 1.08 / MAX: 118.73MIN: 1.17 / MAX: 344.52MIN: 1.24 / MAX: 1.92MIN: 1.34 / MAX: 2.37MIN: 1.34 / MAX: 1.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: efficientnet-b04080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 40903691215SE +/- 0.46, N = 34.074.013.953.883.859.194.744.474.355.94MIN: 3.85 / MAX: 4.79MIN: 3.83 / MAX: 5.28MIN: 3.79 / MAX: 4.59MIN: 3.83 / MAX: 4.61MIN: 3.81 / MAX: 4.75MIN: 3.85 / MAX: 131.42MIN: 3.68 / MAX: 295.7MIN: 4.23 / MAX: 5.82MIN: 4.08 / MAX: 5.62MIN: 3.97 / MAX: 208.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: mnasnet4080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.13, N = 33.093.002.962.982.976.073.245.195.113.12MIN: 2.96 / MAX: 4.98MIN: 2.88 / MAX: 4.37MIN: 2.85 / MAX: 3.82MIN: 2.95 / MAX: 3.9MIN: 2.93 / MAX: 3.3MIN: 2.94 / MAX: 129.1MIN: 2.9 / MAX: 5.34MIN: 3.04 / MAX: 436.91MIN: 2.96 / MAX: 247.47MIN: 2.98 / MAX: 3.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: shufflenet-v24080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.60, N = 33.473.403.363.363.337.814.023.483.423.32MIN: 3.33 / MAX: 5.39MIN: 3.28 / MAX: 3.87MIN: 3.23 / MAX: 3.99MIN: 3.32 / MAX: 3.66MIN: 3.3 / MAX: 3.78MIN: 3.3 / MAX: 131.26MIN: 3.27 / MAX: 328.59MIN: 3.35 / MAX: 4.05MIN: 3.29 / MAX: 3.94MIN: 3.19 / MAX: 4.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3-v2-v2 - Model: mobilenet-v24080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090246810SE +/- 0.53, N = 33.303.203.163.163.167.223.913.363.443.29MIN: 3.11 / MAX: 4.01MIN: 3.05 / MAX: 4.67MIN: 3.01 / MAX: 5.17MIN: 3.11 / MAX: 3.95MIN: 3.09 / MAX: 4.06MIN: 3.17 / MAX: 69.66MIN: 3.04 / MAX: 394.66MIN: 3.21 / MAX: 4.78MIN: 3.27 / MAX: 4.93MIN: 3.13 / MAX: 4.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3-v3-v3-v3-v3 - Model: mobilenet4080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 409048121620SE +/- 0.14, N = 38.458.348.258.078.0616.5210.039.0410.6112.12MIN: 8.01 / MAX: 10.86MIN: 7.89 / MAX: 9.42MIN: 7.78 / MAX: 9.61MIN: 8.01 / MAX: 8.62MIN: 8 / MAX: 8.96MIN: 7.9 / MAX: 82.53MIN: 7.86 / MAX: 346.64MIN: 8.49 / MAX: 10.96MIN: 8.34 / MAX: 225.97MIN: 9.16 / MAX: 505.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

VkFFT

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in half precisionabcdefghi40804080 rep4080 xxx4080 zzz30903090 rep40904090 repnv 409060K120K180K240K300KSE +/- 83.55, N = 3SE +/- 18.50, N = 3SE +/- 26.03, N = 3SE +/- 133.47, N = 391597918129174485181851911041461041711042981322702110762110582107132109912552072651712903422876512927681. (CXX) g++ options: -O3

Test: FFT + iFFT C2C 1D batched in half precision

3070: The test quit with a non-zero exit status.

RTX 3070 Ti: The test quit with a non-zero exit status.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C multidimensional in single precisionabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep40904090 repnv 409020K40K60K80K100KSE +/- 57.83, N = 3SE +/- 116.12, N = 3SE +/- 437.33, N = 3SE +/- 555.86, N = 333001327513281236328370902623826541346866586970068678877004051005548148140680999828751. (CXX) g++ options: -O3

Test: FFT + iFFT C2C multidimensional in single precision

3070: The test quit with a non-zero exit status. E: VkFFT System: 3840x2160x1 Buffer: 63 MB avg_time_per_step: 2.236 ms std_error: 0.035 num_iter: 64 benchmark: 28982 bandwidth: 331.7

RTX 3070 Ti: The test quit with a non-zero exit status. E: VkFFT System: 3840x2160x1 Buffer: 63 MB avg_time_per_step: 1.462 ms std_error: 0.004 num_iter: 64 benchmark: 44332 bandwidth: 507.3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT R2C / C2Rabcdefghi40804080 rep4080 xxx4080 zzz30903090 rep40904090 repnv 409020K40K60K80K100KSE +/- 200.55, N = 3SE +/- 118.74, N = 3SE +/- 3.71, N = 3SE +/- 796.66, N = 34210542163430213539935304265932663826524337276647368279690686768955347544328435181329848871. (CXX) g++ options: -O3

Test: FFT + iFFT R2C / C2R

3070: The test quit with a non-zero exit status. E: VkFFT System: 512x512x128 Buffer: 128 MB avg_time_per_step: 4.833 ms std_error: 0.038 num_iter: 31 benchmark: 27226 bandwidth: 311.6

RTX 3070 Ti: The test quit with a non-zero exit status. E: VkFFT System: 512x512x128 Buffer: 128 MB avg_time_per_step: 3.494 ms std_error: 0.002 num_iter: 31 benchmark: 37664 bandwidth: 431.0

VkResample

VkResample is a Vulkan-based image upscaling library based on VkFFT. The sample input file is upscaling a 4K image to 8K using Vulkan-based GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Singleabcdefgi40804080 rep4080 xxx4080 zzz30903090 rep3070RTX 3070 Ti40904090 repnv 4090816243240SE +/- 0.001, N = 3SE +/- 0.004, N = 3SE +/- 0.000, N = 3SE +/- 0.029, N = 311.68611.69011.68832.85532.85026.73826.76920.93013.13613.13613.13713.12610.39910.42822.06427.1839.2848.9628.9671. (CXX) g++ options: -O3

173 Results Shown

vkpeak:
  fp16-vec4
  int32-scalar
  int16-vec4
  int32-vec4
  int16-scalar
  fp16-scalar
  fp32-vec4
  fp32-scalar
  fp64-scalar
  fp64-vec4
NCNN:
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenet-v3
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - FastestDet
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - vision_transformer
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - regnety_400m
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - squeezenet_ssd
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - yolov4-tiny
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - resnet50
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - alexnet
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - resnet18
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - vgg16
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - googlenet
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - blazeface
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - efficientnet-b0
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mnasnet
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - shufflenet-v2
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v2-v2 - mobilenet-v2
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenet
VkFFT
VkResample
NCNN:
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - FastestDet
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - vision_transformer
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - regnety_400m
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - squeezenet_ssd
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - yolov4-tiny
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - resnet50
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - alexnet
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - resnet18
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - vgg16
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - googlenet
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - blazeface
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - efficientnet-b0
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mnasnet
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - shufflenet-v2
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenet-v3
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v2-v2 - mobilenet-v2
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenet
VkFFT
NCNN
VkFFT
NCNN:
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - yolov4-tiny
  CPU-v3-v3 - mobilenet-v3
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - FastestDet
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - vision_transformer
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - regnety_400m
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - squeezenet_ssd
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - resnet50
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - alexnet
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - resnet18
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - vgg16
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - googlenet
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - blazeface
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - efficientnet-b0
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - mnasnet
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - shufflenet-v2
  Vulkan GPU-v3-v3-v3-v3-v3-v3-v2-v2 - mobilenet-v2
  Vulkan GPU-v3-v3-v3-v3-v3-v3 - mobilenet
  Vulkan GPU - FastestDet
  Vulkan GPU - vision_transformer
  Vulkan GPU - regnety_400m
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - resnet50
  Vulkan GPU - alexnet
  Vulkan GPU - resnet18
  Vulkan GPU - vgg16
  Vulkan GPU - googlenet
  Vulkan GPU - blazeface
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - mnasnet
  Vulkan GPU - shufflenet-v2
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU - mobilenet
  CPU - FastestDet
  CPU - blazeface
  Vulkan GPU-v3-v3-v3-v3-v3 - mobilenet-v3
  CPU-v3-v3-v3-v3-v3 - mobilenet-v3
  CPU - vision_transformer
  CPU - regnety_400m
  CPU - squeezenet_ssd
  CPU - yolov4-tiny
  CPU - resnet50
  CPU - alexnet
  CPU - resnet18
  CPU - vgg16
  CPU - googlenet
  CPU - efficientnet-b0
  CPU - mnasnet
  CPU - shufflenet-v2
  CPU-v2-v2 - mobilenet-v2
  CPU - mobilenet
  CPU-v3-v3-v3 - FastestDet
  CPU-v3-v3-v3 - vision_transformer
  CPU-v3-v3-v3 - regnety_400m
  CPU-v3-v3-v3 - squeezenet_ssd
  CPU-v3-v3-v3 - yolov4-tiny
  CPU-v3-v3-v3 - resnet50
  CPU-v3-v3-v3 - alexnet
  CPU-v3-v3-v3 - resnet18
  CPU-v3-v3-v3 - vgg16
  CPU-v3-v3-v3 - googlenet
  CPU-v3-v3-v3 - blazeface
  CPU-v3-v3-v3 - efficientnet-b0
  CPU-v3-v3-v3 - mnasnet
  CPU-v3-v3-v3 - shufflenet-v2
  CPU-v3-v3-v3-v2-v2 - mobilenet-v2
  CPU-v3-v3-v3 - mobilenet
  Vulkan GPU-v3-v3-v3 - regnety_400m
  Vulkan GPU-v3-v3-v3 - FastestDet
  Vulkan GPU-v3-v3-v3 - vision_transformer
  Vulkan GPU-v3-v3-v3 - squeezenet_ssd
  Vulkan GPU-v3-v3-v3 - yolov4-tiny
  Vulkan GPU-v3-v3-v3 - resnet50
  Vulkan GPU-v3-v3-v3 - alexnet
  Vulkan GPU-v3-v3-v3 - resnet18
  Vulkan GPU-v3-v3-v3 - vgg16
  Vulkan GPU-v3-v3-v3 - googlenet
  Vulkan GPU-v3-v3-v3 - blazeface
  Vulkan GPU-v3-v3-v3 - efficientnet-b0
  Vulkan GPU-v3-v3-v3 - mnasnet
  Vulkan GPU-v3-v3-v3 - shufflenet-v2
  Vulkan GPU-v3-v3-v3-v2-v2 - mobilenet-v2
  Vulkan GPU-v3-v3-v3 - mobilenet
VkFFT
NCNN:
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - FastestDet
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - vision_transformer
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - regnety_400m
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - squeezenet_ssd
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - yolov4-tiny
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - resnet50
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - alexnet
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - resnet18
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - vgg16
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - googlenet
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - blazeface
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - efficientnet-b0
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mnasnet
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - shufflenet-v2
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenet-v3
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v2-v2 - mobilenet-v2
  CPU-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenet
  CPU-v3-v3-v3-v3-v3-v3-v3-v3 - mobilenet-v3
VkFFT
NCNN:
  CPU-v3-v3-v3-v3-v3-v3 - FastestDet
  CPU-v3-v3-v3-v3-v3-v3 - vision_transformer
  CPU-v3-v3-v3-v3-v3-v3 - regnety_400m
  CPU-v3-v3-v3-v3-v3-v3 - squeezenet_ssd
  CPU-v3-v3-v3-v3-v3-v3 - yolov4-tiny
  CPU-v3-v3-v3-v3-v3-v3 - resnet50
  CPU-v3-v3-v3-v3-v3-v3 - alexnet
  CPU-v3-v3-v3-v3-v3-v3 - resnet18
  CPU-v3-v3-v3-v3-v3-v3 - vgg16
  CPU-v3-v3-v3-v3-v3-v3 - googlenet
  CPU-v3-v3-v3-v3-v3-v3 - blazeface
  CPU-v3-v3-v3-v3-v3-v3 - efficientnet-b0
  CPU-v3-v3-v3-v3-v3-v3 - mnasnet
  CPU-v3-v3-v3-v3-v3-v3 - shufflenet-v2
  CPU-v3-v3-v3-v3-v3-v3-v2-v2 - mobilenet-v2
  CPU-v3-v3-v3-v3-v3-v3 - mobilenet
VkFFT:
  FFT + iFFT C2C 1D batched in half precision
  FFT + iFFT C2C multidimensional in single precision
  FFT + iFFT R2C / C2R
VkResample