NCNN Vulkan - AMD vs. NVIDIA

NCNN Vulkan benchmarks by Michael Larabel.

HTML result view exported from: https://openbenchmarking.org/result/2009285-FI-2009260PT20&grr&rdt.

NCNN Vulkan - AMD vs. NVIDIAProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionDisplay DriverRX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 1660HD Graphics 5500 Broadwell GT2AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS)AMD Starship/Matisse16GB2000GB Corsair Force MP600 + 2000GBSapphire AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 6GB (1780/875MHz)AMD Navi 10 HDMI AudioDELL P2415QRealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 20.045.9.0-050900rc6daily20200925-generic (x86_64) 20200924GNOME Shell 3.36.4X Server 1.20.84.6 Mesa 20.3.0-devel (git-3173367 2020-09-25 focal-oibaf-ppa) (LLVM 10.0.1)OpenCL 2.0 AMD-APP (3182.0)1.2.145GCC 9.3.0 + CUDA 11.0ext43840x2160AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz)AMD Radeon RX 56/64 8GB (1590/800MHz)AMD Vega 10 HDMI AudioAMD Radeon VII 16GB (1801/1000MHz)AMD Vega 20 HDMI AudioAMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz)AMD Navi 10 HDMI AudioASUS NVIDIA GeForce GTX 1650 4GB (1485/4001MHz)NVIDIA Device 10fa5.4.0-48-generic (x86_64)NVIDIA 450.664.6.0OpenCL 2.0 AMD-APP (3182.0) + OpenCL 1.2 CUDA 11.0.2281.2.133NVIDIA GeForce GTX 1080 8GB (1607/5005MHz)NVIDIA GP104 HD AudioNVIDIA GeForce GTX 1060 6GB (1506/4006MHz)NVIDIA GP106 HD AudioNVIDIA GeForce RTX 2060 6GB (1365/7000MHz)NVIDIA TU106 HD AudioNVIDIA GeForce RTX 2060 SUPER 8GB (1470/7000MHz)NVIDIA GeForce RTX 2070 SUPER 8GB (375/405MHz)NVIDIA TU104 HD AudioeVGA NVIDIA GeForce GTX 1660 Ti 6GB (1500/6000MHz)NVIDIA TU116 HD AudioeVGA NVIDIA GeForce GTX 1660 SUPER 6GB (1530/7000MHz)ASUS NVIDIA GeForce GTX 1650 SUPER 4GB (375/810MHz)NVIDIA GeForce GTX 1070 8GB (1506/4006MHz)NVIDIA GP104 HD AudioNVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)NVIDIA TU102 HD AudioZotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz)NVIDIA TU104 HD AudioASUS NVIDIA GeForce RTX 2070 8GB (420/405MHz)NVIDIA TU106 HD AudioNVIDIA GeForce RTX 2080 SUPER 8GB (405/405MHz)NVIDIA TU104 HD AudioASUS NVIDIA GeForce GTX 1660 6GB (1530/4001MHz)NVIDIA TU116 HD AudioIntel Core i5-5300U @ 2.90GHz (2 Cores / 4 Threads)LENOVO 20CLS02KGE (N10ET53W 1.32 BIOS)Intel Broadwell-U-OPI8GB500GB Seagate ST500LM021-1KJ15Intel HD 5500 3GB (900MHz)Intel Broadwell-U AudioIntel I218-LM + Intel 7265Ubuntu 18.04MATE 1.20.1modesetting 1.20.84.6 Mesa 20.0.0-devel padoka PPAOpenCL 2.11.1.129GCC 7.5.01366x768OpenBenchmarking.orgCompiler Details- RX 5600 XT: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- RX 5700: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- RX Vega 56: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- Radeon VII: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- RX 5700 XT: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- GTX 1650: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- GTX 1080: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- GTX 1060: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- RTX 2060: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- RTX 2060 SUPER: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- RTX 2070 SUPER: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- GTX 1660 Ti: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- GTX 1660 SUPER: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- GTX 1650 SUPER: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- GTX 1070: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- RTX 2080 Ti: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- RTX 2080: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- RTX 2070: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- RTX 2080 SUPER: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- GTX 1660: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v- HD Graphics 5500 Broadwell GT2: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -vProcessor Details- RX 5600 XT: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- RX 5700: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- RX Vega 56: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- Radeon VII: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- RX 5700 XT: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- GTX 1650: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- GTX 1080: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- GTX 1060: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- RTX 2060: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- RTX 2060 SUPER: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- RTX 2070 SUPER: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- GTX 1660 Ti: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- GTX 1660 SUPER: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- GTX 1650 SUPER: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- GTX 1070: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- RTX 2080 Ti: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- RTX 2080: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- RTX 2070: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- RTX 2080 SUPER: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- GTX 1660: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013- HD Graphics 5500 Broadwell GT2: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x2fSecurity Details- RX 5600 XT: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- RX 5700: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- RX Vega 56: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- Radeon VII: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- RX 5700 XT: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- GTX 1650: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- GTX 1080: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- GTX 1060: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- RTX 2060: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- RTX 2060 SUPER: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- RTX 2070 SUPER: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- GTX 1660 Ti: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- GTX 1660 SUPER: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- GTX 1650 SUPER: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- GTX 1070: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- RTX 2080 Ti: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- RTX 2080: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- RTX 2070: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- RTX 2080 SUPER: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- GTX 1660: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- HD Graphics 5500 Broadwell GT2: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable

NCNN Vulkan - AMD vs. NVIDIAncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetncnn: CPU - squeezenetrealsr-ncnn: 4x - Yesncnn: 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-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU - squeezenetrealsr-ncnn: 4x - NoRX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 1660HD Graphics 5500 Broadwell GT280.2608.535.025.241.7315.244.240.767.252.331.843.112.156.543.5812.07958.9298.495.245.381.7114.914.270.777.852.251.863.132.186.603.589.35866.1087.676.544.382.2011.565.740.8710.543.092.344.652.956.314.8910.25441.28810.006.623.782.0410.427.220.9211.073.152.604.132.849.025.037.17755.6788.324.464.811.5713.703.870.736.632.081.732.962.056.583.368.982215.51811.958.423.743.3724.155.310.703.502.171.572.291.946.296.8329.372116.4528.844.913.782.0115.044.130.713.401.931.472.252.235.265.8317.214143.94910.528.005.403.1320.205.450.703.652.071.602.421.975.997.7720.54386.3728.744.262.432.0011.083.560.692.841.641.421.791.544.904.7213.40076.3738.543.842.221.7210.313.360.622.611.681.321.931.454.624.6012.12963.8638.303.752.061.688.473.230.662.691.541.361.751.444.654.3310.615117.6749.455.042.742.2615.333.780.662.841.631.461.831.615.135.2417.150120.1489.415.022.752.3815.43.940.632.871.791.331.981.485.095.2017.538186.17910.675.832.952.6121.554.090.643.211.631.401.881.605.425.8025.658102.7879.155.913.842.3914.984.580.713.491.961.552.321.855.476.5215.37444.9867.773.141.611.425.603.050.672.731.481.361.731.444.534.018.26060.3608.223.571.981.638.053.330.712.761.511.441.761.494.654.2810.06175.4378.423.882.241.739.643.710.622.891.771.321.701.454.834.6712.00754.8408.123.531.931.517.633.230.632.711.511.391.621.484.454.309.463138.7219.925.753.052.3716.984.330.673.192.001.512.141.775.575.5219.893112.61134.7252.3164.65251.0161.134.4029.9418.7011.0218.4721.5383.6567.4017.792135.81137.1772.8671.79285.5380.496.5158.9832.0822.1034.3631.99102.65101.6817.752OpenBenchmarking.org

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tinyHD Graphics 5500 Broadwell GT2306090120150SE +/- 0.77, N = 3112.61MIN: 110.21 / MAX: 143.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet50HD Graphics 5500 Broadwell GT2306090120150SE +/- 0.14, N = 3134.72MIN: 132.34 / MAX: 204.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnetHD Graphics 5500 Broadwell GT21224364860SE +/- 0.15, N = 352.31MIN: 51.52 / MAX: 90.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18HD Graphics 5500 Broadwell GT21428425670SE +/- 0.60, N = 364.65MIN: 62.63 / MAX: 73.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg16HD Graphics 5500 Broadwell GT250100150200250SE +/- 0.23, N = 3251.01MIN: 246.67 / MAX: 290.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenetHD Graphics 5500 Broadwell GT21428425670SE +/- 0.34, N = 361.13MIN: 59.79 / MAX: 67.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazefaceHD Graphics 5500 Broadwell GT20.991.982.973.964.95SE +/- 0.01, N = 34.40MIN: 4.27 / MAX: 10.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b0HD Graphics 5500 Broadwell GT2714212835SE +/- 0.04, N = 329.94MIN: 29.3 / MAX: 35.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnetHD Graphics 5500 Broadwell GT2510152025SE +/- 0.02, N = 318.70MIN: 18.28 / MAX: 25.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v2HD Graphics 5500 Broadwell GT23691215SE +/- 0.06, N = 311.02MIN: 10.73 / MAX: 16.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v3HD Graphics 5500 Broadwell GT2510152025SE +/- 0.09, N = 318.47MIN: 17.99 / MAX: 24.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v2HD Graphics 5500 Broadwell GT2510152025SE +/- 0.12, N = 321.53MIN: 20.98 / MAX: 27.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenetHD Graphics 5500 Broadwell GT220406080100SE +/- 0.12, N = 383.65MIN: 82.16 / MAX: 91.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenetHD Graphics 5500 Broadwell GT21530456075SE +/- 0.19, N = 367.40MIN: 65.68 / MAX: 73.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

RealSR-NCNN

Scale: 4x - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 1660HD Graphics 5500 Broadwell GT250100150200250SE +/- 0.13, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.14, N = 3SE +/- 0.29, N = 3SE +/- 0.08, N = 3SE +/- 0.33, N = 3SE +/- 0.26, N = 3SE +/- 0.43, N = 3SE +/- 0.31, N = 3SE +/- 0.19, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.36, N = 3SE +/- 0.23, N = 3SE +/- 0.38, N = 3SE +/- 0.56, N = 3SE +/- 0.19, N = 3SE +/- 0.27, N = 3SE +/- 0.17, N = 380.2658.9366.1141.2955.68215.52116.45143.9586.3776.3763.86117.67120.15186.18102.7944.9960.3675.4454.84138.7217.79

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tinyHD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 1660306090120150SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 4SE +/- 0.01, N = 14SE +/- 0.11, N = 4SE +/- 0.11, N = 3SE +/- 0.08, N = 4SE +/- 0.05, N = 15SE +/- 0.10, N = 3SE +/- 0.06, N = 15SE +/- 0.04, N = 15SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 15SE +/- 0.07, N = 15SE +/- 0.06, N = 15SE +/- 0.07, N = 3SE +/- 0.08, N = 14SE +/- 0.12, N = 7139.848.538.497.6710.008.3211.958.8410.528.748.548.309.459.4110.679.157.778.228.428.129.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet50HD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 1660306090120150SE +/- 0.72, N = 3SE +/- 0.04, N = 3SE +/- 0.16, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 4SE +/- 0.00, N = 14SE +/- 0.18, N = 4SE +/- 0.10, N = 3SE +/- 0.09, N = 4SE +/- 0.04, N = 15SE +/- 0.08, N = 3SE +/- 0.04, N = 15SE +/- 0.03, N = 14SE +/- 0.13, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.09, N = 3SE +/- 0.04, N = 15SE +/- 0.02, N = 7137.025.025.246.546.624.468.424.918.004.263.843.755.045.025.835.913.143.573.883.535.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnetHD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 166020406080100SE +/- 0.48, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 4SE +/- 0.01, N = 14SE +/- 0.03, N = 4SE +/- 0.04, N = 3SE +/- 0.02, N = 4SE +/- 0.04, N = 15SE +/- 0.12, N = 3SE +/- 0.02, N = 15SE +/- 0.04, N = 15SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 14SE +/- 0.02, N = 15SE +/- 0.01, N = 14SE +/- 0.10, N = 3SE +/- 0.03, N = 15SE +/- 0.06, N = 782.095.245.384.383.784.813.743.785.402.432.222.062.742.752.953.841.611.982.241.933.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18HD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 16601632486480SE +/- 0.12, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 4SE +/- 0.00, N = 14SE +/- 0.06, N = 4SE +/- 0.01, N = 3SE +/- 0.06, N = 4SE +/- 0.04, N = 15SE +/- 0.04, N = 3SE +/- 0.04, N = 15SE +/- 0.03, N = 15SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 15SE +/- 0.06, N = 14SE +/- 0.04, N = 14SE +/- 0.03, N = 3SE +/- 0.02, N = 15SE +/- 0.01, N = 771.171.731.712.202.041.573.372.013.132.001.721.682.262.382.612.391.421.631.731.512.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg16HD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 166070140210280350SE +/- 4.32, N = 3SE +/- 0.15, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.11, N = 4SE +/- 0.08, N = 14SE +/- 0.03, N = 4SE +/- 0.14, N = 3SE +/- 0.19, N = 4SE +/- 0.06, N = 15SE +/- 0.56, N = 3SE +/- 0.03, N = 15SE +/- 0.09, N = 15SE +/- 0.17, N = 3SE +/- 0.27, N = 3SE +/- 0.08, N = 15SE +/- 0.03, N = 15SE +/- 0.06, N = 15SE +/- 0.22, N = 3SE +/- 0.06, N = 15SE +/- 0.12, N = 7305.7115.2414.9111.5610.4213.7024.1515.0420.2011.0810.318.4715.3315.4021.5514.985.608.059.647.6316.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenetHD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 166020406080100SE +/- 0.16, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.15, N = 4SE +/- 0.00, N = 14SE +/- 0.01, N = 4SE +/- 0.06, N = 3SE +/- 0.01, N = 4SE +/- 0.04, N = 15SE +/- 0.09, N = 3SE +/- 0.06, N = 15SE +/- 0.04, N = 15SE +/- 0.17, N = 3SE +/- 0.16, N = 3SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.07, N = 15SE +/- 0.22, N = 3SE +/- 0.05, N = 15SE +/- 0.06, N = 781.584.244.275.747.223.875.314.135.453.563.363.233.783.944.094.583.053.333.713.234.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazefaceHD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 1660246810SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 4SE +/- 0.00, N = 14SE +/- 0.01, N = 4SE +/- 0.05, N = 3SE +/- 0.01, N = 4SE +/- 0.04, N = 15SE +/- 0.00, N = 3SE +/- 0.03, N = 15SE +/- 0.03, N = 15SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 15SE +/- 0.05, N = 15SE +/- 0.04, N = 15SE +/- 0.01, N = 3SE +/- 0.02, N = 15SE +/- 0.00, N = 76.670.760.770.870.920.730.700.710.700.690.620.660.660.630.640.710.670.710.620.630.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b0HD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 16601428425670SE +/- 0.23, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 3SE +/- 0.19, N = 3SE +/- 0.06, N = 4SE +/- 0.05, N = 14SE +/- 0.08, N = 4SE +/- 0.10, N = 3SE +/- 0.10, N = 4SE +/- 0.04, N = 15SE +/- 0.01, N = 3SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.12, N = 3SE +/- 0.25, N = 3SE +/- 0.04, N = 15SE +/- 0.08, N = 15SE +/- 0.04, N = 15SE +/- 0.11, N = 3SE +/- 0.05, N = 15SE +/- 0.05, N = 760.607.257.8510.5411.076.633.503.403.652.842.612.692.842.873.213.492.732.762.892.713.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnetHD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 1660714212835SE +/- 0.32, N = 3SE +/- 0.08, N = 3SE +/- 0.00, N = 3SE +/- 0.31, N = 3SE +/- 0.01, N = 4SE +/- 0.02, N = 14SE +/- 0.10, N = 4SE +/- 0.12, N = 3SE +/- 0.03, N = 4SE +/- 0.05, N = 15SE +/- 0.17, N = 2SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 15SE +/- 0.04, N = 14SE +/- 0.03, N = 15SE +/- 0.14, N = 3SE +/- 0.05, N = 15SE +/- 0.07, N = 731.842.332.253.093.152.082.171.932.071.641.681.541.631.791.631.961.481.511.771.512.001. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v2HD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 1660510152025SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 4SE +/- 0.00, N = 14SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 4SE +/- 0.04, N = 15SE +/- 0.03, N = 3SE +/- 0.04, N = 15SE +/- 0.05, N = 15SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 15SE +/- 0.04, N = 15SE +/- 0.08, N = 15SE +/- 0.02, N = 3SE +/- 0.05, N = 15SE +/- 0.05, N = 722.581.841.862.342.601.731.571.471.601.421.321.361.461.331.401.551.361.441.321.391.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3HD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 1660816243240SE +/- 0.12, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.93, N = 3SE +/- 0.12, N = 4SE +/- 0.12, N = 14SE +/- 0.12, N = 4SE +/- 0.11, N = 3SE +/- 0.09, N = 4SE +/- 0.04, N = 15SE +/- 0.11, N = 3SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 15SE +/- 0.05, N = 15SE +/- 0.06, N = 15SE +/- 0.02, N = 3SE +/- 0.03, N = 15SE +/- 0.06, N = 735.273.113.134.654.132.962.292.252.421.791.931.751.831.981.882.321.731.761.701.622.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2HD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 1660714212835SE +/- 0.28, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.36, N = 3SE +/- 0.01, N = 4SE +/- 0.07, N = 14SE +/- 0.00, N = 4SE +/- 0.16, N = 3SE +/- 0.02, N = 4SE +/- 0.04, N = 15SE +/- 0.04, N = 3SE +/- 0.03, N = 15SE +/- 0.04, N = 15SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 15SE +/- 0.04, N = 15SE +/- 0.06, N = 15SE +/- 0.02, N = 3SE +/- 0.05, N = 15SE +/- 0.06, N = 731.862.152.182.952.842.051.942.231.971.541.451.441.611.481.601.851.441.491.451.481.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenetHD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 166020406080100SE +/- 0.19, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 4SE +/- 0.01, N = 14SE +/- 0.02, N = 4SE +/- 0.03, N = 3SE +/- 0.08, N = 4SE +/- 0.05, N = 15SE +/- 0.10, N = 3SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.12, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 15SE +/- 0.03, N = 14SE +/- 0.04, N = 15SE +/- 0.03, N = 3SE +/- 0.05, N = 15SE +/- 0.01, N = 7102.886.546.606.319.026.586.295.265.994.904.624.655.135.095.425.474.534.654.834.455.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenetHD Graphics 5500 Broadwell GT2RX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 166020406080100SE +/- 0.16, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 4SE +/- 0.03, N = 14SE +/- 0.09, N = 4SE +/- 0.02, N = 3SE +/- 0.11, N = 4SE +/- 0.05, N = 15SE +/- 0.05, N = 3SE +/- 0.05, N = 15SE +/- 0.17, N = 15SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.21, N = 15SE +/- 0.05, N = 15SE +/- 0.04, N = 15SE +/- 0.07, N = 3SE +/- 0.03, N = 15SE +/- 0.06, N = 7102.333.583.584.895.033.366.835.837.774.724.604.335.245.205.806.524.014.284.674.305.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

RealSR-NCNN

Scale: 4x - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoRX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 1660HD Graphics 5500 Broadwell GT2714212835SE +/- 0.024, N = 4SE +/- 0.035, N = 5SE +/- 0.021, N = 5SE +/- 0.018, N = 6SE +/- 0.020, N = 5SE +/- 0.039, N = 3SE +/- 0.068, N = 3SE +/- 0.020, N = 3SE +/- 0.021, N = 4SE +/- 0.039, N = 4SE +/- 0.034, N = 5SE +/- 0.030, N = 3SE +/- 0.010, N = 3SE +/- 0.050, N = 3SE +/- 0.035, N = 4SE +/- 0.020, N = 6SE +/- 0.038, N = 5SE +/- 0.039, N = 4SE +/- 0.041, N = 5SE +/- 0.045, N = 3SE +/- 0.278, N = 312.0799.35810.2547.1778.98229.37217.21420.54313.40012.12910.61517.15017.53825.65815.3748.26010.06112.0079.46319.89317.752

GPU Temperature Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringRX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 16601632486480Min: 44 / Avg: 57.67 / Max: 66Min: 38 / Avg: 52.05 / Max: 67Min: 29 / Avg: 51.18 / Max: 65Min: 29 / Avg: 44.95 / Max: 66Min: 35 / Avg: 52.14 / Max: 74Min: 31 / Avg: 56.9 / Max: 66Min: 29 / Avg: 62.17 / Max: 79Min: 27 / Avg: 55.8 / Max: 69Min: 28 / Avg: 50.87 / Max: 70Min: 29 / Avg: 52.23 / Max: 71Min: 26 / Avg: 46.54 / Max: 68Min: 29 / Avg: 52.99 / Max: 69Min: 33 / Avg: 59.37 / Max: 70Min: 30 / Avg: 55.56 / Max: 66Min: 29 / Avg: 60.05 / Max: 78Min: 32 / Avg: 49.95 / Max: 71Min: 29 / Avg: 58.81 / Max: 82Min: 29 / Avg: 54.07 / Max: 74Min: 28 / Avg: 48.45 / Max: 72Min: 29 / Avg: 60.56 / Max: 79

GPU Power Consumption Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringRX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 166050100150200250Min: 22 / Avg: 98.3 / Max: 171Min: 31 / Avg: 89.52 / Max: 165Min: 11 / Avg: 96.87 / Max: 167Min: 21 / Avg: 104.49 / Max: 267Min: 29 / Avg: 88.95 / Max: 225Min: 5.43 / Avg: 53.96 / Max: 68.86Min: 6.57 / Avg: 115.01 / Max: 188.22Min: 5.95 / Avg: 86 / Max: 131.08Min: 9.49 / Avg: 91.04 / Max: 164.41Min: 10.34 / Avg: 108.02 / Max: 179.76Min: 14.42 / Avg: 107.67 / Max: 220.78Min: 7.41 / Avg: 78.56 / Max: 133.19Min: 10.75 / Avg: 90.37 / Max: 129.22Min: 6.51 / Avg: 71.29 / Max: 96.43Min: 6.75 / Avg: 92.52 / Max: 162.74Min: 7.79 / Avg: 115.51 / Max: 274.43Min: 13.31 / Avg: 108.43 / Max: 221.85Min: 7.53 / Avg: 105.98 / Max: 181.01Min: 8.89 / Avg: 110.83 / Max: 255.3Min: 6.69 / Avg: 72.09 / Max: 109.23

RealSR-NCNN

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterRealSR-NCNN 20200818GPU Temperature MonitorRX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 16601428425670Min: 51 / Avg: 57.75 / Max: 63Min: 52 / Avg: 57.79 / Max: 63Min: 49 / Avg: 54.75 / Max: 59Min: 48 / Avg: 53.03 / Max: 58Min: 57 / Avg: 62.43 / Max: 68Min: 50 / Avg: 59.36 / Max: 62Min: 65 / Avg: 69.26 / Max: 72Min: 54 / Avg: 60.61 / Max: 64Min: 52 / Avg: 60.15 / Max: 65Min: 53 / Avg: 60.46 / Max: 65Min: 53 / Avg: 58.67 / Max: 63Min: 48 / Avg: 58.39 / Max: 64Min: 46 / Avg: 59.14 / Max: 65Min: 55 / Avg: 60.68 / Max: 63Min: 65 / Avg: 68.84 / Max: 71Min: 57 / Avg: 61.2 / Max: 66Min: 64 / Avg: 68.73 / Max: 73Min: 57 / Avg: 62.21 / Max: 66Min: 56 / Avg: 61.59 / Max: 66Min: 59 / Avg: 67.45 / Max: 72

RealSR-NCNN

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterRealSR-NCNN 20200818GPU Power Consumption MonitorRX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 166050100150200250Min: 22 / Avg: 89.3 / Max: 156Min: 31 / Avg: 92.51 / Max: 165Min: 11 / Avg: 97.73 / Max: 167Min: 21 / Avg: 114.21 / Max: 262Min: 32 / Avg: 109.14 / Max: 212Min: 6.5 / Avg: 55.46 / Max: 68.27Min: 9.76 / Avg: 120.6 / Max: 186.3Min: 7.31 / Avg: 91.17 / Max: 124.12Min: 9.95 / Avg: 106.24 / Max: 163.21Min: 10.8 / Avg: 116.43 / Max: 178.77Min: 15.5 / Avg: 128.75 / Max: 219.45Min: 8.15 / Avg: 90.4 / Max: 132.9Min: 12.58 / Avg: 94.43 / Max: 127.87Min: 7 / Avg: 72.64 / Max: 95.3Min: 10.43 / Avg: 107.9 / Max: 153.11Min: 10.28 / Avg: 138.39 / Max: 267.04Min: 18.23 / Avg: 129.31 / Max: 221.85Min: 10.76 / Avg: 115.01 / Max: 178.57Min: 10.06 / Avg: 141.36 / Max: 255.21Min: 7.2 / Avg: 77.74 / Max: 106.6

RealSR-NCNN

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterRealSR-NCNN 20200818GPU Temperature MonitorRX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 16601632486480Min: 45 / Avg: 61.02 / Max: 66Min: 40 / Avg: 59.96 / Max: 67Min: 37 / Avg: 60.4 / Max: 65Min: 32 / Avg: 56.43 / Max: 66Min: 42 / Avg: 65.79 / Max: 74Min: 34 / Avg: 62.36 / Max: 66Min: 37 / Avg: 70.82 / Max: 79Min: 32 / Avg: 63.49 / Max: 69Min: 34 / Avg: 63.16 / Max: 70Min: 31 / Avg: 61.48 / Max: 71Min: 32 / Avg: 58.46 / Max: 68Min: 35 / Avg: 63.96 / Max: 69Min: 41 / Avg: 66.66 / Max: 70Min: 34 / Avg: 60.94 / Max: 66Min: 41 / Avg: 70.65 / Max: 78Min: 38 / Avg: 60.3 / Max: 71Min: 43 / Avg: 73.55 / Max: 82Min: 33 / Avg: 63.99 / Max: 74Min: 34 / Avg: 61.48 / Max: 72Min: 37 / Avg: 71.23 / Max: 79

RealSR-NCNN

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterRealSR-NCNN 20200818GPU Power Consumption MonitorRX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 166050100150200250Min: 22 / Avg: 124.95 / Max: 171Min: 31 / Avg: 136.68 / Max: 165Min: 12 / Avg: 150.39 / Max: 167Min: 21 / Avg: 208.15 / Max: 267Min: 32 / Avg: 159.84 / Max: 225Min: 5.59 / Avg: 64.99 / Max: 68.86Min: 7.24 / Avg: 152.95 / Max: 188.22Min: 6.15 / Avg: 112.02 / Max: 131.08Min: 9.49 / Avg: 148.27 / Max: 164.41Min: 10.5 / Avg: 162.04 / Max: 179.76Min: 14.42 / Avg: 196.82 / Max: 220.78Min: 7.82 / Avg: 122.28 / Max: 133.19Min: 11.09 / Avg: 119.27 / Max: 129.22Min: 6.74 / Avg: 88 / Max: 96.43Min: 8.06 / Avg: 139.07 / Max: 162.74Min: 8.53 / Avg: 226.48 / Max: 274.43Min: 14.09 / Avg: 197.01 / Max: 220.77Min: 7.96 / Avg: 160.99 / Max: 181.01Min: 9.25 / Avg: 219.85 / Max: 255.3Min: 6.81 / Avg: 99.98 / Max: 109.23

NCNN

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNCNN 20200916GPU Temperature MonitorRX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 16601224364860Min: 45 / Avg: 49.92 / Max: 54Min: 38 / Avg: 41.97 / Max: 44Min: 29 / Avg: 40.31 / Max: 46Min: 29 / Avg: 35.12 / Max: 39Min: 35 / Avg: 45.08 / Max: 50Min: 31 / Avg: 41.54 / Max: 49Min: 29 / Avg: 38.57 / Max: 48Min: 27 / Avg: 38.51 / Max: 46Min: 28 / Avg: 41.98 / Max: 50Min: 29 / Avg: 36.86 / Max: 43Min: 26 / Avg: 38.38 / Max: 45Min: 29 / Avg: 44.32 / Max: 52Min: 33 / Avg: 47.22 / Max: 58Min: 30 / Avg: 35.87 / Max: 41Min: 29 / Avg: 51.63 / Max: 61Min: 32 / Avg: 43.67 / Max: 50Min: 29 / Avg: 49.32 / Max: 61Min: 29 / Avg: 36.15 / Max: 43Min: 28 / Avg: 40.39 / Max: 47Min: 29 / Avg: 41.23 / Max: 50

NCNN

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNCNN 20200916GPU Power Consumption MonitorRX 5600 XTRX 5700RX Vega 56Radeon VIIRX 5700 XTGTX 1650GTX 1080GTX 1060RTX 2060RTX 2060 SUPERRTX 2070 SUPERGTX 1660 TiGTX 1660 SUPERGTX 1650 SUPERGTX 1070RTX 2080 TiRTX 2080RTX 2070RTX 2080 SUPERGTX 16604080120160200Min: 22 / Avg: 50.03 / Max: 95Min: 31 / Avg: 54.05 / Max: 117Min: 12 / Avg: 73.93 / Max: 164Min: 21 / Avg: 56.3 / Max: 178Min: 29 / Avg: 64.95 / Max: 172Min: 5.43 / Avg: 36.97 / Max: 58.71Min: 6.66 / Avg: 67.08 / Max: 127.61Min: 5.95 / Avg: 52.99 / Max: 89.44Min: 9.5 / Avg: 66.76 / Max: 125.56Min: 10.49 / Avg: 67.01 / Max: 138.49Min: 14.5 / Avg: 76.37 / Max: 153.13Min: 7.41 / Avg: 52.59 / Max: 95.92Min: 10.79 / Avg: 58.28 / Max: 103.39Min: 6.69 / Avg: 41.85 / Max: 70.35Min: 6.75 / Avg: 72.5 / Max: 121.46Min: 8.14 / Avg: 92.05 / Max: 219.12Min: 13.31 / Avg: 80.01 / Max: 161.84Min: 7.53 / Avg: 63.22 / Max: 132.69Min: 8.89 / Avg: 75.86 / Max: 159.23Min: 6.75 / Avg: 41.49 / Max: 72.99

Phoronix Test Suite v10.8.4