Vulkan Compute

Intel Core i7-2600K testing with a Gigabyte P67A-UD7-B3 (F7 BIOS) and eVGA NVIDIA GeForce RTX 3060 12GB on Gentoo 2.7 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2111059-HA-2111054TJ65&sor.

Vulkan ComputeProcessorMotherboardMemoryDiskGraphicsAudioMonitorChipsetNetworkOSKernelDisplay DriverOpenCLFile-SystemScreen ResolutionDesktopDisplay ServerOpenGLVulkanCompilerRX 480 4GBRTX 3060RTX 3060 LinuxIntel Core i7-2600K (8 Cores)Gigabyte P67A-UD7-B3 (F7 BIOS)0 x 4096 MB224GB INTEL SSDSC2CW240A3 + 1863GB WDC WD20EARX-008FB0AMD Radeon RX 480Realtek HD Audio + AMD HD Audio DeviceS7A950DMicrosoft Windows 7 Professional Build 76016.1 (x86_64)27.20.14501.18003OpenCL 2.1 AMD-APP (3188.4)NTFS1920x1080NVIDIA GeForce RTX 3060 12GBNVIDIA HD Audio + Realtek HD Audio472.12 (30.0.14.7212)OpenCL 3.0 CUDA 11.4.136 + OpenCL 2.1 AMD-APP (3188.4)Intel Core i7-2600K @ 3.80GHz (4 Cores / 8 Threads)Intel 2nd Generation Core DRAM16GB240GB INTEL SSDSC2CW24 + 2000GB Western Digital WD20EARX-008eVGA NVIDIA GeForce RTX 3060 12GB (1882/7500MHz)Realtek ALC889S27A950D2 x Realtek RTL8111/8168/8411Gentoo 2.75.14.15-gentoo (x86_64)Xfce 4.16X Server 1.20.6NVIDIA 470.63.014.6.01.2.175GCC 11.2.0 + Clang 12.0.1 + LLVM 12.0.1ext4OpenBenchmarking.orgEnvironment Details- RX 480 4GB, RTX 3060: windows_tracing_flags=3Security Details- RX 480 4GB: __user pointer sanitization: Disabled- RTX 3060: __user pointer sanitization: Disabled + KPTI Enabled: Yes + PTE Inversion: Yes- RTX 3060 Linux: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Vulnerable: Clear buffers attempted no microcode; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected Compiler Details- RTX 3060 Linux: --bindir=/usr/x86_64-pc-linux-gnu/gcc-bin/11.2.0 --build=x86_64-pc-linux-gnu --datadir=/usr/share/gcc-data/x86_64-pc-linux-gnu/11.2.0 --disable-esp --disable-fixed-point --disable-libada --disable-libssp --disable-libunwind-exceptions --disable-libvtv --disable-systemtap --disable-valgrind-annotations --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-languages=c,c++,fortran --enable-libgomp --enable-libstdcxx-time --enable-lto --enable-multilib --enable-nls --enable-obsolete --enable-secureplt --enable-shared --enable-targets=all --enable-threads=posix --host=x86_64-pc-linux-gnu --includedir=/usr/lib/gcc/x86_64-pc-linux-gnu/11.2.0/include --mandir=/usr/share/gcc-data/x86_64-pc-linux-gnu/11.2.0/man --with-multilib-list=m32,m64 --with-python-dir=/share/gcc-data/x86_64-pc-linux-gnu/11.2.0/python --without-isl --without-zstd Processor Details- RTX 3060 Linux: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x25Graphics Details- RTX 3060 Linux: GLAMOR

Vulkan Computevkpeak: fp32-scalarvkpeak: fp32-vec4vkpeak: fp64-scalarvkpeak: fp64-vec4vkpeak: int32-scalarvkpeak: int32-vec4realsr-ncnn: 4x - Norealsr-ncnn: 4x - Yeswaifu2x-ncnn: 2x - 3 - Nowaifu2x-ncnn: 2x - 3 - Yesvkfft: vkresample: 2x - Doublevkresample: 2x - Singlevkpeak: fp16-scalarvkpeak: fp16-vec4vkpeak: int16-scalarvkpeak: int16-vec4RX 480 4GBRTX 3060RTX 3060 Linux5621.785522.92372.65372.671192.331192.4825.359185.0792.07911.3526977.639262.87219.08218.166988.836978.9211.74270.3302.2185.6582779247.08127.1867004.1813614.374628.096162.137024.459320.50220.53217.957009.776981.6611.63968.8525.42123701354.86722.9547051.7413697.944636.486165.04OpenBenchmarking.org

vkpeak

fp32-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-scalarRTX 3060 LinuxRTX 3060RX 480 4GB15003000450060007500SE +/- 0.06, N = 3SE +/- 20.38, N = 3SE +/- 10.76, N = 37024.456977.635621.78

vkpeak

fp32-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp32-vec4RTX 3060 LinuxRTX 3060RX 480 4GB2K4K6K8K10KSE +/- 0.22, N = 3SE +/- 27.73, N = 3SE +/- 6.80, N = 39320.509262.875522.92

vkpeak

fp64-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-scalarRX 480 4GBRTX 3060 LinuxRTX 306080160240320400SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.69, N = 3372.65220.53219.08

vkpeak

fp64-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp64-vec4RX 480 4GBRTX 3060RTX 3060 Linux80160240320400SE +/- 0.00, N = 2SE +/- 0.18, N = 3SE +/- 0.01, N = 3372.67218.16217.95

vkpeak

int32-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-scalarRTX 3060 LinuxRTX 3060RX 480 4GB15003000450060007500SE +/- 2.65, N = 3SE +/- 19.64, N = 3SE +/- 0.01, N = 37009.776988.831192.33

vkpeak

int32-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int32-vec4RTX 3060 LinuxRTX 3060RX 480 4GB15003000450060007500SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 36981.666978.921192.48

RealSR-NCNN

Scale: 4x - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoRTX 3060 LinuxRTX 3060RX 480 4GB612182430SE +/- 0.01, N = 3SE +/- 0.09, N = 12SE +/- 0.23, N = 711.6411.7425.36

RealSR-NCNN

Scale: 4x - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRTX 3060 LinuxRTX 3060RX 480 4GB4080120160200SE +/- 0.15, N = 3SE +/- 0.06, N = 3SE +/- 0.21, N = 368.8570.33185.08

Waifu2x-NCNN Vulkan

Scale: 2x - Denoise: 3 - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: NoRX 480 4GBRTX 30600.49910.99821.49731.99642.4955SE +/- 0.054, N = 15SE +/- 0.051, N = 152.0792.218

Waifu2x-NCNN Vulkan

Scale: 2x - Denoise: 3 - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesRTX 3060 LinuxRTX 3060RX 480 4GB3691215SE +/- 0.003, N = 3SE +/- 0.060, N = 3SE +/- 0.051, N = 35.4215.65811.352

VkFFT

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.1.1RTX 3060RTX 3060 Linux6K12K18K24K30KSE +/- 297.81, N = 4SE +/- 187.69, N = 327792237011. (CXX) g++ options: -O3 -pthread

VkResample

Upscale: 2x - Precision: Double

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: DoubleRTX 3060RTX 3060 Linux80160240320400SE +/- 0.38, N = 15SE +/- 0.13, N = 347.08354.871. (CXX) g++ options: -O3 -pthread

VkResample

Upscale: 2x - Precision: Single

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleRTX 3060 LinuxRTX 3060612182430SE +/- 0.00, N = 3SE +/- 2.24, N = 1522.9527.191. (CXX) g++ options: -O3 -pthread

vkpeak

fp16-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-scalarRTX 3060 LinuxRTX 306015003000450060007500SE +/- 0.11, N = 3SE +/- 21.16, N = 37051.747004.18

vkpeak

fp16-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20210424fp16-vec4RTX 3060 LinuxRTX 30603K6K9K12K15KSE +/- 0.33, N = 3SE +/- 39.61, N = 313697.9413614.37

vkpeak

int16-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-scalarRTX 3060 LinuxRTX 306010002000300040005000SE +/- 0.06, N = 3SE +/- 3.82, N = 34636.484628.09

vkpeak

int16-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20210424int16-vec4RTX 3060 LinuxRTX 306013002600390052006500SE +/- 0.08, N = 3SE +/- 0.07, N = 36165.046162.13


Phoronix Test Suite v10.8.4