CUDA
We also support CUDA.jl.
Load
Before using a CuArray
simply invoke.
using CUDA
Our routines need as input array either only Array
s or CuArray
s. To get the deconvolution running, both the PSF and the measured array needs to be a CuArray
. See also our 3D example here.
Issues with Regularizers
However, our approach to express the regularizers with Tullio.jl is currently not performant with GPUs. Therefore, to use CuArray
s with regularizers, you need to choose TV_cuda
. Other regularizers are not yet supported since we hope that Tullio.jl will be one day mature enough to produce reasonable fast gradients for CUDA kernels as well.