Open ArnoStrouwen opened 2 years ago
The documentation says CuArray u0 are supported. But only one dimensional arrays are supported because of lines like: https://github.com/SciML/DiffEqGPU.jl/blob/8489a3e74f9179aafddb38912bedd9321fadd68b/src/DiffEqGPU.jl#L345
CuArray
u0
To generalize this to N dimensions the u0 should concatenate across an additional dimension. And the kernels should then index over this last dimension, instead of assuming there are only 2: https://github.com/SciML/DiffEqGPU.jl/blob/8489a3e74f9179aafddb38912bedd9321fadd68b/src/DiffEqGPU.jl#L24
The documentation says
CuArray
u0
are supported. But only one dimensional arrays are supported because of lines like: https://github.com/SciML/DiffEqGPU.jl/blob/8489a3e74f9179aafddb38912bedd9321fadd68b/src/DiffEqGPU.jl#L345To generalize this to N dimensions the
u0
should concatenate across an additional dimension. And the kernels should then index over this last dimension, instead of assuming there are only 2: https://github.com/SciML/DiffEqGPU.jl/blob/8489a3e74f9179aafddb38912bedd9321fadd68b/src/DiffEqGPU.jl#L24