Improve use of unified memory about metal.jl HOT 8 CLOSED

CUDA.jl has recently seen a bunch of unified memory-related improvements, https://info.juliahub.com/cuda-jl-5-1-unified-memory, we should probably backport a bunch of those here (e.g. the ability to conveniently unsafe_wrap a Julia Array to MtlArray, if possible).

from metal.jl.

tracked also here: #62

from metal.jl.

Hi -- this looks to be done already:

If this seems correct, lmk and I will add documentation for others (and our future-selves.)

from metal.jl.

Ah right, that's where it's set. That doesn't seem great, as per Apple we should be using private storage.

from metal.jl.

I agree with that. I will try changing the default and updating the unifiedmemory example (and the gtk example)

from metal.jl.

Just wanted to add that I stumbled across this issue when using Metal.jl through KernelAbstractions; I wanted to do some experiments with shared arrays but quickly found that the default allocator allocates arrays in private storage mode. I ended up just adding some defaults to the allocator (jvkersch@08ea259), but as I'm neither a Julia or GPU programmer this is probably not the right approach. Still interested in seeing how this issue evolves, however!

from metal.jl.

fixed by #305

from metal.jl.

There's still a couple of important improvements to make, e.g. the ability to cheaply wrap Arrays with an MtlArray and vice-versa. That should make it much easier to use Metal.jl in an existing application.

from metal.jl.