Valentin Churavy comments

Results 1415 comments of


                                            Valentin Churavy

Doc: what does CPU() do ?

You can use `@macroexpand` on the `@kernel` to see the code KA generates for the CPU.

Attempt at including offsets in kernel launch

Thanks for the initial implementation I will have to think about this a bit. I still feel like this may be better expressed as a projection `f(Idx) -> Idx`. ```...

Attempt at including offsets in kernel launch

@timholy might also be able to offer advise. IIUC you are trying to implement an exterior/interior iteration split like `EdgeIterator` from https://github.com/JuliaArrays/TiledIteration.jl?

Attempt at including offsets in kernel launch

You can do this right now as you would do with CUDA.jl/AMDGPU.jl by projecting a smaller ndrange to your custom index space. This is more about if we can do...

StackOverflow Error on get_backend(cu(rand(3)))

You need to be on https://github.com/JuliaGPU/CUDA.jl/pull/1772

StackOverflow Error on get_backend(cu(rand(3)))

AMDGPU support for KA 0.9 https://github.com/JuliaGPU/AMDGPU.jl/pull/398

Dynamic parallelism

Slightly confusing, so not expected. In my experience dynamic parallelism doesn't have the best performance and of course we will need to figure out what it means for at least...

exposing warp-level semantics

There currently is no support in KA for wavefront/warp level programming. Two immediate questions: 1. What would the semantics be on the CPU level? 2. Does Intel and Metal also...

exposing warp-level semantics

Coming back to my question: What's the reason you want to access this functionality? Generally speaking I don't think warpsize is something we should expose in KA, but there are...

exposing warp-level semantics

KernelAbstractions is not One API, so the meaning of subgroup needs to be defined clearly and independently. If often comes down to can we expose these semantics without to much...