JuliaGPU / JuliaGPU/KernelAbstractions.jl
API for # of cores/multiprocessors
Nobody has claimed this yet.
- Dominant language
- Julia
- Stars
- 523
- Forks
- 88
- Avg merge
- 1d 11h
- Merged PRs (30d)
- 25
Description
This may not be the best way to approach this, but to improve the heuristic deciding whether to reduce with blocks or with threads I'm thinking there should be a way to expose the number of cores.
See https://github.com/JuliaGPU/CUDA.jl/blob/e561e7a106684f8e4be59cad98a51cc304c671d2/src/mapreduce.jl#L163-L167 and https://github.com/JuliaGPU/Metal.jl/pull/626
I guess we would also need a way to access the max threads per block/group. Maybe we expose an API specifically for reductions that is essentially an interface for what CUDA has defined in big_mapreduce_threshold?
@vchuravy @maleadt @anicusan
Should probably update https://discourse.julialang.org/t/how-to-get-the-device-name-and-the-number-of-compute-units-when-using-oneapi-jl-or-amdgpu-jl/128361 once resolved
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked CUDA.jl mapreduce.jl section around lines 163-167 and comparing the approach with Metal.jl pull request #626. Clarify the desired API for core counts and maximum threads per block or group, including whether it should be reduction-specific. Once resolved, update the linked Julia Discourse discussion.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- julia
- Domain
- backend-api-design, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100