[PATCH] D73893: [MLIR][GPU] Implement initial mapping from loop.parallel to gpu.launch.
Stephan Herhut via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Tue Feb 4 02:25:04 PST 2020
herhut added a comment.
In D73893#1854949 <https://reviews.llvm.org/D73893#1854949>, @nicolasvasilache wrote:
> 2. one of the problems you solve here is to go from type (the affine maps for mapping) to values (tidx, bidy, etc)). This is a recurrent transition that would be great to try and make retargetable (e.g. OpenMP or other runtimes), I would love to see this separated from GPU. This would also force separating concerns a bit more re outlining of kernel vs mapping of loops.
I use attributes here instead of baking the mapping into the lowering part to enable reuse. My idea was that we can have different implementations/strategies for mapping that inform a single code generation. I'd be happy to get to a shared "mapping language" that can be reused but it has to start somewhere.
> 3. Along the lines of point 2., I would have hoped to see `mapLoopToProcessorIds` be templatized and retargeted to this use case, is this possible as a followup?
There is no code at all yet to produce the mapping attributes. But map LoopToProcessorIds could be one producer indeed.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D73893/new/
https://reviews.llvm.org/D73893
More information about the llvm-commits
mailing list