[PATCH] D75287: [mlir][GPU] Expose the functionality to create a gpu.GPUFuncOp from a gpu.GPULaunchOp
Mahesh Ravishankar via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Wed Mar 4 22:58:24 PST 2020
mravishankar added inline comments.
================
Comment at: mlir/lib/Dialect/GPU/Transforms/KernelOutlining.cpp:236
+ return WalkResult::interrupt();
+ }
+ gpu::GPUFuncOp outlinedFunc =
----------------
mehdi_amini wrote:
> mravishankar wrote:
> > mehdi_amini wrote:
> > > Note: this is still not decoupled from this pass right now (i.e. not tested in isolation, etc.): we still have "outlining" and "sinking" part of the same pass, can't they be separated?
> > They are separate functions. I have no visibility into the clients of the pass. So if any user of the pass is relying on sinking happening then removing the sinking would "potentially" break. One could argue that then it is incorrect usage since the gpu.launch_func op gets updated accordingly, but at this point I would rather keep this change as an NFC.
> Keeping it NFC is a very good point!
>
> (what would break here is an optimization and not correctness right? So we can still do it in the absolute?)
Yes, it would indeed be an optimization thing and not a correctness thing.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D75287/new/
https://reviews.llvm.org/D75287
More information about the llvm-commits
mailing list