[PATCH] D59295: [AMDGPU] Pre-allocate WWM registers to reduce VGPR pressure.

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: include/llvm/IR/IntrinsicsAMDGPU.td:1363-1365
 def int_amdgcn_wwm : Intrinsic<[llvm_any_ty],
-  [LLVMMatchType<0>], [IntrNoMem, IntrSpeculatable]
+  [LLVMMatchType<0>], [IntrNoMem, IntrSpeculatable, IntrConvergent]
 >;
----------------
sheredom wrote:
> arsenm wrote:
> > This is a separate fix that can be split into its own patch
> So I tried to remove this (forgetting why I needed it) and LLVM will sink the WWM out of the branch which totally messes up the WWM calculation. So this is actually a requirement for the patch, not a separate thing.
You can commit that first then


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D59295/new/

https://reviews.llvm.org/D59295