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

[Neil Henning via Phabricator via llvm-commits]

sheredom marked 2 inline comments as done.
sheredom 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:
> > 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
> https://reviews.llvm.org/D59536
I've submitted that other change, so this should be good to go once I get a sign off!


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

https://reviews.llvm.org/D59295