[clang] [llvm] [llvm][AMDGPU] Fold `llvm.amdgcn.wavefrontsize` early (PR #114481)

[Alex Voicu via cfe-commits]

================
@@ -1024,6 +1024,15 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
     }
     break;
   }
+  case Intrinsic::amdgcn_wavefrontsize: {
+    // TODO: this is a workaround for the pseudo-generic target one gets with no
+    // specified mcpu, which spoofs its wave size to 64; it should be removed.
----------------
AlexVlx wrote:

I don't think that this interpretation is actually correct, if you rely on lockstep of a full wave and you optimise around wavesize this will break in bad ways on wave32. The current `generic` is not particularly god, but we have to live with it for now I guess.

https://github.com/llvm/llvm-project/pull/114481