[PATCH] D157133: [AMDGPU] Extend CalculateByteProvider to capture vectors and signed

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:10440
 
+  case ISD::ANY_EXTEND:
+  case ISD::SIGN_EXTEND:
----------------
handling any_extend here seems dangerous, can you do that in a separate patch? It might be correct but I'd rather keep it separate


================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:10452
+      return std::nullopt;
+    uint64_t NarrowByteWidth = NarrowVT.getSizeInBits() / 8;
+
----------------
getStoreSize


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D157133/new/

https://reviews.llvm.org/D157133