[PATCH] D145586: [AMDGPU] Tweak PromoteAlloca limits

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp:407
+  const unsigned SizeFactor = (MaxVGPRs >= 64 ? 2 : 4);
+  dbgs() << "SizeFactor: " << SizeFactor << ", MaxVGPRs: " << MaxVGPRs << "\n";
+  if (DL.getTypeSizeInBits(AllocaTy) * SizeFactor > Limit) {
----------------
Leftover debug print


================
Comment at: llvm/test/CodeGen/AMDGPU/vector-alloca-limits.ll:86
-; LIMIT32-NOT: <9 x i128>
-define amdgpu_kernel void @alloca_9xi128_max256(ptr addrspace(1) %out, i32 %index) #2 {
-entry:
----------------
I wouldn't expect deleting these cases


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D145586/new/

https://reviews.llvm.org/D145586