[PATCH] D152706: [AMDGPU] Use SSAUpdater in PromoteAlloca
Matt Arsenault via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Tue Jul 11 05:21:47 PDT 2023
arsenm added inline comments.
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp:391
+ // (e.g. load <8 x i8> as ptr), we first need to cast to int.
+ if (Inst->getType()->isPointerTy()) {
+ CurVal =
----------------
Doesn't consider vector of pointers
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp:426
+ if (SrcTy->isPointerTy()) {
+ Val = Builder.CreateBitOrPointerCast(
+ Val, Builder.getIntNTy(VecStoreSize * 8));
----------------
Specifically use PtrToInt?
================
Comment at: llvm/test/CodeGen/AMDGPU/promote-alloca-loadstores.ll:89
+ ret ptr %tmp
+}
----------------
Add some load/store vector of pointer cases. Also mix different pointer sizes
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D152706/new/
https://reviews.llvm.org/D152706
More information about the llvm-commits
mailing list