[PATCH] D35146: AMDGPU : Widen extending scalar loads to 32-bits

[Wei Ding via Phabricator via llvm-commits]

wdng added inline comments.


================
Comment at: lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp:452
+  if (I.getPointerAddressSpace() == AMDGPUASI.CONSTANT_ADDRESS &&
+      !I.isVolatile() && (!VT || (VT && VT->getBitWidth() < 32)) &&
+      needsPromotionToI32(I.getType()) && DA->isUniform(&I)) {
----------------
arsenm wrote:
> This should be able to handle vectors. This should also use the DataLayout so it works for pointers
This one (VT && VT->getBitWidth() < 32) is able to handle vectors with bitwidth < 32 or scalar (!VT). Are you saying to use DataLayout to handle the pointer dereferenceable issue?


Repository:
  rL LLVM

https://reviews.llvm.org/D35146