[PATCH] D53750: [AMDGPU] support image load/store a16

Fri Oct 26 02:24:50 PDT 2018

sheredom created this revision.
sheredom added reviewers: rtaylor, nhaehnle, arsenm.
sheredom added a project: AMDGPU.
Herald added subscribers: llvm-commits, t-tye, tpr, dstuttard, yaxunl, wdng, jvesely, kzhuravl.

Our a16 support was only enabled for sample/gather and buffer load/store, but not for image load/store operations (which take an i16 as the pixel index rather than a half).

Fix our isel lowering and add test cases to prove it out.

Repository:
  rL LLVM

https://reviews.llvm.org/D53750

Files:
  lib/Target/AMDGPU/SIISelLowering.cpp
  test/CodeGen/AMDGPU/llvm.amdgcn.image.load.a16.d16.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.image.load.a16.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.image.store.a16.d16.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.image.store.a16.ll
  test/MC/AMDGPU/mimg.s

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D53750.171272.patch
Type: text/x-patch
Size: 32692 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20181026/f7aa749f/attachment.bin>