]> granicus.if.org Git - llvm/commit
AMDGPU/SI: Support data types other than V4f32 in image intrinsics
authorChangpeng Fang <changpeng.fang@gmail.com>
Mon, 14 Nov 2016 18:33:18 +0000 (18:33 +0000)
committerChangpeng Fang <changpeng.fang@gmail.com>
Mon, 14 Nov 2016 18:33:18 +0000 (18:33 +0000)
commitaf761456000bd5061a70daf4885c1e2cf3da07bc
tree845ae9e4e4db9642140331419a0cc76055a58072
parentb0a9b661224c1ba8f00a8569245daabcccac1eea
AMDGPU/SI: Support data types other than V4f32 in image intrinsics

Summary:
  Extend image intrinsics to support data types of V1F32 and V2F32.

  TODO: we should define a mapping table to change the opcode for data type of V2F32 but just one channel is active,
  even though such case should be very rare.

Reviewers:
  tstellarAMD

Differential Revision:
  http://reviews.llvm.org/D26472

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@286860 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AMDGPU/MIMGInstructions.td
lib/Target/AMDGPU/SIISelLowering.cpp
test/CodeGen/AMDGPU/llvm.amdgcn.image.gather4.ll
test/CodeGen/AMDGPU/llvm.amdgcn.image.ll
test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.ll