[PATCH] D15543: Use Flat For 64-bit Global Buffer

[Changpeng Fang via llvm-commits]

cfang updated this revision to Diff 43415.
cfang added a comment.

Change the way of initialization for FlatForGlobal to make -mattr=-flat-for-global work;
Fix LIT test failures due to generating flat instructions instead of buffer ones.


http://reviews.llvm.org/D15543

Files:
  lib/Target/AMDGPU/AMDGPU.td
  lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
  lib/Target/AMDGPU/AMDGPUSubtarget.cpp
  lib/Target/AMDGPU/AMDGPUSubtarget.h
  lib/Target/AMDGPU/CIInstructions.td
  lib/Target/AMDGPU/VIInstructions.td
  test/CodeGen/AMDGPU/ci-use-flat-for-global.ll
  test/CodeGen/AMDGPU/hsa.ll
  test/CodeGen/AMDGPU/large-alloca-compute.ll
  test/CodeGen/AMDGPU/llvm.dbg.value.ll
  test/CodeGen/AMDGPU/move-addr64-rsrc-dead-subreg-writes.ll
  test/CodeGen/AMDGPU/register-count-comments.ll
  test/CodeGen/AMDGPU/work-item-intrinsics.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D15543.43415.patch
Type: text/x-patch
Size: 19168 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20151222/f6f5e6a9/attachment.bin>