[PATCH] D21326: AMDGPU: Fix MUBUF offset bugs affecting llvm.amdgcn.buffer.* intrinsics

[Nicolai Hähnle via llvm-commits]

nhaehnle created this revision.
nhaehnle added reviewers: arsenm, tstellarAMD.
nhaehnle added a subscriber: llvm-commits.
Herald added subscribers: kzhuravl, arsenm.

This fixes two related bugs. First, the generic optimization passes
unfortunately generate negative constant offsets but the hardware treats
SOffset as an unsigned value.

Second, there is a hardware bug on SI and CI, where address clamping in MUBUF
instructions does not work correctly when SOffset is larger than the buffer
size. This patch works around this bug by never using SOffset.

An alternative workaround would be to do the clamping manually when SOffset
is too large, but generating the required code sequence during instruction
selection would be rather involved, and in any case the resulting code would
probably be worse.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=96360

http://reviews.llvm.org/D21326

Files:
  lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
  test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.buffer.load.format.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.buffer.load.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D21326.60684.patch
Type: text/x-patch
Size: 10483 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160614/f491d46e/attachment.bin>