[PATCH] D98549: [AMDGPU] Fix copyPhysReg to not produce unalined vgpr access

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec created this revision.
rampitec added a reviewer: arsenm.
Herald added subscribers: kerbowa, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl.
rampitec requested review of this revision.
Herald added a subscriber: wdng.
Herald added a project: LLVM.

RA can insert something like a sub1_sub2 COPY of a wide VGPR
tuple which results in the unaligned acces with v_pk_mov_b32
after the copy is expanded. This is regression after D97316 <https://reviews.llvm.org/D97316>.


https://reviews.llvm.org/D98549

Files:
  llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
  llvm/test/CodeGen/AMDGPU/copy_phys_vgpr64.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D98549.330356.patch
Type: text/x-patch
Size: 12956 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210312/0fd182a0/attachment.bin>