[PATCH] D73880: AMDGPU/GlobalISel: Fix move s.buffer.load to VALU

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: nhaehnle, kerbowa.
Herald added subscribers: Petar.Avramovic, hiraditya, t-tye, tpr, dstuttard, rovka, yaxunl, wdng, jvesely, kzhuravl.
Herald added a project: LLVM.

We were executing this in a waterfall loop as a placeholder, but this
should really be converted to a MUBUF load. Also execute in a
waterfall loop if the resource isn't an SGPR. This is a case where the
DAG handling was wrong because doing the right thing was too hard.

     

Currently, this will mishandle 96-bit loads. There's currently no way
to track the original memory size with an MMO, so these loads will be
widened andd the resulting memory size will be 128-bits.


https://reviews.llvm.org/D73880

Files:
  llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
  llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.h
  llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn-s-buffer-load.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.s.buffer.load.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.s.buffer.load.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D73880.242035.patch
Type: text/x-patch
Size: 144523 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200203/2729cf41/attachment-0001.bin>