[PATCH] D117710: AMDGPU/GlobalISel: Mostly fix BFI patterns

[Matt Arsenault via Phabricator via llvm-commits]

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

Most importantly, fixes constant bus errors in the 64-bit cases. It's
surprising to me these were even passing the selection test using
SReg_* sources. Also fixes pattern matching in the 32-bit cases, with
simple operands.

      

These patterns aren't working in a few cases, like with mixed SGPR
inputs. The patterns aren't looking through the SGPR->VGPR copies like
they need to. The vector cases also have some unmerges of build_vector
which are obscuring the inputs.


https://reviews.llvm.org/D117710

Files:
  llvm/lib/Target/AMDGPU/SIInstructions.td
  llvm/test/CodeGen/AMDGPU/bfi_int.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D117710.401360.patch
Type: text/x-patch
Size: 45727 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220119/16f434e1/attachment-0001.bin>