[PATCH] D156104: [AMDGPU] Switch to using real True16 operands.

[Ivan Kosarev via Phabricator via llvm-commits]

kosarev created this revision.
kosarev added reviewers: arsenm, rampitec, Joe_Nash, foad.
Herald added subscribers: StephenFan, kerbowa, hiraditya, tpr, dstuttard, yaxunl, jvesely, kzhuravl.
Herald added a project: All.
kosarev requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

The DPP source operands remain unchanged for now.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D156104

Files:
  llvm/lib/Target/AMDGPU/SIInstrInfo.td
  llvm/lib/Target/AMDGPU/SIInstructions.td
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fcanonicalize.mir
  llvm/test/CodeGen/AMDGPU/true16-ra-f128-fail.mir
  llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop2.txt
  llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop2_dpp16.txt
  llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop2_dpp8.txt
  llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16_from_vop2.txt
  llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8_from_vop2.txt
  llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_from_vop2.txt

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D156104.543468.patch
Type: text/x-patch
Size: 163616 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230724/ba0a37f3/attachment.bin>