[all-commits] [llvm/llvm-project] bbfbec: [AMDGPU] Enable OMod on more VOP3 instructions

[Joe Nash via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: bbfbec94b10699d473c106d85d5a48ff5d69e721
      https://github.com/llvm/llvm-project/commit/bbfbec94b10699d473c106d85d5a48ff5d69e721
  Author: Joe Nash <Joseph.Nash at amd.com>
  Date:   2022-12-07 (Wed, 07 Dec 2022)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
    M llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    M llvm/lib/Target/AMDGPU/SIInstrInfo.td
    M llvm/lib/Target/AMDGPU/VOP2Instructions.td
    M llvm/lib/Target/AMDGPU/VOP3Instructions.td
    M llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-amdgcn.fmed3.s16.mir
    M llvm/test/CodeGen/AMDGPU/commute-vop3.mir
    M llvm/test/CodeGen/AMDGPU/fmul-2-combine-multi-use.ll
    M llvm/test/CodeGen/AMDGPU/gfx11-twoaddr-fma.mir
    M llvm/test/CodeGen/AMDGPU/omod.ll
    M llvm/test/CodeGen/AMDGPU/shrink-mad-fma.mir
    M llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
    M llvm/test/MC/AMDGPU/gfx9_asm_vop3_e64.s
    M llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
    M llvm/test/MC/Disassembler/AMDGPU/gfx9_vop3.txt

  Log Message:
  -----------
  [AMDGPU] Enable OMod on more VOP3 instructions

OMod was disabled if OpSel was enabled, but that restriction is more
specific than necessary. Any VOP3 with float operands can use OMod.

On GFX11, FMAC_F16_e64 can use op_sel.
Previously, SIFoldOperands and convertToThreeAddress were accidentally correct when
they reinterpreted the zero OMod operand on V_FMAC_F16_e64 as the OpSel operand on
V_FMA_F16_gfx9_e64. Now we explicitly add op_sel if required.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D139469