[all-commits] [llvm/llvm-project] 9f40d9: [AMDGPU][MC][GFX11] Correct encoding of neg modifi...

[dpreobra via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 9f40d9ffd18685f1605869efb358f4532112c295
      https://github.com/llvm/llvm-project/commit/9f40d9ffd18685f1605869efb358f4532112c295
  Author: Dmitry Preobrazhensky <dmitri.preobrazhenski at gmail.com>
  Date:   2022-12-30 (Fri, 30 Dec 2022)

  Changed paths:
    M llvm/lib/Target/AMDGPU/VOP3PInstructions.td
    M llvm/test/MC/AMDGPU/gfx11_asm_vop3p.s
    M llvm/test/MC/AMDGPU/gfx11_asm_vop3p_features.s
    M llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3p.txt

  Log Message:
  -----------
  [AMDGPU][MC][GFX11] Correct encoding of neg modifier for v_dot2_f32_bf16

Fix a bug with neg_lo:[0,1,0] and neg_hi:[0,1,0] modifiers - they are accepted but not encoded.

Differential Revision: https://reviews.llvm.org/D140470