[all-commits] [llvm/llvm-project] 084f1c: [AMDGPU][True16] Support V_CEIL_F16. (#73108)

[Ivan Kosarev via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 084f1c2ee074a5ac8186ea4b5b181b48bf4621b6
      https://github.com/llvm/llvm-project/commit/084f1c2ee074a5ac8186ea4b5b181b48bf4621b6
  Author: Ivan Kosarev <ivan.kosarev at amd.com>
  Date:   2024-01-10 (Wed, 10 Jan 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
    M llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    M llvm/lib/Target/AMDGPU/VOP1Instructions.td
    M llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fceil.s16.mir
    M llvm/test/CodeGen/AMDGPU/fix-sgpr-copies-f16.mir
    M llvm/test/CodeGen/AMDGPU/llvm.ceil.f16.ll
    M llvm/test/CodeGen/AMDGPU/move-to-valu-pseudo-scalar-trans.ll
    M llvm/test/MC/AMDGPU/gfx11_asm_err.s
    A llvm/test/MC/AMDGPU/gfx11_asm_vop1-fake16.s
    M llvm/test/MC/AMDGPU/gfx11_asm_vop1.s
    A llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16-fake16.s
    M llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp16.s
    A llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8-fake16.s
    M llvm/test/MC/AMDGPU/gfx11_asm_vop1_dpp8.s
    A llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err-fake16.s
    M llvm/test/MC/AMDGPU/gfx11_asm_vop1_t16_err.s
    A llvm/test/MC/AMDGPU/gfx11_unsupported_sdwa-fake16.s
    M llvm/test/MC/AMDGPU/gfx11_unsupported_sdwa.s
    M llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop1.txt

  Log Message:
  -----------
  [AMDGPU][True16] Support V_CEIL_F16. (#73108)

As not all fake instructions have their real counterparts implemented
yet, we specify no AssemblerPredicate for UseFakeTrue16Insts to allow
both fake and real True16 instructions in assembler and disassembler
tests in the -mattr=+real-true16 mode during the transition period.

Source DPP and desitnation VOPDstOperand_t16 operands are still not
supported and will be addressed separately.