[clang] [llvm] [RFC][AMDGPU] Use `bf16` instead of `i16` for bfloat (PR #80908)
Shilei Tian via cfe-commits
cfe-commits at lists.llvm.org
Thu Feb 8 13:47:03 PST 2024
================
@@ -4181,13 +4181,20 @@ bool SIInstrInfo::isInlineConstant(const MachineOperand &MO,
case AMDGPU::OPERAND_REG_INLINE_C_V2INT16:
case AMDGPU::OPERAND_REG_INLINE_AC_V2INT16:
return AMDGPU::isInlinableLiteralV2I16(Imm);
+ case AMDGPU::OPERAND_REG_IMM_V2BF16:
----------------
shiltian wrote:
Yeah, I made some mistakes here. Will take care of them.
https://github.com/llvm/llvm-project/pull/80908
More information about the cfe-commits
mailing list