[llvm] [AMDGPU] Prevent hang in SIFoldOperands (PR #82099)

[via llvm-commits]

================
@@ -219,10 +219,8 @@ bool SIFoldOperands::canUseImmWithOpSel(FoldCandidate &Fold) const {
   default:
     return false;
   case AMDGPU::OPERAND_REG_IMM_V2FP16:
-  case AMDGPU::OPERAND_REG_IMM_V2BF16:
----------------
choikwa wrote:

Thanks for catching! not sure if I ever touched that but it seems concerning if rebase did that.

https://github.com/llvm/llvm-project/pull/82099