[llvm] [AMDGPU][True16][CodeGen] support v_mov_b16 and v_swap_b16 in true16 format (PR #102198)

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Wed Aug 7 10:08:56 PDT 2024


================
@@ -1460,7 +1460,15 @@ bool SIFoldOperands::tryFoldFoldableCopy(
     return false;
   }
 
-  MachineOperand &OpToFold = MI.getOperand(1);
+  MachineOperand *OpToFoldPtr;
+  if (MI.getOpcode() == AMDGPU::V_MOV_B16_t16_e64) {
----------------
arsenm wrote:

I don't expect to need special casing here. Should this be filtered in isFoldableCopy? I thought we had filtering for regular v_mov_b32_e64 already somewhere here 

https://github.com/llvm/llvm-project/pull/102198


More information about the llvm-commits mailing list