[llvm] [AMDGPU] Add OMOD folding for TRANS bfloat16 instructions (PR #208595)

Changpeng Fang via llvm-commits llvm-commits at lists.llvm.org
Thu Jul 9 20:50:17 PDT 2026


================
@@ -2363,6 +2358,117 @@ SIFoldOperandsImpl::isOMod(const MachineInstr &MI) const {
 
     return std::pair(nullptr, SIOutMods::NONE);
   }
+  case AMDGPU::V_FMA_MIXLO_BF16:
+  case AMDGPU::V_FMA_MIX_BF16_t16: {
----------------
changpeng wrote:

'case AMDGPU::V_FMA_MIXLO_BF16' for non-true16 actually.

https://github.com/llvm/llvm-project/pull/208595


More information about the llvm-commits mailing list