[llvm] [AMDGPU] Exclude certain opcodes from being marked as single use (PR #91802)

[Scott Egerton via llvm-commits]

================
@@ -156,10 +156,12 @@ defm V_MAX_F64 : VOP3Inst <"v_max_f64", VOP3_Profile<VOP_F64_F64_F64>, fmaxnum_l
 } // End SchedRW = [WriteDoubleAdd]
 
 let SchedRW = [WriteIntMul] in {
+defm V_MUL_LO_I32 : VOP3Inst <"v_mul_lo_i32", V_MUL_PROF<VOP_I32_I32_I32>>;
----------------
ScottEgerton wrote:

That's good to know. I've changed the code back to handle all the mul opcodes together.

https://github.com/llvm/llvm-project/pull/91802