fix mutli use list modification

Author: broxigarchen

llvm/lib/Target/AMDGPU/SIInstrInfo.cpp

@@ -8716,6 +8716,8 @@ void SIInstrInfo::splitScalar64BitCountOp(SIInstrWorklist &Worklist,
 void SIInstrInfo::addUsersToMoveToVALUWorklist(
     Register DstReg, MachineRegisterInfo &MRI,
     SIInstrWorklist &Worklist) const {
+  SmallVector<std::pair<MachineInstr *, unsigned>> EarlyRangeInc;
+
   for (MachineRegisterInfo::use_iterator I = MRI.use_begin(DstReg),
          E = MRI.use_end(); I != E;) {
     MachineInstr &UseMI = *I->getParent();
@@ -8744,11 +8746,14 @@ void SIInstrInfo::addUsersToMoveToVALUWorklist(
         ++I;
       } while (I != E && I->getParent() == &UseMI);
     } else {
-      legalizeOperandsVALUt16(UseMI, OpNo, MRI);
+      EarlyRangeInc.emplace_back(&UseMI, OpNo);
 
       ++I;
     }
   }
+
+  for (auto &[UseMI, OpNo] : EarlyRangeInc)
+    legalizeOperandsVALUt16(*UseMI, OpNo, MRI);
 }
 
 void SIInstrInfo::movePackToVALU(SIInstrWorklist &Worklist,

llvm/test/CodeGen/AMDGPU/fix-sgpr-copies-f16-true16.mir

@@ -108,6 +108,32 @@ body:             |
     %4:sreg_32 = S_FMAC_F16 %3:sreg_32, %3:sreg_32, %2:sreg_32, implicit $mode
 ...
 
+---
+name:            legalize_with_multi_user
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: legalize_with_multi_user
+    ; GCN: [[DEF:%[0-9]+]]:vgpr_16 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vgpr_16 = IMPLICIT_DEF
+    ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vgpr_32 = REG_SEQUENCE [[DEF]], %subreg.lo16, [[DEF1]], %subreg.hi16
+    ; GCN-NEXT: [[V_ADD_F16_t16_e64_:%[0-9]+]]:vgpr_16 = V_ADD_F16_t16_e64 0, [[REG_SEQUENCE]].lo16, 0, 1, 0, 0, 0, implicit $mode, implicit $exec
+    ; GCN-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 32768
+    ; GCN-NEXT: [[DEF2:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF3:%[0-9]+]]:vgpr_16 = IMPLICIT_DEF
+    ; GCN-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:vgpr_32 = REG_SEQUENCE [[V_ADD_F16_t16_e64_]], %subreg.lo16, [[DEF3]], %subreg.hi16
+    ; GCN-NEXT: [[V_PK_FMA_F16_:%[0-9]+]]:vgpr_32 = V_PK_FMA_F16 11, [[S_MOV_B32_]], 0, [[REG_SEQUENCE1]], 8, [[DEF2]], 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    ; GCN-NEXT: [[DEF4:%[0-9]+]]:vgpr_16 = IMPLICIT_DEF
+    ; GCN-NEXT: [[REG_SEQUENCE2:%[0-9]+]]:vgpr_32 = REG_SEQUENCE [[V_ADD_F16_t16_e64_]], %subreg.lo16, [[DEF4]], %subreg.hi16
+    ; GCN-NEXT: [[V_XOR_B32_e64_:%[0-9]+]]:vgpr_32 = V_XOR_B32_e64 [[REG_SEQUENCE2]], [[S_MOV_B32_]], implicit $exec
+    %0:vgpr_16 = IMPLICIT_DEF
+    %1:sreg_32 = COPY %0:vgpr_16
+    %2:sreg_32 = S_ADD_F16 %1:sreg_32, 1, implicit $mode
+    %3:sreg_32 = S_MOV_B32 32768
+    %4:vgpr_32 = IMPLICIT_DEF
+    %5:vgpr_32 = V_PK_FMA_F16 11, %3:sreg_32, 0, %2:sreg_32, 8, %4:vgpr_32, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
+    %6:sreg_32 = S_XOR_B32 %2:sreg_32, %3:sreg_32, implicit-def dead $scc
+...
+
 ---
 name:            vgpr16_to_spgr32
 body:             |