Index: lib/CodeGen/TwoAddressInstructionPass.cpp
===================================================================
--- lib/CodeGen/TwoAddressInstructionPass.cpp
+++ lib/CodeGen/TwoAddressInstructionPass.cpp
@@ -102,6 +102,8 @@
   bool sink3AddrInstruction(MachineInstr *MI, unsigned Reg,
                             MachineBasicBlock::iterator OldPos);
 
+  MachineInstr *getSingleDefUse(unsigned Reg, bool def);
+
   bool noUseAfterLastDef(unsigned Reg, unsigned Dist, unsigned &LastDef);
 
   bool isProfitableToCommute(unsigned regA, unsigned regB, unsigned regC,
@@ -309,6 +311,26 @@
   return true;
 }
 
+// getSingleDefUse -- If def is true, return the MachineInstr* if it is the single
+// def of the Reg. If def is false, return the MachineInstr* if it is the single
+// use of the Reg.
+MachineInstr* TwoAddressInstructionPass::getSingleDefUse(unsigned Reg, bool def) {
+  MachineInstr *ret = NULL;
+  for (MachineOperand &MO : MRI->reg_operands(Reg)) {
+    MachineInstr *MI = MO.getParent();
+    if (MI->getParent() != MBB || MI->isDebugValue())
+      continue;
+    if ((def && MO.isDef()) ||
+        (!def && MO.isUse())) {
+      if (!ret)
+        ret = MI;
+      else if (ret != MI)
+        ret = NULL;
+    }
+  }
+  return ret;
+}
+
 /// noUseAfterLastDef - Return true if there are no intervening uses between the
 /// last instruction in the MBB that defines the specified register and the
 /// two-address instruction which is being processed. It also returns the last
@@ -574,6 +596,25 @@
   if (!noUseAfterLastDef(regB, Dist, LastDefB))
     return true;
 
+  // Look for situation like this:
+  // %reg101 = MOV %reg100
+  // %reg102 = ...
+  // %reg103 = ADD %reg102, %reg101
+  // %reg100 = MOV %reg103
+  // Commute the ADD to hopefully eliminate an otherwise unavoidable copy.
+  MachineInstr *defB = getSingleDefUse(regB, true);
+  MachineInstr *defC = getSingleDefUse(regC, true);
+  MachineInstr *useA = getSingleDefUse(regA, false);
+  if (useA && defC &&
+      useA->isCopy() && defC->isCopy() &&
+      useA->getOperand(0).getReg() == defC->getOperand(1).getReg())
+    return true;
+
+  if (useA && defB &&
+      useA->isCopy() && defB->isCopy() &&
+      useA->getOperand(0).getReg() == defB->getOperand(1).getReg())
+    return false;
+
   // Since there are no intervening uses for both registers, then commute
   // if the def of regC is closer. Its live interval is shorter.
   return LastDefB && LastDefC && LastDefC > LastDefB;
Index: test/CodeGen/X86/twoaddr-coalesce-3.ll
===================================================================
--- test/CodeGen/X86/twoaddr-coalesce-3.ll
+++ test/CodeGen/X86/twoaddr-coalesce-3.ll
@@ -0,0 +1,42 @@
+; RUN: llc < %s -march=x86 | grep mov | count 4
+
+@M = common global i32 0, align 4
+@total = common global i32 0, align 4
+
+; Function Attrs: nounwind uwtable
+define void @foo() #0 {
+entry:
+  %0 = load i32* @M, align 4, !tbaa !1
+  %cmp3 = icmp sgt i32 %0, 0
+  br i1 %cmp3, label %for.body.lr.ph, label %for.end
+
+for.body.lr.ph:                                   ; preds = %entry
+  %total.promoted = load i32* @total, align 4, !tbaa !1
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.lr.ph, %for.body
+  %add5 = phi i32 [ %total.promoted, %for.body.lr.ph ], [ %add, %for.body ]
+  %i.04 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.body ]
+  %div = sdiv i32 %i.04, 2
+  %add = add nsw i32 %div, %add5
+  %inc = add nuw nsw i32 %i.04, 1
+  %cmp = icmp slt i32 %inc, %0
+  br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
+
+for.cond.for.end_crit_edge:                       ; preds = %for.body
+  store i32 %add, i32* @total, align 4, !tbaa !1
+  br label %for.end
+
+for.end:                                          ; preds = %for.cond.for.end_crit_edge, %entry
+  ret void
+}
+
+attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!llvm.ident = !{!0}
+
+!0 = !{!"clang version 3.7.0 (trunk 230041)"}
+!1 = !{!2, !2, i64 0}
+!2 = !{!"int", !3, i64 0}
+!3 = !{!"omnipotent char", !4, i64 0}
+!4 = !{!"Simple C/C++ TBAA"}