Index: lib/CodeGen/TailDuplication.cpp
===================================================================
--- lib/CodeGen/TailDuplication.cpp
+++ lib/CodeGen/TailDuplication.cpp
@@ -352,6 +352,18 @@
   return false;
 }
 
+static bool isKilledInBB(unsigned Reg, MachineBasicBlock *BB,
+    const MachineRegisterInfo *MRI)
+{
+  for (MachineOperand &MO : MRI->use_operands(Reg)) {
+    if (MO.getParent()->getParent() != BB)
+      continue;
+    if (MO.isKill())
+      return true;
+  }
+  return false;
+}
+
 static unsigned getPHISrcRegOpIdx(MachineInstr *MI, MachineBasicBlock *SrcBB) {
   for (unsigned i = 1, e = MI->getNumOperands(); i != e; i += 2)
     if (MI->getOperand(i+1).getMBB() == SrcBB)
@@ -408,7 +420,8 @@
   // Insert a copy from source to the end of the block. The def register is the
   // available value liveout of the block.
   unsigned NewDef = MRI->createVirtualRegister(RC);
-  Copies.push_back(std::make_pair(NewDef, SrcReg));
+  if (!isKilledInBB(DefReg, TailBB, MRI))
+    Copies.push_back(std::make_pair(NewDef, SrcReg));
   if (isDefLiveOut(DefReg, TailBB, MRI) || RegsUsedByPhi.count(DefReg))
     AddSSAUpdateEntry(DefReg, NewDef, PredBB);
 
Index: test/CodeGen/Generic/taildup-kill.ll
===================================================================
--- /dev/null
+++ test/CodeGen/Generic/taildup-kill.ll
@@ -0,0 +1,48 @@
+; RUN: llc < %s -fast-isel -mcpu=core2 -O3 -verify-machineinstrs
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-darwin14.0.0"
+
+%jl_value_t = type { %jl_value_t* }
+
+declare %jl_value_t* @jl_apply_generic()
+
+define void @julia_anonymous1421() {
+pass25:                                           ; preds = %L22
+  br i1 undef, label %L31, label %if23
+
+if23:                                             ; preds = %pass25
+  br i1 undef, label %ok27, label %fail17
+
+ok27:                                             ; preds = %if23
+  br i1 undef, label %ok29, label %fail17
+
+ok29:                                             ; preds = %ok27
+  br i1 undef, label %isf, label %notf
+
+isf:                                              ; preds = %ok29
+  %0 = getelementptr %jl_value_t** undef, i64 4
+  br label %mergef
+
+fail17:                                           ; preds = %ok16
+  unreachable
+
+notf:                                             ; preds = %ok29
+  %1 = call %jl_value_t* @jl_apply_generic()
+  br label %mergef
+
+mergef:                                           ; preds = %notf, %isf
+  %2 = phi %jl_value_t* [ undef, %isf ], [ %1, %notf ]
+  store %jl_value_t* %2, %jl_value_t** undef
+  br label %L34
+
+L31:                                              ; preds = %pass25
+  br i1 undef, label %ok33, label %fail17
+
+ok33:                                             ; preds = %L31
+  store %jl_value_t* undef, %jl_value_t** undef
+  br label %L34
+
+L34:                                              ; preds = %ok33, %mergef
+  unreachable
+
+}