Index: lib/CodeGen/CodeGenPrepare.cpp
===================================================================
--- lib/CodeGen/CodeGenPrepare.cpp
+++ lib/CodeGen/CodeGenPrepare.cpp
@@ -4227,11 +4227,20 @@
 
 } // end anonymous namespace
 
-/// Return true if the specified values are defined in a
-/// different basic block than BB.
-static bool IsNonLocalValue(Value *V, BasicBlock *BB) {
-  if (Instruction *I = dyn_cast<Instruction>(V))
-    return I->getParent() != BB;
+/// Return true if the specified value is defined in a
+/// different basic block than I or is defined in the same BB but after BI.
+static bool IsNonLocalValueOrAfter(Value *V, Instruction *BI) {
+  BasicBlock *BB = BI->getParent();
+  if (Instruction *I = dyn_cast<Instruction>(V)) {
+    if (I->getParent() != BB)
+      return true;
+    for (Instruction &BBI : *BB) {
+      if (&BBI == I)
+        return false;
+      if (&BBI == BI)
+        return true;
+    }
+  }
   return false;
 }
 
@@ -4343,7 +4352,7 @@
 
   // If all the instructions matched are already in this BB, don't do anything.
   if (none_of(AddrModeInsts, [&](Value *V) {
-        return IsNonLocalValue(V, MemoryInst->getParent());
+        return IsNonLocalValueOrAfter(V, MemoryInst);
       })) {
     DEBUG(dbgs() << "CGP: Found      local addrmode: " << AddrMode << "\n");
     return false;
Index: test/CodeGen/X86/sink-gep-before-mem-inst.ll
===================================================================
--- /dev/null
+++ test/CodeGen/X86/sink-gep-before-mem-inst.ll
@@ -0,0 +1,25 @@
+; RUN: opt < %s -S -codegenprepare -mtriple=x86_64-unknown-linux-gnu | FileCheck %s
+
+define i64 @test.after(i8 addrspace(1)* readonly align 8) {
+; CHECK-LABEL: test.after
+; CHECK: sunkaddr
+entry:
+  %.0 = getelementptr inbounds i8, i8 addrspace(1)* %0, i64 8
+  %addr = bitcast i8 addrspace(1)* %.0 to i32 addrspace(1)*
+  br label %header
+
+header:
+  %addr.in.loop = phi i32 addrspace(1)* [ %addr, %entry ], [ %addr.after, %header ]
+  %local_2_ = phi i64 [ 0, %entry ], [ %.9, %header ]
+  %.7 = load i32, i32 addrspace(1)* %addr.in.loop, align 8
+  fence acquire
+  %.1 = getelementptr inbounds i8, i8 addrspace(1)* %0, i64 8
+  %addr.after = bitcast i8 addrspace(1)* %.1 to i32 addrspace(1)*
+  %.8 = sext i32 %.7 to i64
+  %.9 = add i64 %local_2_, %.8
+  %not. = icmp sgt i64 %.9, 999
+  br i1 %not., label %exit, label %header
+
+exit:
+  ret i64 %.9
+}