Index: include/llvm/Analysis/GlobalsModRef.h
===================================================================
--- include/llvm/Analysis/GlobalsModRef.h
+++ include/llvm/Analysis/GlobalsModRef.h
@@ -105,6 +105,8 @@
   bool AnalyzeIndirectGlobalMemory(GlobalValue *GV);
 
   bool isNonEscapingGlobalNoAlias(const GlobalValue *GV, const Value *V);
+  ModRefInfo getModRefInfoForIntrinsic(ImmutableCallSite CS,
+                                       const GlobalValue *GV);
 };
 
 /// Analysis pass providing a never-invalidated alias analysis result.
Index: lib/Analysis/GlobalsModRef.cpp
===================================================================
--- lib/Analysis/GlobalsModRef.cpp
+++ lib/Analysis/GlobalsModRef.cpp
@@ -765,6 +765,32 @@
   return AAResultBase::alias(LocA, LocB);
 }
 
+ModRefInfo GlobalsAAResult::getModRefInfoForIntrinsic(ImmutableCallSite CS,
+                                                      const GlobalValue *GV) {
+  auto IsGV = [&](unsigned OpIdx) {
+    return GetUnderlyingObject(CS.getArgument(OpIdx), DL) == GV;
+  };
+
+  switch (CS.getCalledFunction()->getIntrinsicID()) {
+  default:
+    // We don't know the intrinsic, but if it's readnone, it doesn't modify
+    // or reference anything...
+    if (CS.doesNotAccessMemory())
+      return MRI_NoModRef;
+    // ... and if it's readonly it only references.
+    if (CS.onlyReadsMemory())
+      return MRI_Ref;
+    // Fallback - we don't know anything about this intrinsic.
+    return MRI_ModRef;
+  case Intrinsic::memset:
+    return (IsGV(0) ? MRI_Mod : MRI_NoModRef);
+  case Intrinsic::memcpy:
+  case Intrinsic::memmove:
+    return static_cast<ModRefInfo>((IsGV(0) ? MRI_Mod : MRI_NoModRef) |
+                                   (IsGV(1) ? MRI_Ref : MRI_NoModRef));
+  }
+}
+
 ModRefInfo GlobalsAAResult::getModRefInfo(ImmutableCallSite CS,
                                           const MemoryLocation &Loc) {
   unsigned Known = MRI_ModRef;
@@ -777,7 +803,8 @@
       if (const Function *F = CS.getCalledFunction())
         if (NonAddressTakenGlobals.count(GV))
           if (const FunctionInfo *FI = getFunctionInfo(F))
-            Known = FI->getModRefInfoForGlobal(*GV);
+            Known = FI->getModRefInfoForGlobal(*GV) |
+              getModRefInfoForIntrinsic(CS, GV);
 
   if (Known == MRI_NoModRef)
     return MRI_NoModRef; // No need to query other mod/ref analyses
Index: lib/Analysis/ScalarEvolution.cpp
===================================================================
--- lib/Analysis/ScalarEvolution.cpp
+++ lib/Analysis/ScalarEvolution.cpp
@@ -8474,7 +8474,7 @@
   F.printAsOperand(OS, /*PrintType=*/false);
   OS << "\n";
   for (inst_iterator I = inst_begin(F), E = inst_end(F); I != E; ++I)
-    if (isSCEVable(I->getType()) && !isa<CmpInst>(*I)) {
+    if (isSCEVable(I->getType()) /*&& !isa<CmpInst>(*I)*/) {
       OS << *I << '\n';
       OS << "  -->  ";
       const SCEV *SV = SE.getSCEV(&*I);
Index: test/Analysis/GlobalsModRef/memset-escape.ll
===================================================================
--- /dev/null
+++ test/Analysis/GlobalsModRef/memset-escape.ll
@@ -0,0 +1,65 @@
+; RUN: opt < %s -O1 -S -enable-non-lto-gmr=true | FileCheck %s
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.10.0"
+
+@a = internal global [3 x i32] zeroinitializer, align 4
+@b = common global i32 0, align 4
+
+; The important thing we're checking for here is the reload of (some element of)
+; @a after the memset.
+
+; CHECK-LABEL: @main
+; CHECK: call void @llvm.memset.p0i8.i64{{.*}} @a
+; CHECK: store i32 3
+; CHECK: load i32, i32* getelementptr {{.*}} @a
+; CHECK: icmp eq i32
+; CHECK: br i1
+
+define i32 @main() {
+entry:
+  %retval = alloca i32, align 4
+  %c = alloca [1 x i32], align 4
+  store i32 0, i32* %retval, align 4
+  %0 = bitcast [1 x i32]* %c to i8*
+  call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 4, i32 4, i1 false)
+  store i32 1, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 2), align 4
+  store i32 0, i32* @b, align 4
+  br label %for.cond
+
+for.cond:                                         ; preds = %for.inc, %entry
+  %1 = load i32, i32* @b, align 4
+  %cmp = icmp slt i32 %1, 3
+  br i1 %cmp, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.cond
+  %2 = load i32, i32* @b, align 4
+  %idxprom = sext i32 %2 to i64
+  %arrayidx = getelementptr inbounds [3 x i32], [3 x i32]* @a, i64 0, i64 %idxprom
+  store i32 0, i32* %arrayidx, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body
+  %3 = load i32, i32* @b, align 4
+  %inc = add nsw i32 %3, 1
+  store i32 %inc, i32* @b, align 4
+  br label %for.cond
+
+for.end:                                          ; preds = %for.cond
+  %4 = load i32, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 2), align 4
+  %cmp1 = icmp ne i32 %4, 0
+  br i1 %cmp1, label %if.then, label %if.end
+
+if.then:                                          ; preds = %for.end
+  call void @abort() #3
+  unreachable
+
+if.end:                                           ; preds = %for.end
+  ret i32 0
+}
+
+; Function Attrs: nounwind argmemonly
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind argmemonly
+
+; Function Attrs: noreturn nounwind
+declare void @abort() noreturn nounwind