Index: llvm/trunk/lib/Transforms/Scalar/IndVarSimplify.cpp
===================================================================
--- llvm/trunk/lib/Transforms/Scalar/IndVarSimplify.cpp
+++ llvm/trunk/lib/Transforms/Scalar/IndVarSimplify.cpp
@@ -36,6 +36,7 @@
 #include "llvm/Analysis/ScalarEvolutionAliasAnalysis.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
+#include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/CFG.h"
 #include "llvm/IR/Constants.h"
@@ -1281,7 +1282,8 @@
     }
   }
   // Our raison d'etre! Eliminate sign and zero extension.
-  if (IsSigned ? isa<SExtInst>(DU.NarrowUse) : isa<ZExtInst>(DU.NarrowUse)) {
+  if ((isa<SExtInst>(DU.NarrowUse) && (IsSigned || DU.NeverNegative)) ||
+      (isa<ZExtInst>(DU.NarrowUse) && (!IsSigned || DU.NeverNegative))) {
     Value *NewDef = DU.WideDef;
     if (DU.NarrowUse->getType() != WideType) {
       unsigned CastWidth = SE->getTypeSizeInBits(DU.NarrowUse->getType());
@@ -1370,9 +1372,12 @@
 ///
 void WidenIV::pushNarrowIVUsers(Instruction *NarrowDef, Instruction *WideDef) {
   const SCEV *NarrowSCEV = SE->getSCEV(NarrowDef);
+  // isKnownPredicate is enough for most cases but still need isKnownNonNegative 
+  // here to work around conservatism in ScalarEvolution about no-wrap flags. 
   bool NeverNegative =
       SE->isKnownPredicate(ICmpInst::ICMP_SGE, NarrowSCEV,
-                           SE->getConstant(NarrowSCEV->getType(), 0));
+                           SE->getConstant(NarrowSCEV->getType(), 0)) ||
+      isKnownNonNegative(NarrowDef, NarrowDef->getModule()->getDataLayout());
   for (User *U : NarrowDef->users()) {
     Instruction *NarrowUser = cast<Instruction>(U);
 
Index: llvm/trunk/test/Transforms/IndVarSimplify/iv-widen-elim-ext.ll
===================================================================
--- llvm/trunk/test/Transforms/IndVarSimplify/iv-widen-elim-ext.ll
+++ llvm/trunk/test/Transforms/IndVarSimplify/iv-widen-elim-ext.ll
@@ -0,0 +1,82 @@
+; RUN: opt < %s -indvars -S | FileCheck %s
+
+target datalayout = "p:64:64:64-n32:64"
+
+; When widening IV and its users, trunc and zext/sext are not needed
+; if the original 32-bit user is known to be non-negative, whether
+; the IV is considered signed or unsigned.
+define void @foo(i32* %A, i32* %B, i32* %C, i32 %N) {
+; CHECK-LABEL: @foo(
+; CHECK-NOT: zext
+; CHECK-NOT: sext
+entry:
+  %cmp1 = icmp slt i32 0, %N
+  br i1 %cmp1, label %for.body.lr.ph, label %for.end
+
+for.body.lr.ph:                                   ; preds = %entry
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.lr.ph, %for.inc
+  %i.02 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
+  %idxprom = sext i32 %i.02 to i64
+  %arrayidx = getelementptr inbounds i32, i32* %B, i64 %idxprom
+  %0 = load i32, i32* %arrayidx, align 4
+  %add = add nsw i32 %i.02, 2
+  %idxprom1 = zext i32 %add to i64
+  %arrayidx2 = getelementptr inbounds i32, i32* %C, i64 %idxprom1
+  %1 = load i32, i32* %arrayidx2, align 4
+  %add3 = add nsw i32 %0, %1
+  %idxprom4 = zext i32 %i.02 to i64
+  %arrayidx5 = getelementptr inbounds i32, i32* %A, i64 %idxprom4
+  store i32 %add3, i32* %arrayidx5, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body
+  %inc = add nsw i32 %i.02, 1
+  %cmp = icmp slt i32 %inc, %N
+  br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
+
+for.cond.for.end_crit_edge:                       ; preds = %for.inc
+  br label %for.end
+
+for.end:                                          ; preds = %for.cond.for.end_crit_edge, %entry
+  ret void
+}
+
+define void @foo1(i32* %A, i32* %B, i32* %C, i32 %N) {
+; CHECK-LABEL: @foo1(
+; CHECK-NOT: zext
+; CHECK-NOT: sext
+entry:
+  %cmp1 = icmp slt i32 0, %N
+  br i1 %cmp1, label %for.body.lr.ph, label %for.end
+
+for.body.lr.ph:                                   ; preds = %entry
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.lr.ph, %for.inc
+  %i.02 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
+  %idxprom = zext i32 %i.02 to i64
+  %arrayidx = getelementptr inbounds i32, i32* %B, i64 %idxprom
+  %0 = load i32, i32* %arrayidx, align 4
+  %add = add nsw i32 %i.02, 2
+  %idxprom1 = sext i32 %add to i64
+  %arrayidx2 = getelementptr inbounds i32, i32* %C, i64 %idxprom1
+  %1 = load i32, i32* %arrayidx2, align 4
+  %add3 = add nsw i32 %0, %1
+  %idxprom4 = sext i32 %i.02 to i64
+  %arrayidx5 = getelementptr inbounds i32, i32* %A, i64 %idxprom4
+  store i32 %add3, i32* %arrayidx5, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body
+  %inc = add nsw i32 %i.02, 1
+  %cmp = icmp slt i32 %inc, %N
+  br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
+
+for.cond.for.end_crit_edge:                       ; preds = %for.inc
+  br label %for.end
+
+for.end:                                          ; preds = %for.cond.for.end_crit_edge, %entry
+  ret void
+}