Index: lib/Transforms/Scalar/LoopStrengthReduce.cpp
===================================================================
--- lib/Transforms/Scalar/LoopStrengthReduce.cpp
+++ lib/Transforms/Scalar/LoopStrengthReduce.cpp
@@ -2088,7 +2088,26 @@
 LSRInstance::OptimizeLoopTermCond() {
   SmallPtrSet<Instruction *, 4> PostIncs;
 
+  // We need a different set of heuristics for rotated and non-rotated loops.
+  // If a loop is rotated then the latch is also the backedge, so inserting
+  // post-inc expressions just before the latch is ideal. To reduce live ranges
+  // it also makes sense to rewrite terminating conditions to use post-inc
+  // expressions.
+  //
+  // If the loop is not rotated then the latch is not a backedge; the latch
+  // check is done in the loop head. Adding post-inc expressions before the
+  // latch will cause overlapping live-ranges of pre-inc and post-inc expressions
+  // in the loop body. In this case we do *not* want to use post-inc expressions
+  // in the latch check, and we want to insert post-inc expressions before
+  // the backedge.
   BasicBlock *LatchBlock = L->getLoopLatch();
+  if (L->getExitingBlock() && LatchBlock != L->getExitingBlock()) {
+    // The backedge doesn't exit the loop; treat this as a head-tested loop.
+    IVIncInsertPos = LatchBlock->getTerminator();
+    return;
+  }
+
+  // Otherwise treat this as a rotated loop.
   SmallVector<BasicBlock*, 8> ExitingBlocks;
   L->getExitingBlocks(ExitingBlocks);
 
Index: test/CodeGen/Hexagon/hwloop-loop1.ll
===================================================================
--- test/CodeGen/Hexagon/hwloop-loop1.ll
+++ test/CodeGen/Hexagon/hwloop-loop1.ll
@@ -2,8 +2,6 @@
 ;
 ; Generate loop1 instruction for double loop sequence.
 
-; CHECK: loop0(.LBB{{.}}_{{.}}, #100)
-; CHECK: endloop0
 ; CHECK: loop1(.LBB{{.}}_{{.}}, #100)
 ; CHECK: loop0(.LBB{{.}}_{{.}}, #100)
 ; CHECK: endloop0
Index: test/CodeGen/X86/lsr-loop-exit-cond.ll
===================================================================
--- test/CodeGen/X86/lsr-loop-exit-cond.ll
+++ test/CodeGen/X86/lsr-loop-exit-cond.ll
@@ -3,12 +3,12 @@
 
 ; CHECK-LABEL: t:
 ; CHECK: movl (%r9,%rax,4), %e{{..}}
-; CHECK-NEXT: decq
+; CHECK-NEXT: testq
 ; CHECK-NEXT: jne
 
 ; ATOM-LABEL: t:
 ; ATOM: movl (%r9,%r{{.+}},4), %e{{..}}
-; ATOM-NEXT: decq
+; ATOM-NEXT: testq
 ; ATOM-NEXT: jne
 
 @Te0 = external global [256 x i32]		; <[256 x i32]*> [#uses=5]
Index: test/Transforms/LoopStrengthReduce/post-inc-optsize.ll
===================================================================
--- /dev/null
+++ test/Transforms/LoopStrengthReduce/post-inc-optsize.ll
@@ -0,0 +1,41 @@
+; RUN: opt < %s -loop-reduce
+
+target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
+target triple = "thumbv7m-arm-none-eabi"
+
+; Check that the PHIs are not transformed to post-inc, and that they are inserted in the
+; latch block. Inserting them in the header block doubles register pressure and adds
+; moves.
+
+; CHECK-LABEL: @f
+; CHECK: while.body:
+; CHECK: incdec.ptr =
+; CHECK: incdec.ptr1 =
+; CHECK: incdec.ptr2 =
+; CHECK: dec = 
+define void @f(float* nocapture readonly %a, float* nocapture readonly %b, float* nocapture %c, i32 %n) {
+entry:
+  br label %while.cond
+
+while.cond:                                       ; preds = %while.body, %entry
+  %a.addr.0 = phi float* [ %a, %entry ], [ %incdec.ptr, %while.body ]
+  %b.addr.0 = phi float* [ %b, %entry ], [ %incdec.ptr1, %while.body ]
+  %c.addr.0 = phi float* [ %c, %entry ], [ %incdec.ptr2, %while.body ]
+  %n.addr.0 = phi i32 [ %n, %entry ], [ %dec, %while.body ]
+  %cmp = icmp sgt i32 %n.addr.0, 0
+  br i1 %cmp, label %while.body, label %while.end
+
+while.body:                                       ; preds = %while.cond
+  %incdec.ptr = getelementptr inbounds float, float* %a.addr.0, i32 1
+  %0 = load float, float* %a.addr.0, align 4
+  %incdec.ptr1 = getelementptr inbounds float, float* %b.addr.0, i32 1
+  %1 = load float, float* %b.addr.0, align 4
+  %add = fadd float %0, %1
+  %incdec.ptr2 = getelementptr inbounds float, float* %c.addr.0, i32 1
+  store float %add, float* %c.addr.0, align 4
+  %dec = add nsw i32 %n.addr.0, -1
+  br label %while.cond
+
+while.end:                                        ; preds = %while.cond
+  ret void
+}