Index: lib/Transforms/Utils/LoopUnroll.cpp
===================================================================
--- lib/Transforms/Utils/LoopUnroll.cpp
+++ lib/Transforms/Utils/LoopUnroll.cpp
@@ -172,6 +172,62 @@
   return false;
 }
 
+/// The function chooses which type of unroll (epilog or prolog) is more
+/// profitabale.
+/// Epilog unroll is more profitable when there is PHI that starts from
+/// constant.  In this case epilog will leave PHI start from constant,
+/// but prolog will convert it to non-constant.
+///
+/// loop:
+///   PN = PHI [I, Latch], [CI, PreHeader]
+///   I = foo(PN)
+///   ...
+///
+/// Epilog unroll case.
+/// loop:
+///   PN = PHI [I2, Latch], [CI, PreHeader]
+///   I1 = foo(PN)
+///   I2 = foo(I1)
+///   ...
+/// Prolog unroll case.
+///   NewPN = PHI [PrologI, Prolog], [CI, PreHeader]
+/// loop:
+///   PN = PHI [I2, Latch], [NewPN, PreHeader]
+///   I1 = foo(PN)
+///   I2 = foo(I1)
+///   ...
+///
+/// In addition we get potential alignment benefit if
+/// the constant is modulo of unroll count.
+static bool isEpilogProfitable(Loop *L, unsigned Count) {
+  assert(Count > 0);
+  BasicBlock *Latch = L->getLoopLatch();
+  BasicBlock *PreHeader = L->getLoopPreheader();
+  BasicBlock *Header = L->getHeader();
+  assert(Latch || PreHeader || Header);
+  for (Instruction &BBI : *Header) {
+    PHINode *PN = dyn_cast<PHINode>(&BBI);
+    if (!PN)
+      break;
+    if (PN->getBasicBlockIndex(PreHeader) < 0)
+      continue;
+    Value *V = PN->getIncomingValueForBlock(PreHeader);
+    if (!V)
+      continue;
+    if (ConstantInt *CI = dyn_cast<ConstantInt>(V)) {
+      APInt Val = CI->getValue();
+      // If CI type width is less than Count width, consider epilog unroll
+      // is profitable.  For example for bool type, epilog is always profitable.
+      if (Val.getBitWidth() <= 31 && (1UL << Val.getBitWidth()) <= Count)
+        return true;
+      APInt Divider (Val.getBitWidth(), (uint64_t)Count);
+      if (Val.urem(Divider) == 0)
+        return true;
+    }
+  }
+  return false;
+}
+
 /// Unroll the given loop by Count. The loop must be in LCSSA form. Returns true
 /// if unrolling was successful, or false if the loop was unmodified. Unrolling
 /// can only fail when the loop's latch block is not terminated by a conditional
@@ -301,12 +357,15 @@
                "Unroll count must divide trip multiple if loop contains a "
                "convergent operation.");
       });
+  bool EpiplogProfitability =
+      UnrollRuntimeEpilog.getNumOccurrences() ? UnrollRuntimeEpilog
+                                              : isEpilogProfitable (L, Count);
   // Don't output the runtime loop remainder if Count is a multiple of
   // TripMultiple.  Such a remainder is never needed, and is unsafe if the loop
   // contains a convergent instruction.
   if (RuntimeTripCount && TripMultiple % Count != 0 &&
       !UnrollRuntimeLoopRemainder(L, Count, AllowExpensiveTripCount,
-                                  UnrollRuntimeEpilog, LI, SE, DT, 
+                                  EpiplogProfitability, LI, SE, DT, 
                                   PreserveLCSSA)) {
     if (Force)
       RuntimeTripCount = false;
Index: test/Transforms/LoopUnroll/runtime-loop5.ll
===================================================================
--- test/Transforms/LoopUnroll/runtime-loop5.ll
+++ test/Transforms/LoopUnroll/runtime-loop5.ll
@@ -11,9 +11,6 @@
   %cmp1 = icmp eq i3 %n, 0
   br i1 %cmp1, label %for.end, label %for.body
 
-; UNROLL-16-NOT: for.body.prol:
-; UNROLL-4: for.body.prol:
-
 for.body:                                         ; preds = %for.body, %entry
 ; UNROLL-16-LABEL: for.body:
 ; UNROLL-4-LABEL: for.body:
@@ -39,6 +36,10 @@
 
 ; UNROLL-16-LABEL: for.end
 ; UNROLL-4-LABEL: for.end
+
+; UNROLL-16-NOT: for.body.epil:
+; UNROLL-4: for.body.epil:
+
 for.end:                                          ; preds = %for.body, %entry
   %sum.0.lcssa = phi i3 [ 0, %entry ], [ %add, %for.body ]
   ret i3 %sum.0.lcssa
Index: test/Transforms/LoopUnroll/unroll-pragmas.ll
===================================================================
--- test/Transforms/LoopUnroll/unroll-pragmas.ll
+++ test/Transforms/LoopUnroll/unroll-pragmas.ll
@@ -171,10 +171,6 @@
 ; should be duplicated (original and 4x unrolled).
 ;
 ; CHECK-LABEL: @runtime_loop_with_count4(
-; CHECK: for.body.prol:
-; CHECK: store
-; CHECK-NOT: store
-; CHECK: br i1
 ; CHECK: for.body
 ; CHECK: store
 ; CHECK: store
@@ -182,6 +178,10 @@
 ; CHECK: store
 ; CHECK-NOT: store
 ; CHECK: br i1
+; CHECK: for.body.epil:
+; CHECK: store
+; CHECK-NOT: store
+; CHECK: br i1
 define void @runtime_loop_with_count4(i32* nocapture %a, i32 %b) {
 entry:
   %cmp3 = icmp sgt i32 %b, 0
@@ -287,10 +287,6 @@
 ; (original and 8x).
 ;
 ; CHECK-LABEL: @runtime_loop_with_enable(
-; CHECK: for.body.prol:
-; CHECK: store
-; CHECK-NOT: store
-; CHECK: br i1
 ; CHECK: for.body:
 ; CHECK: store i32
 ; CHECK: store i32
@@ -302,6 +298,10 @@
 ; CHECK: store i32
 ; CHECK-NOT: store i32
 ; CHECK: br i1
+; CHECK: for.body.epil:
+; CHECK: store
+; CHECK-NOT: store
+; CHECK: br i1
 define void @runtime_loop_with_enable(i32* nocapture %a, i32 %b) {
 entry:
   %cmp3 = icmp sgt i32 %b, 0
@@ -328,16 +328,16 @@
 ; should be duplicated (original and 3x unrolled).
 ;
 ; CHECK-LABEL: @runtime_loop_with_count3(
-; CHECK: for.body.prol:
-; CHECK: store
-; CHECK-NOT: store
-; CHECK: br i1
 ; CHECK: for.body
 ; CHECK: store
 ; CHECK: store
 ; CHECK: store
 ; CHECK-NOT: store
 ; CHECK: br i1
+; CHECK: for.body.epil:
+; CHECK: store
+; CHECK-NOT: store
+; CHECK: br i1
 define void @runtime_loop_with_count3(i32* nocapture %a, i32 %b) {
 entry:
   %cmp3 = icmp sgt i32 %b, 0