Index: lib/Transforms/Utils/LoopUnrollRuntime.cpp
===================================================================
--- lib/Transforms/Utils/LoopUnrollRuntime.cpp
+++ lib/Transforms/Utils/LoopUnrollRuntime.cpp
@@ -313,6 +313,27 @@
   BasicBlock *Header = L->getHeader();
   const DataLayout &DL = Header->getModule()->getDataLayout();
   SCEVExpander Expander(*SE, DL, "loop-unroll");
+
+  // If IV's step is one or minus one, we can unroll the loop.
+  // Because we don't need to generate division for computing trip count.
+  if (BranchInst *BI =
+          dyn_cast<BranchInst>(L->getExitingBlock()->getTerminator())) {
+    if (ICmpInst *ExitCondICmp = dyn_cast<ICmpInst>(BI->getCondition())) {
+      if (const SCEVAddRecExpr *AR =
+              dyn_cast<SCEVAddRecExpr>(SE->getSCEVAtScope(
+                  SE->getSCEV(ExitCondICmp->getOperand(0)), L))) {
+        if (AR->isAffine() && AR->getOperand(1)->getSCEVType() == scConstant) {
+          if (const SCEVConstant *SCConst =
+                  cast<SCEVConstant>(AR->getOperand(1))) {
+            if (SCConst->getValue()->isOne() ||
+                SCConst->getValue()->isMinusOne())
+              AllowExpensiveTripCount = true;
+          }
+        }
+      }
+    }
+  }
+
   if (!AllowExpensiveTripCount && Expander.isHighCostExpansion(TripCountSC, L))
     return false;
 
Index: test/Transforms/LoopUnroll/high-cost-trip-count-computation.ll
===================================================================
--- test/Transforms/LoopUnroll/high-cost-trip-count-computation.ll
+++ test/Transforms/LoopUnroll/high-cost-trip-count-computation.ll
@@ -24,4 +24,47 @@
   ret i32 0
 }
 
+;; We expect this loop to be unrolled, because IV's step is minus one.
+;; So we don't need to generate division for computing trip count.
+
+define i32 @test2(i64 %v12, i8* %array, i64* %loc, fp128 %call1.i, fp128 %call2.i) {
+; CHECK-LABEL: @test2(
+; CHECK-LABEL: for.body.prol
+; CHECK: 0xL0000000000000000401DFFFFFFF80000
+; CHECK: 0xL0000000000000000401DFFFFFFF80000
+; CHECK: 0xL0000000000000000401DFFFFFFF80000
+entry:
+  %rem0 = load i64, i64* %loc, align 8, !tbaa !0
+  %div1 = fdiv fast fp128 %call1.i, %call2.i
+  %conv7 = fptoui fp128 %div1 to i64
+  %sub11 = add i64 %conv7, 23
+  %div11 = udiv i64 %sub11, %conv7
+  %cmp.i38 = icmp ugt i64 %div11, 1
+  %div12 = select i1 %cmp.i38, i64 %div11, i64 1
+  br label %for.body
+for.body:
+  %rem1 = phi i64 [ %rem0, %entry ], [ %rem2, %for.body ]
+  %tmp1 = phi float [ 1.000000e+00, %entry ], [ %conv21, %for.body ]
+  %sum1 = phi float [ 0.000000e+00, %entry ], [ %add18, %for.body ]
+  %k1 = phi i64 [ %div12, %entry ], [ %dec, %for.body ]
+  %mul1 = mul i64 %rem1, 48271
+  %rem2 = urem i64 %mul1, 2147483647
+  %sub16 = add nsw i64 %rem2, -1
+  %conv17. = uitofp i64 %sub16 to float
+  %mul2 = fmul fast float %conv17., %tmp1
+  %add18 = fadd fast float %mul2, %sum1
+  %conv19 = fpext float %tmp1 to fp128
+  %mul3 = fmul fast fp128 %conv19, 0xL0000000000000000401DFFFFFFF80000
+  %conv21 = fptrunc fp128 %mul3 to float
+  %dec = add i64 %k1, -1
+  %cmp = icmp eq i64 %dec, 0
+  br i1 %cmp, label %exit, label %for.body
+exit:
+  %conv22 = phi float [ %conv21, %for.body ]
+  %add19 = phi float [ %add18, %for.body ]
+  %rem3 = phi i64 [ %rem2, %for.body ]
+  store i64 %rem3, i64* %loc, align 8, !tbaa !0
+  ret i32 0
+}
+
 !0 = !{i64 1, i64 100}