Index: lib/Transforms/Scalar/LoopUnrollPass.cpp
===================================================================
--- lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ lib/Transforms/Scalar/LoopUnrollPass.cpp
@@ -531,7 +531,9 @@
     return None;
 
   SmallSetVector<BasicBlock *, 16> BBWorklist;
-  DenseMap<Value *, Constant *> SimplifiedValues;
+  DenseMap<Value *, Constant *> SimplifiedToConstantValues;
+  SmallSetVector<Instruction *, 16> SimplifiedToConstantOrDeadInsts;
+  SmallSetVector<Instruction *, 16> SimplifiedInsts;
 
   // The estimated cost of the unrolled form of the loop. We try to estimate
   // this by simplifying as much as we can while computing the estimate.
@@ -551,8 +553,10 @@
   // we literally have to go through all loop's iterations.
   for (unsigned Iteration = 0; Iteration < TripCount; ++Iteration) {
     DEBUG(dbgs() << " Analyzing iteration " << Iteration << "\n");
-    SimplifiedValues.clear();
-    UnrolledInstAnalyzer Analyzer(Iteration, SimplifiedValues, L, SE);
+    SimplifiedToConstantValues.clear();
+    SimplifiedToConstantOrDeadInsts.clear();
+    SimplifiedInsts.clear();
+    UnrolledInstAnalyzer Analyzer(Iteration, SimplifiedToConstantValues, L, SE);
 
     BBWorklist.clear();
     BBWorklist.insert(L->getHeader());
@@ -572,10 +576,13 @@
         if (!Analyzer.visit(I))
           UnrolledCost += InstCost;
         else {
+          SimplifiedInsts.insert(&I);
           DEBUG(dbgs() << "  " << I
                        << " would be simplified if loop is unrolled.\n");
           (void)0;
         }
+        if (SimplifiedToConstantValues.count(&I))
+          SimplifiedToConstantOrDeadInsts.insert(&I);
 
         // Also track this instructions expected cost when executing the rolled
         // loop form.
@@ -598,7 +605,7 @@
       if (BranchInst *BI = dyn_cast<BranchInst>(TI)) {
         if (BI->isConditional()) {
           if (Constant *SimpleCond =
-                  SimplifiedValues.lookup(BI->getCondition())) {
+                  SimplifiedToConstantValues.lookup(BI->getCondition())) {
             BasicBlock *Succ = BI->getSuccessor(
                 cast<ConstantInt>(SimpleCond)->isZero() ? 1 : 0);
             if (L->contains(Succ))
@@ -608,7 +615,7 @@
         }
       } else if (SwitchInst *SI = dyn_cast<SwitchInst>(TI)) {
         if (Constant *SimpleCond =
-                SimplifiedValues.lookup(SI->getCondition())) {
+                SimplifiedToConstantValues.lookup(SI->getCondition())) {
           BasicBlock *Succ =
               SI->getSuccessor(cast<ConstantInt>(SimpleCond)->getSExtValue());
           if (L->contains(Succ))
@@ -630,6 +637,31 @@
                    << "  UnrolledCost: " << UnrolledCost << "\n");
       return None;
     }
+
+    for (unsigned Idx = 0; Idx != SimplifiedToConstantOrDeadInsts.size();
+         ++Idx) {
+      Instruction *Root = SimplifiedToConstantOrDeadInsts[Idx];
+      for (auto &Op : Root->operands()) {
+        Instruction *I = dyn_cast<Instruction>(Op);
+        if (!I)
+          continue;
+        if (isa<TerminatorInst>(I) || isa<DbgInfoIntrinsic>(I) ||
+            isa<LandingPadInst>(I) || I->mayHaveSideEffects()) {
+          continue;
+        }
+        if (SimplifiedInsts.count(I))
+          continue;
+        if (std::all_of(I->user_begin(), I->user_end(), [&](User *U) {
+              return SimplifiedToConstantOrDeadInsts.count(
+                  cast<Instruction>(U));
+            })) {
+          DEBUG(dbgs() << "  " << *I
+                       << " would be dead if loop is unrolled.\n");
+          UnrolledCost -= TTI.getUserCost(I);
+          SimplifiedToConstantOrDeadInsts.insert(I);
+        }
+      }
+    }
   }
   DEBUG(dbgs() << "Analysis finished:\n"
                << "UnrolledCost: " << UnrolledCost << ", "
Index: test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll
===================================================================
--- /dev/null
+++ test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll
@@ -0,0 +1,38 @@
+; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-dynamic-cost-savings-discount=1000 -unroll-threshold=10 -unroll-percent-dynamic-cost-saved-threshold=80 | FileCheck %s
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+@known_constant = internal unnamed_addr constant [10 x i32] [i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0, i32 0], align 16
+
+; If a load becomes a constant after loop unrolling, we sometimes can simplify
+; CFG. This test verifies that we handle such cases.
+; After one operand in an instruction is constant-folded and the
+; instruction is simplified, the other operand might become dead.
+; In this test we have::
+; for i in 1..10:
+;   r += A[i] * B[i]
+; A[i] is 0 almost at every iteration, so there is no need in loading B[i] at
+; all.
+
+
+; CHECK-LABEL: @unroll_dce
+; CHECK-NOT:   br i1 %exitcond, label %for.end, label %for.body
+define i32 @unroll_dce(i32* noalias nocapture readonly %b) {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %iv.0 = phi i64 [ 0, %entry ], [ %iv.1, %for.body ]
+  %r.0 = phi i32 [ 0, %entry ], [ %r.1, %for.body ]
+  %arrayidx1 = getelementptr inbounds [10 x i32], [10 x i32]* @known_constant, i64 0, i64 %iv.0
+  %x1 = load i32, i32* %arrayidx1, align 4
+  %arrayidx2 = getelementptr inbounds i32, i32* %b, i64 %iv.0
+  %x2 = load i32, i32* %arrayidx2, align 4
+  %mul = mul i32 %x1, %x2
+  %r.1 = add i32 %mul, %r.0
+  %iv.1 = add nuw nsw i64 %iv.0, 1
+  %exitcond = icmp eq i64 %iv.1, 10
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret i32 %r.1
+}