Index: lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- lib/Transforms/Vectorize/LoopVectorize.cpp
+++ lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -5023,10 +5023,11 @@
   LLVM_DEBUG(dbgs() << "LV: Scalar loop costs: " << (int)ScalarCost << ".\n");
 
   bool ForceVectorization = Hints->getForce() == LoopVectorizeHints::FK_Enabled;
-  // Ignore scalar width, because the user explicitly wants vectorization.
   if (ForceVectorization && MaxVF > 1) {
-    Width = 2;
-    Cost = expectedCost(Width).first / (float)Width;
+    // Ignore scalar width, because the user explicitly wants vectorization.
+    // Initialize cost to max so that VF = 2 is, at least, chosen during cost
+    // evaluation.
+    Cost = std::numeric_limits<float>::max();
   }
 
   for (unsigned i = 2; i <= MaxVF; i *= 2) {
Index: test/Transforms/LoopVectorize/redundant-vf2-cost.ll
===================================================================
--- test/Transforms/LoopVectorize/redundant-vf2-cost.ll
+++ test/Transforms/LoopVectorize/redundant-vf2-cost.ll
@@ -0,0 +1,34 @@
+; RUN: opt < %s -loop-vectorize -mtriple x86_64 -debug -disable-output 2>&1 | FileCheck %s
+; REQUIRES: asserts
+
+; Check that cost model is not executed twice for VF=2 when vectorization is
+; forced for a particular loop.
+
+; CHECK: LV: Found an estimated cost of {{[0-9]+}} for VF 2 For instruction:   %{{[0-9]+}} = load i32
+; CHECK: LV: Found an estimated cost of {{[0-9]+}} for VF 2 For instruction:   store i32
+; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF 2 For instruction:   %{{[0-9]+}} = load i32
+; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF 2 For instruction:   store i32
+; CHECK: LV: Vector loop of width 2 costs: {{[0-9]+}}.
+
+define i32 @foo(i32* %A, i32 %n) {
+entry:
+  %cmp3.i = icmp eq i32 %n, 0
+  br i1 %cmp3.i, label %exit, label %for.body.i
+
+for.body.i:
+  %iv = phi i32 [ %add.i, %for.body.i ], [ 0, %entry ]
+  %ld_addr = getelementptr inbounds i32, i32* %A, i32 %iv
+  %0 = load i32, i32* %ld_addr, align 4
+  %val = add i32 %0, 1
+  store i32 %val, i32* %ld_addr, align 4
+  %add.i = add nsw i32 %iv, 1
+  %cmp.i = icmp eq i32 %add.i, %n
+  br i1 %cmp.i, label %exit, label %for.body.i, !llvm.loop !0
+
+exit:
+  %__init.addr.0.lcssa.i = phi i32 [ 0, %entry ], [ %add.i, %for.body.i ]
+  ret i32 %__init.addr.0.lcssa.i
+}
+
+!0 = !{!0, !1}
+!1 = !{!"llvm.loop.vectorize.enable", i1 true}