Index: lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- lib/Transforms/Vectorize/LoopVectorize.cpp
+++ lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -7155,7 +7155,7 @@
   unsigned C = getInstructionCost(I, VF, VectorTy);
 
   bool TypeNotScalarized =
-      VF > 1 && !VectorTy->isVoidTy() && TTI.getNumberOfParts(VectorTy) < VF;
+      VF > 1 && VectorTy->isVectorTy() && TTI.getNumberOfParts(VectorTy) < VF;
   return VectorizationCostTy(C, TypeNotScalarized);
 }
 
@@ -7238,7 +7238,7 @@
   Type *RetTy = I->getType();
   if (canTruncateToMinimalBitwidth(I, VF))
     RetTy = IntegerType::get(RetTy->getContext(), MinBWs[I]);
-  VectorTy = ToVectorTy(RetTy, VF);
+  VectorTy = isScalarAfterVectorization(I, VF) ? RetTy : ToVectorTy(RetTy, VF);
   auto SE = PSE.getSE();
 
   // TODO: We need to estimate the cost of intrinsic calls.
@@ -7371,9 +7371,10 @@
     } else if (Legal->isUniform(Op2)) {
       Op2VK = TargetTransformInfo::OK_UniformValue;
     }
-    SmallVector<const Value *, 4> Operands(I->operand_values()); 
-    return TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK,
-                                      Op2VK, Op1VP, Op2VP, Operands);
+    SmallVector<const Value *, 4> Operands(I->operand_values());
+    unsigned N = isScalarAfterVectorization(I, VF) ? VF : 1;
+    return N * TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK,
+                                          Op2VK, Op1VP, Op2VP, Operands);
   }
   case Instruction::Select: {
     SelectInst *SI = cast<SelectInst>(I);
@@ -7396,7 +7397,15 @@
   }
   case Instruction::Store:
   case Instruction::Load: {
-    VectorTy = ToVectorTy(getMemInstValueType(I), VF);
+    unsigned Width = VF;
+    if (Width > 1) {
+      InstWidening Decision = getWideningDecision(I, Width);
+      assert(Decision != CM_Unknown &&
+             "CM decision should be taken at this point");
+      if (Decision == CM_Scalarize)
+        Width = 1;
+    }
+    VectorTy = ToVectorTy(getMemInstValueType(I), Width);
     return getMemoryInstructionCost(I, VF);
   }
   case Instruction::ZExt:
Index: test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll
===================================================================
--- /dev/null
+++ test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll
@@ -0,0 +1,26 @@
+; REQUIRES: asserts
+; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -S --debug-only=loop-vectorize 2>&1 | FileCheck %s
+
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64--linux-gnu"
+
+; CHECK-LABEL: all_scalar
+; CHECK:       LV: Found scalar instruction: %i.next = add nuw nsw i64 %i, 2
+; CHECK:       LV: Found an estimated cost of 2 for VF 2 For instruction: %i.next = add nuw nsw i64 %i, 2
+; CHECK:       LV: Not considering vector loop of width 2 because it will not generate any vector instructions
+;
+define void @all_scalar(i64* %a, i64 %n) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
+  %tmp0 = getelementptr i64, i64* %a, i64 %i
+  store i64 0, i64* %tmp0, align 1
+  %i.next = add nuw nsw i64 %i, 2
+  %cond = icmp eq i64 %i.next, %n
+  br i1 %cond, label %for.end, label %for.body
+
+for.end:
+  ret void
+}