Index: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -1334,6 +1334,10 @@
     return ScalarsPerVF->second.count(I);
   }
 
+#ifndef NDEBUG
+  bool hasSingleCopyAfterVectorization(Instruction *I, ElementCount VF);
+#endif
+
   /// \returns True if instruction \p I can be truncated to a smaller bitwidth
   /// for vectorization factor \p VF.
   bool canTruncateToMinimalBitwidth(Instruction *I, ElementCount VF) const {
@@ -7235,16 +7239,44 @@
   }
 }
 
+#ifndef NDEBUG
+bool LoopVectorizationCostModel::hasSingleCopyAfterVectorization(
+    Instruction *I, ElementCount VF) {
+  if (VF.isVector()) {
+    auto Scalarized = InstsToScalarize.find(VF);
+    assert(Scalarized != InstsToScalarize.end() &&
+           "VF not yet analyzed for scalarization profitability");
+    return !Scalarized->second.count(I) &&
+           llvm::all_of(I->users(), [&](User *U) {
+             auto *UI = cast<Instruction>(U);
+             return !Scalarized->second.count(UI);
+           });
+  }
+  return true;
+}
+#endif
+
 InstructionCost
 LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
                                                Type *&VectorTy) {
   Type *RetTy = I->getType();
   if (canTruncateToMinimalBitwidth(I, VF))
     RetTy = IntegerType::get(RetTy->getContext(), MinBWs[I]);
-  VectorTy = isScalarAfterVectorization(I, VF) ? RetTy : ToVectorTy(RetTy, VF);
   auto SE = PSE.getSE();
   TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
 
+  if (isScalarAfterVectorization(I, VF)) {
+    VectorTy = RetTy;
+    // With the exception of GEPs, after scalarization there should only be one
+    // copy of the instruction generated in the loop. This is because the VF is
+    // either 1, or any instructions that need scalarizing have already been
+    // dealt with by the the time we get here. As a result, it means we don't
+    // have to multiply the instruction cost by VF.
+    assert(I->getOpcode() == Instruction::GetElementPtr ||
+           hasSingleCopyAfterVectorization(I, VF));
+  } else
+    VectorTy = ToVectorTy(RetTy, VF);
+
   // TODO: We need to estimate the cost of intrinsic calls.
   switch (I->getOpcode()) {
   case Instruction::GetElementPtr:
@@ -7372,21 +7404,16 @@
       Op2VK = TargetTransformInfo::OK_UniformValue;
 
     SmallVector<const Value *, 4> Operands(I->operand_values());
-    unsigned N = isScalarAfterVectorization(I, VF) ? VF.getKnownMinValue() : 1;
-    return N * TTI.getArithmeticInstrCost(
-                   I->getOpcode(), VectorTy, CostKind,
-                   TargetTransformInfo::OK_AnyValue,
-                   Op2VK, TargetTransformInfo::OP_None, Op2VP, Operands, I);
+    return TTI.getArithmeticInstrCost(
+        I->getOpcode(), VectorTy, CostKind, TargetTransformInfo::OK_AnyValue,
+        Op2VK, TargetTransformInfo::OP_None, Op2VP, Operands, I);
   }
   case Instruction::FNeg: {
     assert(!VF.isScalable() && "VF is assumed to be non scalable.");
-    unsigned N = isScalarAfterVectorization(I, VF) ? VF.getKnownMinValue() : 1;
-    return N * TTI.getArithmeticInstrCost(
-                   I->getOpcode(), VectorTy, CostKind,
-                   TargetTransformInfo::OK_AnyValue,
-                   TargetTransformInfo::OK_AnyValue,
-                   TargetTransformInfo::OP_None, TargetTransformInfo::OP_None,
-                   I->getOperand(0), I);
+    return TTI.getArithmeticInstrCost(
+        I->getOpcode(), VectorTy, CostKind, TargetTransformInfo::OK_AnyValue,
+        TargetTransformInfo::OK_AnyValue, TargetTransformInfo::OP_None,
+        TargetTransformInfo::OP_None, I->getOperand(0), I);
   }
   case Instruction::Select: {
     SelectInst *SI = cast<SelectInst>(I);
@@ -7510,14 +7537,7 @@
       }
     }
 
-    unsigned N;
-    if (isScalarAfterVectorization(I, VF)) {
-      assert(!VF.isScalable() && "VF is assumed to be non scalable");
-      N = VF.getKnownMinValue();
-    } else
-      N = 1;
-    return N *
-           TTI.getCastInstrCost(Opcode, VectorTy, SrcVecTy, CCH, CostKind, I);
+    return TTI.getCastInstrCost(Opcode, VectorTy, SrcVecTy, CCH, CostKind, I);
   }
   case Instruction::Call: {
     bool NeedToScalarize;
@@ -7534,8 +7554,8 @@
   default:
     // The cost of executing VF copies of the scalar instruction. This opcode
     // is unknown. Assume that it is the same as 'mul'.
-    return VF.getKnownMinValue() * TTI.getArithmeticInstrCost(
-                                       Instruction::Mul, VectorTy, CostKind) +
+    return VF.getFixedValue() * TTI.getArithmeticInstrCost(Instruction::Mul,
+                                                           VectorTy, CostKind) +
            getScalarizationOverhead(I, VF);
   } // end of switch.
 }
Index: llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll
===================================================================
--- llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll
+++ llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll
@@ -6,7 +6,7 @@
 
 ; 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: Found an estimated cost of 1 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) {