Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -129,13 +129,17 @@
   /// Try to return an estimate cost factor that can be used as a multiplier
   /// when scalarizing an operation for a vector with ElementCount \p VF.
   /// For scalable vectors this currently takes the most pessimistic view based
-  /// upon the maximum possible value for vscale.
-  unsigned getMaxNumElements(ElementCount VF,
+  /// upon the maximum possible value for vscale, which is determined as follows:
+  ///   1. If the Function \p F contains a vscale_range attribute then we use the
+  ///      max value from that, otherwise
+  ///   2. Use the \p DefaultMaxVscale value passed in by the user, which is 16
+  ///      if unspecified.
+  unsigned getMaxNumElements(ElementCount VF, unsigned DefaultMaxVscale = 16,
                              const Function *F = nullptr) const {
     if (!VF.isScalable())
       return VF.getFixedValue();
 
-    unsigned MaxNumVScale = 16;
+    unsigned MaxNumVScale = DefaultMaxVscale;
     if (F && F->hasFnAttribute(Attribute::VScaleRange)) {
       unsigned VScaleMax =
           F->getFnAttribute(Attribute::VScaleRange).getVScaleRangeArgs().second;
Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -1548,7 +1548,7 @@
   ElementCount LegalVF = LT.second.getVectorElementCount();
   InstructionCost MemOpCost =
       getMemoryOpCost(Opcode, VT->getElementType(), Alignment, 0, CostKind, I);
-  return LT.first * MemOpCost * getMaxNumElements(LegalVF, I->getFunction());
+  return LT.first * MemOpCost * getMaxNumElements(LegalVF, 4, I->getFunction());
 }
 
 bool AArch64TTIImpl::useNeonVector(const Type *Ty) const {
@@ -1973,7 +1973,7 @@
     auto *VTy = cast<ScalableVectorType>(ValTy);
     InstructionCost Cost =
         getArithmeticInstrCost(Opcode, VTy->getScalarType(), CostKind);
-    Cost *= getMaxNumElements(VTy->getElementCount());
+    Cost *= getMaxNumElements(VTy->getElementCount(), 4);
     return Cost;
   }
 
Index: llvm/test/Analysis/CostModel/AArch64/sve-gather.ll
===================================================================
--- llvm/test/Analysis/CostModel/AArch64/sve-gather.ll
+++ llvm/test/Analysis/CostModel/AArch64/sve-gather.ll
@@ -19,14 +19,14 @@
 
 define void @masked_gathers_no_vscale_range() {
 ; CHECK-LABEL: 'masked_gathers_no_vscale_range'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %NXV4F64 = call <vscale x 4 x double> @llvm.masked.gather.nxv4f64.nxv4p0f64(<vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %NXV2F64 = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64.nxv2p0f64(<vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %NXV8F32 = call <vscale x 8 x float> @llvm.masked.gather.nxv8f32.nxv8p0f32(<vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %NXV4F32 = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0f32(<vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %NXV2F32 = call <vscale x 2 x float> @llvm.masked.gather.nxv2f32.nxv2p0f32(<vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %NXV16I16 = call <vscale x 16 x i16> @llvm.masked.gather.nxv16i16.nxv16p0i16(<vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %NXV8I16 = call <vscale x 8 x i16> @llvm.masked.gather.nxv8i16.nxv8p0i16(<vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %NXV4I16 = call <vscale x 4 x i16> @llvm.masked.gather.nxv4i16.nxv4p0i16(<vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NXV4F64 = call <vscale x 4 x double> @llvm.masked.gather.nxv4f64.nxv4p0f64(<vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NXV2F64 = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64.nxv2p0f64(<vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %NXV8F32 = call <vscale x 8 x float> @llvm.masked.gather.nxv8f32.nxv8p0f32(<vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NXV4F32 = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32.nxv4p0f32(<vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NXV2F32 = call <vscale x 2 x float> @llvm.masked.gather.nxv2f32.nxv2p0f32(<vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %NXV16I16 = call <vscale x 16 x i16> @llvm.masked.gather.nxv16i16.nxv16p0i16(<vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %NXV8I16 = call <vscale x 8 x i16> @llvm.masked.gather.nxv8i16.nxv8p0i16(<vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NXV4I16 = call <vscale x 4 x i16> @llvm.masked.gather.nxv4i16.nxv4p0i16(<vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
   %NXV4F64 = call <vscale x 4 x double> @llvm.masked.gather.nxv4f64(<vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef, <vscale x 4 x double> undef)
   %NXV2F64 = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64(<vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
 
Index: llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
===================================================================
--- llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
+++ llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
@@ -80,8 +80,8 @@
 
 define void @strict_fp_reductions(<vscale x 4 x float> %v0, <vscale x 4 x double> %v1) {
 ; CHECK-LABEL: 'strict_fp_reductions'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %fadd_nxv4f32 = call float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %fadd_nxv4f64 = call double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %fadd_nxv4f32 = call float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %fadd_nxv4f64 = call double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %fmul_nxv4f32 = call float @llvm.vector.reduce.fmul.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %fmul_nxv4f64 = call double @llvm.vector.reduce.fmul.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
Index: llvm/test/Analysis/CostModel/AArch64/sve-scatter.ll
===================================================================
--- llvm/test/Analysis/CostModel/AArch64/sve-scatter.ll
+++ llvm/test/Analysis/CostModel/AArch64/sve-scatter.ll
@@ -19,14 +19,14 @@
 
 define void @masked_scatters_no_vscale_range() {
 ; CHECK-LABEL: 'masked_scatters_no_vscale_range'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.nxv4f64.nxv4p0f64(<vscale x 4 x double> undef, <vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.nxv2f64.nxv2p0f64(<vscale x 2 x double> undef, <vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.nxv8f32.nxv8p0f32(<vscale x 8 x float> undef, <vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.nxv4f32.nxv4p0f32(<vscale x 4 x float> undef, <vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.nxv2f32.nxv2p0f32(<vscale x 2 x float> undef, <vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: call void @llvm.masked.scatter.nxv16i16.nxv16p0i16(<vscale x 16 x i16> undef, <vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.nxv8i16.nxv8p0i16(<vscale x 8 x i16> undef, <vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.nxv4i16.nxv4p0i16(<vscale x 4 x i16> undef, <vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv4f64.nxv4p0f64(<vscale x 4 x double> undef, <vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv2f64.nxv2p0f64(<vscale x 2 x double> undef, <vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.nxv8f32.nxv8p0f32(<vscale x 8 x float> undef, <vscale x 8 x float*> undef, i32 1, <vscale x 8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv4f32.nxv4p0f32(<vscale x 4 x float> undef, <vscale x 4 x float*> undef, i32 1, <vscale x 4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.nxv2f32.nxv2p0f32(<vscale x 2 x float> undef, <vscale x 2 x float*> undef, i32 1, <vscale x 2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.nxv16i16.nxv16p0i16(<vscale x 16 x i16> undef, <vscale x 16 x i16*> undef, i32 1, <vscale x 16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.nxv8i16.nxv8p0i16(<vscale x 8 x i16> undef, <vscale x 8 x i16*> undef, i32 1, <vscale x 8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.nxv4i16.nxv4p0i16(<vscale x 4 x i16> undef, <vscale x 4 x i16*> undef, i32 1, <vscale x 4 x i1> undef)
   call void @llvm.masked.scatter.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double*> undef, i32 1, <vscale x 4 x i1> undef)
   call void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double*> undef, i32 1, <vscale x 2 x i1> undef)
 
Index: llvm/test/Transforms/LoopVectorize/AArch64/sve-strict-fadd-cost.ll
===================================================================
--- llvm/test/Transforms/LoopVectorize/AArch64/sve-strict-fadd-cost.ll
+++ llvm/test/Transforms/LoopVectorize/AArch64/sve-strict-fadd-cost.ll
@@ -6,8 +6,8 @@
 
 target triple="aarch64-unknown-linux-gnu"
 
-; CHECK-VF4: Found an estimated cost of 128 for VF vscale x 4 For instruction:   %add = fadd float %0, %sum.07
-; CHECK-VF8: Found an estimated cost of 256 for VF vscale x 8 For instruction:   %add = fadd float %0, %sum.07
+; CHECK-VF4: Found an estimated cost of 32 for VF vscale x 4 For instruction:   %add = fadd float %0, %sum.07
+; CHECK-VF8: Found an estimated cost of 64 for VF vscale x 8 For instruction:   %add = fadd float %0, %sum.07
 
 define float @fadd_strict32(float* noalias nocapture readonly %a, i64 %n) #0 {
 entry:
@@ -28,8 +28,8 @@
 }
 
 
-; CHECK-VF4: Found an estimated cost of 128 for VF vscale x 4 For instruction:   %add = fadd double %0, %sum.07
-; CHECK-VF8: Found an estimated cost of 256 for VF vscale x 8 For instruction:   %add = fadd double %0, %sum.07
+; CHECK-VF4: Found an estimated cost of 32 for VF vscale x 4 For instruction:   %add = fadd double %0, %sum.07
+; CHECK-VF8: Found an estimated cost of 64 for VF vscale x 8 For instruction:   %add = fadd double %0, %sum.07
 
 define double @fadd_strict64(double* noalias nocapture readonly %a, i64 %n) #0 {
 entry: