diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.h b/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
@@ -202,6 +202,9 @@
                                  bool UseMaskForCond = false,
                                  bool UseMaskForGaps = false);
 
+  unsigned getGatherScatterOpCost(unsigned Opcode, Type *DataTy, Value *Ptr,
+                                  bool VariableMask, unsigned Alignment);
+
   bool isLoweredToCall(const Function *F);
   bool isHardwareLoopProfitable(Loop *L, ScalarEvolution &SE,
                                 AssumptionCache &AC,
diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -860,6 +860,67 @@
                                            UseMaskForCond, UseMaskForGaps);
 }
 
+unsigned ARMTTIImpl::getGatherScatterOpCost(unsigned Opcode, Type *DataTy,
+                                            Value *Ptr, bool VariableMask,
+                                            unsigned Alignment) {
+  if (!ST->hasMVEIntegerOps() || !EnableMaskedGatherScatters)
+    return BaseT::getGatherScatterOpCost(Opcode, DataTy, Ptr, VariableMask,
+                                         Alignment);
+
+  assert(DataTy->isVectorTy() && "Can't do gather/scatters on scalar!");
+  VectorType *VTy = cast<VectorType>(DataTy);
+
+  // TODO: Splitting, once we do that.
+  // TODO: trunc/sext/zext the result/input
+
+  unsigned NumElems = VTy->getNumElements();
+  unsigned EltSize = VTy->getScalarSizeInBits();
+  std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, DataTy);
+
+  // For now, it is assumed that for the MVE gather instructions the loads are
+  // all effectively serialised. This means the cost is the scalar cost
+  // multiplied by the number of elements being loaded. This is possibly very
+  // conservative, but even so we still end up vectorising loops because the
+  // cost per iteration for many loops is lower than for scalar loops.
+  unsigned VectorCost = NumElems * LT.first;
+  // The scalarization cost should be a lot higher. We use the number of vector
+  // elements plus the scalarization overhead.
+  unsigned ScalarCost =
+      NumElems * LT.first + BaseT::getScalarizationOverhead(DataTy, {});
+
+  // TODO: Cost extended gathers or trunc stores correctly.
+  if (EltSize * NumElems != 128 || NumElems < 4)
+    return ScalarCost;
+  if (Alignment < EltSize / 8)
+    return ScalarCost;
+
+  // Any (aligned) i32 gather will not need to be scalarised.
+  if (EltSize == 32)
+    return VectorCost;
+  // For smaller types, we need to ensure that the gep's inputs are correctly
+  // extended from a small enough value. Other size (including i64) are
+  // scalarized for now.
+  if (EltSize != 8 && EltSize != 16)
+    return ScalarCost;
+
+  if (auto BC = dyn_cast<BitCastInst>(Ptr))
+    Ptr = BC->getOperand(0);
+  if (auto *GEP = dyn_cast<GetElementPtrInst>(Ptr)) {
+    if (GEP->getNumOperands() != 2)
+      return ScalarCost;
+    unsigned Scale = DL.getTypeAllocSize(GEP->getResultElementType());
+    // Scale needs to be correct (which is only relevant for i16s).
+    if (Scale != 1 && Scale * 8 != EltSize)
+      return ScalarCost;
+    // And we need to zext (not sext) the indexes from a small enough type.
+    if (auto ZExt = dyn_cast<ZExtInst>(GEP->getOperand(1)))
+      if (ZExt->getOperand(0)->getType()->getScalarSizeInBits() <= EltSize)
+        return VectorCost;
+    return ScalarCost;
+  }
+  return ScalarCost;
+}
+
 bool ARMTTIImpl::isLoweredToCall(const Function *F) {
   if (!F->isIntrinsic())
     BaseT::isLoweredToCall(F);
diff --git a/llvm/test/Analysis/CostModel/ARM/mve-gather-scatter-cost.ll b/llvm/test/Analysis/CostModel/ARM/mve-gather-scatter-cost.ll
--- a/llvm/test/Analysis/CostModel/ARM/mve-gather-scatter-cost.ll
+++ b/llvm/test/Analysis/CostModel/ARM/mve-gather-scatter-cost.ll
@@ -3,31 +3,31 @@
 
 define i32 @masked_gather() {
 ; CHECK-LABEL: 'masked_gather'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 4, <4 x i1> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 4, <2 x i1> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 4, <16 x i1> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 4, <8 x i1> undef, <8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 4, <4 x i1> undef, <4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 4, <2 x i1> undef, <2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F16 = call <16 x half> @llvm.masked.gather.v16f16.v16p0f16(<16 x half*> undef, i32 2, <16 x i1> undef, <16 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> undef, i32 2, <8 x i1> undef, <8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = call <4 x half> @llvm.masked.gather.v4f16.v4p0f16(<4 x half*> undef, i32 2, <4 x i1> undef, <4 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = call <2 x half> @llvm.masked.gather.v2f16.v2p0f16(<2 x half*> undef, i32 2, <2 x i1> undef, <2 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 4, <4 x i1> undef, <4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 4, <2 x i1> undef, <2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 4, <16 x i1> undef, <16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 4, <8 x i1> undef, <8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 4, <4 x i1> undef, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 4, <2 x i1> undef, <2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 2, <16 x i1> undef, <16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 2, <8 x i1> undef, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 2, <4 x i1> undef, <4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I16 = call <2 x i16> @llvm.masked.gather.v2i16.v2p0i16(<2 x i16*> undef, i32 2, <2 x i1> undef, <2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I8 = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> undef, i32 1, <4 x i1> undef, <4 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I8 = call <2 x i8> @llvm.masked.gather.v2i8.v2p0i8(<2 x i8*> undef, i32 1, <2 x i1> undef, <2 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 4, <4 x i1> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 4, <2 x i1> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 4, <16 x i1> undef, <16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 4, <8 x i1> undef, <8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 4, <4 x i1> undef, <4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 4, <2 x i1> undef, <2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: %V16F16 = call <16 x half> @llvm.masked.gather.v16f16.v16p0f16(<16 x half*> undef, i32 2, <16 x i1> undef, <16 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V8F16 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> undef, i32 2, <8 x i1> undef, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V4F16 = call <4 x half> @llvm.masked.gather.v4f16.v4p0f16(<4 x half*> undef, i32 2, <4 x i1> undef, <4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2F16 = call <2 x half> @llvm.masked.gather.v2f16.v2p0f16(<2 x half*> undef, i32 2, <2 x i1> undef, <2 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 4, <4 x i1> undef, <4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 4, <2 x i1> undef, <2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 4, <16 x i1> undef, <16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 4, <8 x i1> undef, <8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 4, <4 x i1> undef, <4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 4, <2 x i1> undef, <2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 2, <16 x i1> undef, <16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 2, <8 x i1> undef, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 2, <4 x i1> undef, <4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2I16 = call <2 x i16> @llvm.masked.gather.v2i16.v2p0i16(<2 x i16*> undef, i32 2, <2 x i1> undef, <2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2112 for instruction: %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V4I8 = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> undef, i32 1, <4 x i1> undef, <4 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2I8 = call <2 x i8> @llvm.masked.gather.v2i8.v2p0i8(<2 x i8*> undef, i32 1, <2 x i1> undef, <2 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
   %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 4, <4 x i1> undef, <4 x double> undef)
@@ -67,31 +67,31 @@
 
 define i32 @masked_scatter() {
 ; CHECK-LABEL: 'masked_scatter'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 4, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 4, <2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 4, <16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 4, <8 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 4, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 4, <2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v16f16.v16p0f16(<16 x half> undef, <16 x half*> undef, i32 2, <16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> undef, <8 x half*> undef, i32 2, <8 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4f16.v4p0f16(<4 x half> undef, <4 x half*> undef, i32 2, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v2f16.v2p0f16(<2 x half> undef, <2 x half*> undef, i32 2, <2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 4, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 4, <2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 4, <16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 4, <8 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 4, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 4, <2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 2, <16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 2, <8 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 2, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v2i16.v2p0i16(<2 x i16> undef, <2 x i16*> undef, i32 2, <2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> undef, <4 x i8*> undef, i32 1, <4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v2i8.v2p0i8(<2 x i8> undef, <2 x i8*> undef, i32 1, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 4, <4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 4, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 4, <16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 4, <8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 4, <4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 4, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: call void @llvm.masked.scatter.v16f16.v16p0f16(<16 x half> undef, <16 x half*> undef, i32 2, <16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> undef, <8 x half*> undef, i32 2, <8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4f16.v4p0f16(<4 x half> undef, <4 x half*> undef, i32 2, <4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2f16.v2p0f16(<2 x half> undef, <2 x half*> undef, i32 2, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 4, <4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 4, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 576 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 4, <16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 4, <8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 4, <4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 4, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 544 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 2, <16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 2, <8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 2, <4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2i16.v2p0i16(<2 x i16> undef, <2 x i16*> undef, i32 2, <2 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2112 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> undef, <4 x i8*> undef, i32 1, <4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v2i8.v2p0i8(<2 x i8> undef, <2 x i8*> undef, i32 1, <2 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
   call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 4, <4 x i1> undef)
@@ -132,27 +132,27 @@
 define void @gep_v4i32(i32* %base, i16* %base16, i8* %base8, <4 x i32> %ind32, <4 x i16> %ind16, <4 x i1> %mask)  {
 ; CHECK-LABEL: 'gep_v4i32'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep1 = getelementptr i32, i32* %base, <4 x i32> %ind32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res1 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gep1, i32 4, <4 x i1> %mask, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %res1, <4 x i32*> %gep1, i32 4, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res1 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gep1, i32 4, <4 x i1> %mask, <4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %res1, <4 x i32*> %gep1, i32 4, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indzext = zext <4 x i16> %ind16 to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep2 = getelementptr i32, i32* %base, <4 x i32> %indzext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res2 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gep2, i32 4, <4 x i1> %mask, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %res2, <4 x i32*> %gep2, i32 4, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res2 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gep2, i32 4, <4 x i1> %mask, <4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %res2, <4 x i32*> %gep2, i32 4, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indsext = sext <4 x i16> %ind16 to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep3 = getelementptr i32, i32* %base, <4 x i32> %indsext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res3 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gep3, i32 4, <4 x i1> %mask, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %res3, <4 x i32*> %gep3, i32 4, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res3 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gep3, i32 4, <4 x i1> %mask, <4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %res3, <4 x i32*> %gep3, i32 4, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepu = getelementptr i32, i32* %base, <4 x i32> %ind32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resu = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gepu, i32 1, <4 x i1> %mask, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %resu, <4 x i32*> %gepu, i32 1, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %resu = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gepu, i32 1, <4 x i1> %mask, <4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %resu, <4 x i32*> %gepu, i32 1, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepos = getelementptr i8, i8* %base8, <4 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %geposb = bitcast <4 x i8*> %gepos to <4 x i32*>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resos = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %geposb, i32 4, <4 x i1> %mask, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %resos, <4 x i32*> %geposb, i32 4, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %resos = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %geposb, i32 4, <4 x i1> %mask, <4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %resos, <4 x i32*> %geposb, i32 4, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i16, i16* %base16, <4 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <4 x i16*> %gepbs to <4 x i32*>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resbs = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gepbsb, i32 4, <4 x i1> %mask, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %resbs, <4 x i32*> %gepbsb, i32 4, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %resbs = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gepbsb, i32 4, <4 x i1> %mask, <4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %resbs, <4 x i32*> %gepbsb, i32 4, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %gep1 = getelementptr i32, i32* %base, <4 x i32> %ind32
@@ -191,27 +191,27 @@
 define void @gep_v4f32(float* %base, i16* %base16, i8* %base8, <4 x i32> %ind32, <4 x i16> %ind16, <4 x i1> %mask)  {
 ; CHECK-LABEL: 'gep_v4f32'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep1 = getelementptr float, float* %base, <4 x i32> %ind32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res1 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep1, i32 4, <4 x i1> %mask, <4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res1, <4 x float*> %gep1, i32 4, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res1 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep1, i32 4, <4 x i1> %mask, <4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res1, <4 x float*> %gep1, i32 4, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indzext = zext <4 x i16> %ind16 to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep2 = getelementptr float, float* %base, <4 x i32> %indzext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res2 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep2, i32 4, <4 x i1> %mask, <4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res2, <4 x float*> %gep2, i32 4, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res2 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep2, i32 4, <4 x i1> %mask, <4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res2, <4 x float*> %gep2, i32 4, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indsext = sext <4 x i16> %ind16 to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep3 = getelementptr float, float* %base, <4 x i32> %indsext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res3 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep3, i32 4, <4 x i1> %mask, <4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res3, <4 x float*> %gep3, i32 4, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res3 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep3, i32 4, <4 x i1> %mask, <4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res3, <4 x float*> %gep3, i32 4, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gepu = getelementptr float, float* %base, <4 x i32> %ind32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resu = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gepu, i32 1, <4 x i1> %mask, <4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resu, <4 x float*> %gepu, i32 1, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %resu = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gepu, i32 1, <4 x i1> %mask, <4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resu, <4 x float*> %gepu, i32 1, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepos = getelementptr i8, i8* %base8, <4 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %geposb = bitcast <4 x i8*> %gepos to <4 x float*>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resos = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %geposb, i32 4, <4 x i1> %mask, <4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resos, <4 x float*> %geposb, i32 4, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %resos = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %geposb, i32 4, <4 x i1> %mask, <4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resos, <4 x float*> %geposb, i32 4, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i16, i16* %base16, <4 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <4 x i16*> %gepbs to <4 x float*>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resbs = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gepbsb, i32 4, <4 x i1> %mask, <4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resbs, <4 x float*> %gepbsb, i32 4, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %resbs = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gepbsb, i32 4, <4 x i1> %mask, <4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resbs, <4 x float*> %gepbsb, i32 4, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %gep1 = getelementptr float, float* %base, <4 x i32> %ind32
@@ -250,16 +250,16 @@
 define void @gep_v4i16(i16* %base, <4 x i32> %ind32, <4 x i16> %ind16, <4 x i1> %mask)  {
 ; CHECK-LABEL: 'gep_v4i16'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep1 = getelementptr i16, i16* %base, <4 x i32> %ind32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res1 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep1, i32 2, <4 x i1> %mask, <4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res1, <4 x i16*> %gep1, i32 2, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %res1 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep1, i32 2, <4 x i1> %mask, <4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res1, <4 x i16*> %gep1, i32 2, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indzext = zext <4 x i16> %ind16 to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep2 = getelementptr i16, i16* %base, <4 x i32> %indzext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res2 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep2, i32 2, <4 x i1> %mask, <4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res2, <4 x i16*> %gep2, i32 2, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %res2 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep2, i32 2, <4 x i1> %mask, <4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res2, <4 x i16*> %gep2, i32 2, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indsext = sext <4 x i16> %ind16 to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep3 = getelementptr i16, i16* %base, <4 x i32> %indsext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res3 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep3, i32 2, <4 x i1> %mask, <4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res3, <4 x i16*> %gep3, i32 2, <4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %res3 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep3, i32 2, <4 x i1> %mask, <4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res3, <4 x i16*> %gep3, i32 2, <4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %gep1 = getelementptr i16, i16* %base, <4 x i32> %ind32
@@ -281,26 +281,26 @@
 define void @gep_v8i16(i16* %base, i8* %base8, i32* %base32, <8 x i32> %ind32, <8 x i16> %ind16, <8 x i1> %mask)  {
 ; CHECK-LABEL: 'gep_v8i16'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep1 = getelementptr i16, i16* %base, <8 x i32> %ind32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res1 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep1, i32 2, <8 x i1> %mask, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res1, <8 x i16*> %gep1, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %res1 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep1, i32 2, <8 x i1> %mask, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res1, <8 x i16*> %gep1, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indzext = zext <8 x i16> %ind16 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep2 = getelementptr i16, i16* %base, <8 x i32> %indzext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res2 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep2, i32 2, <8 x i1> %mask, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res2, <8 x i16*> %gep2, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res2 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep2, i32 2, <8 x i1> %mask, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res2, <8 x i16*> %gep2, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indsext = sext <8 x i16> %ind16 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep3 = getelementptr i16, i16* %base, <8 x i32> %indsext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res3 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep3, i32 2, <8 x i1> %mask, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res3, <8 x i16*> %gep3, i32 2, <8 x i1> %mask)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resu = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep2, i32 1, <8 x i1> %mask, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resu, <8 x i16*> %gep2, i32 1, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %res3 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep3, i32 2, <8 x i1> %mask, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res3, <8 x i16*> %gep3, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %resu = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep2, i32 1, <8 x i1> %mask, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resu, <8 x i16*> %gep2, i32 1, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepos = getelementptr i8, i8* %base8, <8 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %geposb = bitcast <8 x i8*> %gepos to <8 x i16*>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resos = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %geposb, i32 2, <8 x i1> %mask, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resos, <8 x i16*> %geposb, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %resos = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %geposb, i32 2, <8 x i1> %mask, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resos, <8 x i16*> %geposb, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i32, i32* %base32, <8 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <8 x i32*> %gepbs to <8 x i16*>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resbs = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gepbsb, i32 2, <8 x i1> %mask, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resbs, <8 x i16*> %gepbsb, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %resbs = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gepbsb, i32 2, <8 x i1> %mask, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resbs, <8 x i16*> %gepbsb, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %gep1 = getelementptr i16, i16* %base, <8 x i32> %ind32
@@ -338,26 +338,26 @@
 define void @gep_v8f16(half* %base, i8* %base8, i32* %base32, <8 x i32> %ind32, <8 x i16> %ind16, <8 x i1> %mask)  {
 ; CHECK-LABEL: 'gep_v8f16'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep1 = getelementptr half, half* %base, <8 x i32> %ind32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res1 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep1, i32 2, <8 x i1> %mask, <8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res1, <8 x half*> %gep1, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %res1 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep1, i32 2, <8 x i1> %mask, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res1, <8 x half*> %gep1, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indzext = zext <8 x i16> %ind16 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep2 = getelementptr half, half* %base, <8 x i32> %indzext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res2 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep2, i32 2, <8 x i1> %mask, <8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res2, <8 x half*> %gep2, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res2 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep2, i32 2, <8 x i1> %mask, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res2, <8 x half*> %gep2, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indsext = sext <8 x i16> %ind16 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep3 = getelementptr half, half* %base, <8 x i32> %indsext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res3 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep3, i32 2, <8 x i1> %mask, <8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res3, <8 x half*> %gep3, i32 2, <8 x i1> %mask)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resu = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep2, i32 1, <8 x i1> %mask, <8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resu, <8 x half*> %gep2, i32 1, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %res3 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep3, i32 2, <8 x i1> %mask, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res3, <8 x half*> %gep3, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %resu = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep2, i32 1, <8 x i1> %mask, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resu, <8 x half*> %gep2, i32 1, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepos = getelementptr i8, i8* %base8, <8 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %geposb = bitcast <8 x i8*> %gepos to <8 x half*>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resos = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %geposb, i32 2, <8 x i1> %mask, <8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resos, <8 x half*> %geposb, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %resos = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %geposb, i32 2, <8 x i1> %mask, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resos, <8 x half*> %geposb, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i32, i32* %base32, <8 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <8 x i32*> %gepbs to <8 x half*>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resbs = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gepbsb, i32 2, <8 x i1> %mask, <8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resbs, <8 x half*> %gepbsb, i32 2, <8 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %resbs = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gepbsb, i32 2, <8 x i1> %mask, <8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resbs, <8 x half*> %gepbsb, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %gep1 = getelementptr half, half* %base, <8 x i32> %ind32
@@ -395,20 +395,20 @@
 define void @gep_v16i8(i8* %base, i16* %base16, <16 x i8> %ind8, <16 x i32> %ind32, <16 x i1> %mask)  {
 ; CHECK-LABEL: 'gep_v16i8'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep1 = getelementptr i8, i8* %base, <16 x i32> %ind32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res1 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep1, i32 1, <16 x i1> %mask, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res1, <16 x i8*> %gep1, i32 2, <16 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %res1 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep1, i32 1, <16 x i1> %mask, <16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res1, <16 x i8*> %gep1, i32 2, <16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %indzext = zext <16 x i8> %ind8 to <16 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep2 = getelementptr i8, i8* %base, <16 x i32> %indzext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res2 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep2, i32 2, <16 x i1> %mask, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res2, <16 x i8*> %gep2, i32 2, <16 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res2 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep2, i32 2, <16 x i1> %mask, <16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res2, <16 x i8*> %gep2, i32 2, <16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %indsext = sext <16 x i8> %ind8 to <16 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep3 = getelementptr i8, i8* %base, <16 x i32> %indsext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res3 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep3, i32 2, <16 x i1> %mask, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res3, <16 x i8*> %gep3, i32 2, <16 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %res3 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep3, i32 2, <16 x i1> %mask, <16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res3, <16 x i8*> %gep3, i32 2, <16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i16, i16* %base16, <16 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <16 x i16*> %gepbs to <16 x i8*>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbsb, i32 2, <16 x i1> %mask, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbsb, i32 2, <16 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbsb, i32 2, <16 x i1> %mask, <16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbsb, i32 2, <16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %gep1 = getelementptr i8, i8* %base, <16 x i32> %ind32
@@ -433,6 +433,19 @@
   ret void
 }
 
+define void @gep_v16i8p(<16 x i8*> %base, i32 %off, <16 x i1> %mask)  {
+; CHECK-LABEL: 'gep_v16i8p'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i8, <16 x i8*> %base, i32 %off
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbs, i32 2, <16 x i1> %mask, <16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbs, i32 2, <16 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %gepbs = getelementptr i8, <16 x i8*> %base, i32 %off
+  %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbs, i32 2, <16 x i1> %mask, <16 x i8> undef)
+  call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbs, i32 2, <16 x i1> %mask)
+  ret void
+}
+
 declare <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*>, i32, <4 x i1>, <4 x double>)
 declare <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*>, i32, <2 x i1>, <2 x double>)