[X86][Costmodel] Fix `X86TTIImpl::getGSScalarCost()`

[lebedev.ri]

Summary

X86TTIImpl::getGSScalarCost() has (at least) two issues:

• it naively computes the cost of sequence of insertelement/extractelement. If we are operating not on the XMM (but YMM/ZMM), this widely overestimates the cost of subvector insertions/extractions.
• Gather/scatter takes a vector of pointers, and scalarization results in us performing scalar memory operation for each of these pointers, but we never account for the cost of extracting these pointers out of the vector of pointers.

[lebedev.ri]

Rebased, NFC.

[lebedev.ri]

Note that even with the proper LV fix (D111460), we still want this fix too.

[RKSimon]

LGTM

[lebedev.ri]

In D111222#3062385, @RKSimon wrote:

LGTM

Thank you for the review!
I'm going to land this, all these patches probably conflict with eachother..

[RKSimon]

Do you think we should add gather/scatter test coverage for x86 triples with 32-bit pointers (i686 or gnux32 ?)

[lebedev.ri]

In D111222#3062480, @RKSimon wrote:

Do you think we should add gather/scatter test coverage for x86 triples with 32-bit pointers (i686 or gnux32 ?)

Does anyone actually care about 32-bit performance, especially vectorized?
We could extract gather/scatter coverage out of llvm/test/Analysis/CostModel/X86/masked-intrinsic-cost.ll into a new file and either duplicate it or just duplicate runlines i suppose.

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

 /// VariableMask - The mask is non-constant at compile time.
 /// Alignment - Alignment for one element.
 /// AddressSpace - pointer[s] address space.
 ///
 /// FIXME: Add TargetCostKind support.
 InstructionCost X86TTIImpl::getGSScalarCost(unsigned Opcode, Type *SrcVTy,
                                             bool VariableMask, Align Alignment,
                                             unsigned AddressSpace) {
+  Type *ScalarTy = SrcVTy->getScalarType();
   unsigned VF = cast<FixedVectorType>(SrcVTy)->getNumElements();
   APInt DemandedElts = APInt::getAllOnes(VF);
   TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
 
   InstructionCost MaskUnpackCost = 0;
   if (VariableMask) {
     auto *MaskTy =
         FixedVectorType::get(Type::getInt1Ty(SrcVTy->getContext()), VF);
-    MaskUnpackCost =
-        getScalarizationOverhead(MaskTy, DemandedElts, false, true);
+    MaskUnpackCost = getScalarizationOverhead(
+        MaskTy, DemandedElts, /*Insert=*/false, /*Extract=*/true);
     InstructionCost ScalarCompareCost = getCmpSelInstrCost(
         Instruction::ICmp, Type::getInt1Ty(SrcVTy->getContext()), nullptr,
         CmpInst::BAD_ICMP_PREDICATE, CostKind);
     InstructionCost BranchCost = getCFInstrCost(Instruction::Br, CostKind);
     MaskUnpackCost += VF * (BranchCost + ScalarCompareCost);
   }
 
+  InstructionCost AddressUnpackCost = getScalarizationOverhead(
+      FixedVectorType::get(ScalarTy->getPointerTo(), VF), DemandedElts,
+      /*Insert=*/false, /*Extract=*/true);
+
   // The cost of the scalar loads/stores.
   InstructionCost MemoryOpCost =
-      VF * getMemoryOpCost(Opcode, SrcVTy->getScalarType(),
-                           MaybeAlign(Alignment), AddressSpace, CostKind);
+      VF * getMemoryOpCost(Opcode, ScalarTy, MaybeAlign(Alignment),
+                           AddressSpace, CostKind);
 
-  InstructionCost InsertExtractCost = 0;
-  if (Opcode == Instruction::Load)
-    for (unsigned i = 0; i < VF; ++i)
-      // Add the cost of inserting each scalar load into the vector
-      InsertExtractCost +=
-        getVectorInstrCost(Instruction::InsertElement, SrcVTy, i);
-  else
-    for (unsigned i = 0; i < VF; ++i)
-      // Add the cost of extracting each element out of the data vector
-      InsertExtractCost +=
-        getVectorInstrCost(Instruction::ExtractElement, SrcVTy, i);
+  // The cost of forming the vector from loaded scalars/
+  // scalarizing the vector to perform scalar stores.
+  InstructionCost InsertExtractCost =
+      getScalarizationOverhead(cast<FixedVectorType>(SrcVTy), DemandedElts,
+                               /*Insert=*/Opcode == Instruction::Load,
+                               /*Extract=*/Opcode == Instruction::Store);
 
-  return MemoryOpCost + MaskUnpackCost + InsertExtractCost;
+  return AddressUnpackCost + MemoryOpCost + MaskUnpackCost + InsertExtractCost;
 }
 
 /// Calculate the cost of Gather / Scatter operation
 InstructionCost X86TTIImpl::getGatherScatterOpCost(
     unsigned Opcode, Type *SrcVTy, const Value *Ptr, bool VariableMask,
     Align Alignment, TTI::TargetCostKind CostKind,
     const Instruction *I = nullptr) {
   if (CostKind != TTI::TCK_RecipThroughput) {

llvm/test/Analysis/CostModel/X86/gather-i32-with-i8-index.ll

 ; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction:   %valB = load i32, i32* %inB, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction:   %valB = load i32, i32* %inB, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 4 For instruction:   %valB = load i32, i32* %inB, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 12 for VF 8 For instruction:   %valB = load i32, i32* %inB, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 24 for VF 16 For instruction:   %valB = load i32, i32* %inB, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 48 for VF 32 For instruction:   %valB = load i32, i32* %inB, align 4
 ;
 ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction:   %valB = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction:   %valB = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 8 for VF 4 For instruction:   %valB = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction:   %valB = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction:   %valB = load i32, i32* %inB, align 4
 ; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction:   %valB = load i32, i32* %inB, align 4
 ; AVX512: LV: Found an estimated cost of 18 for VF 16 For instruction:   %valB = load i32, i32* %inB, align 4
 ; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction:   %valB = load i32, i32* %inB, align 4
 ; AVX512: LV: Found an estimated cost of 72 for VF 64 For instruction:   %valB = load i32, i32* %inB, align 4
 ;
 ; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction:   %valB = load i32, i32* %inB, align 4
 define void @test() {
 entry:

llvm/test/Analysis/CostModel/X86/gather-i64-with-i8-index.ll

 ; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction:   %valB = load i64, i64* %inB, align 8
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction:   %valB = load i64, i64* %inB, align 8
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 4 For instruction:   %valB = load i64, i64* %inB, align 8
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 12 for VF 8 For instruction:   %valB = load i64, i64* %inB, align 8
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 24 for VF 16 For instruction:   %valB = load i64, i64* %inB, align 8
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 48 for VF 32 For instruction:   %valB = load i64, i64* %inB, align 8
 ;
 ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction:   %valB = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction:   %valB = load i64, i64* %inB, align 8
-; AVX512: LV: Found an estimated cost of 12 for VF 4 For instruction:   %valB = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction:   %valB = load i64, i64* %inB, align 8
+; AVX512: LV: Found an estimated cost of 16 for VF 4 For instruction:   %valB = load i64, i64* %inB, align 8
 ; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction:   %valB = load i64, i64* %inB, align 8
 ; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction:   %valB = load i64, i64* %inB, align 8
 ; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction:   %valB = load i64, i64* %inB, align 8
 ; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction:   %valB = load i64, i64* %inB, align 8
 ;
 ; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction:   %v0 = load i8, i8* %in0, align 2
 
 define void @test() {

llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll

 ;
   %s = call i32 @llvm.fshl.i32(i32 %a, i32 %b, i32 %c)
   %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
   ret void
 }
 
 define void @maskedgather(<16 x float*> %va, <16 x i1> %vb, <16 x float> %vc) {
 ; THRU-LABEL: 'maskedgather'
-; THRU-NEXT:  Cost Model: Found an estimated cost of 87 for instruction: %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
+; THRU-NEXT:  Cost Model: Found an estimated cost of 107 for instruction: %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; LATE-LABEL: 'maskedgather'
 ; LATE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
 ; LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE-LABEL: 'maskedgather'
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE_LATE-LABEL: 'maskedgather'
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %v = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %va, i32 1, <16 x i1> %vb, <16 x float> %vc)
   ret void
 }
 
 define void @maskedscatter(<16 x float> %va, <16 x float*> %vb, <16 x i1> %vc) {
 ; THRU-LABEL: 'maskedscatter'
-; THRU-NEXT:  Cost Model: Found an estimated cost of 75 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %va, <16 x float*> %vb, i32 1, <16 x i1> %vc)
+; THRU-NEXT:  Cost Model: Found an estimated cost of 107 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %va, <16 x float*> %vb, i32 1, <16 x i1> %vc)
 ; THRU-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; LATE-LABEL: 'maskedscatter'
 ; LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %va, <16 x float*> %vb, i32 1, <16 x i1> %vc)
 ; LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE-LABEL: 'maskedscatter'
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %va, <16 x float*> %vb, i32 1, <16 x i1> %vc)

llvm/test/Analysis/CostModel/X86/masked-gather-i32-with-i8-index.ll

 ; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 2 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 6 for VF 4 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 12 for VF 8 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 24 for VF 16 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 48 for VF 32 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
 ;
 ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 8 for VF 2 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
-; AVX512: LV: Found an estimated cost of 16 for VF 4 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 10 for VF 2 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
+; AVX512: LV: Found an estimated cost of 22 for VF 4 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
 ; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
 ; AVX512: LV: Found an estimated cost of 18 for VF 16 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
 ; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
 ; AVX512: LV: Found an estimated cost of 72 for VF 64 For instruction:   %valB.loaded = load i32, i32* %inB, align 4
 ;
 ; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction:   %valB = load i32, i32* %inB, align 4
 define void @test() {
 entry:

llvm/test/Analysis/CostModel/X86/masked-intrinsic-cost-inseltpoison.ll

;
   call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
   call void @llvm.masked.store.v8i8.p0v8i8(<8 x i8> undef, <8 x i8>* undef, i32 1, <8 x i1> undef)
 
   ret i32 0
 }
 
 define i32 @masked_gather() {
 ; SSE2-LABEL: 'masked_gather'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 960 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 480 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)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 240 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)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 72 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)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 316 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 158 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)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 79 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)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 39 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)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; SSE42-LABEL: 'masked_gather'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 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)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 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)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 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)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 96 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)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 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)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 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)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; AVX1-LABEL: 'masked_gather'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 96 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)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 32 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)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 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)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 228 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 114 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)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 56 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)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 28 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)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; AVX2-LABEL: 'masked_gather'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 96 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)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 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)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 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)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 228 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 114 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)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 56 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)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 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)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; SKL-LABEL: 'masked_gather'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 96 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)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 32 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)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 16 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)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 228 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 114 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)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 56 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)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 28 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)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; KNL-LABEL: 'masked_gather'
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 96 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)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 32 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)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 16 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)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 124 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 244 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 122 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)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 60 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)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 30 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)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; SKX-LABEL: 'masked_gather'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 96 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)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 32 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)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 16 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)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 124 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 244 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 122 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)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 60 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)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 30 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)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
   %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
   %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
   %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
   %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
 
   %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
;
   %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
   %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
 
   ret i32 0
 }
 
 define i32 @masked_scatter() {
 ; SSE2-LABEL: 'masked_scatter'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 188 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 316 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 158 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; SSE42-LABEL: 'masked_scatter'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; AVX-LABEL: 'masked_scatter'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; KNL-LABEL: 'masked_scatter'
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; SKX-LABEL: 'masked_scatter'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
   call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
   call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
   call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
   call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
 
   call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)

 ;
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
   %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1>%mask, <2 x i32>%dst)
   ret <2 x i32> %res
 }
 
 define <2 x double> @test_gather_2f64(<2 x double*> %ptrs, <2 x i1> %mask, <2 x double> %src0)  {
 ; SSE2-LABEL: 'test_gather_2f64'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
 ;
 ; SSE42-LABEL: 'test_gather_2f64'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
 ;
 ; AVX1-LABEL: 'test_gather_2f64'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
 ;
 ; AVX2-LABEL: 'test_gather_2f64'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
 ;
 ; SKL-LABEL: 'test_gather_2f64'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
 ;
 ; AVX512-LABEL: 'test_gather_2f64'
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
 ;
   %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
   ret <2 x double> %res
 }
 
 define <4 x i32> @test_gather_4i32(<4 x i32*> %ptrs, <4 x i1> %mask, <4 x i32> %src0)  {
 ; SSE2-LABEL: 'test_gather_4i32'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; SSE42-LABEL: 'test_gather_4i32'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; AVX1-LABEL: 'test_gather_4i32'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; AVX2-LABEL: 'test_gather_4i32'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; SKL-LABEL: 'test_gather_4i32'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; KNL-LABEL: 'test_gather_4i32'
-; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; SKX-LABEL: 'test_gather_4i32'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
   %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
   ret <4 x i32> %res
 }
 
 define <4 x i32> @test_gather_4i32_const_mask(<4 x i32*> %ptrs, <4 x i32> %src0)  {
 ; SSE2-LABEL: 'test_gather_4i32_const_mask'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; SSE42-LABEL: 'test_gather_4i32_const_mask'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; AVX1-LABEL: 'test_gather_4i32_const_mask'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; AVX2-LABEL: 'test_gather_4i32_const_mask'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; SKL-LABEL: 'test_gather_4i32_const_mask'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; KNL-LABEL: 'test_gather_4i32_const_mask'
-; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; SKX-LABEL: 'test_gather_4i32_const_mask'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
   %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
   ret <4 x i32> %res
 }
 
 define <16 x float> @test_gather_16f32_const_mask(float* %base, <16 x i32> %ind) {
 ; SSE2-LABEL: 'test_gather_16f32_const_mask'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SSE42-LABEL: 'test_gather_16f32_const_mask'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX1-LABEL: 'test_gather_16f32_const_mask'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX2-LABEL: 'test_gather_16f32_const_mask'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SKL-LABEL: 'test_gather_16f32_const_mask'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
;
   %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
   ret <16 x float>%res
 }
 
 define <16 x float> @test_gather_16f32_var_mask(float* %base, <16 x i32> %ind, <16 x i1>%mask) {
 ; SSE2-LABEL: 'test_gather_16f32_var_mask'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 87 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 107 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SSE42-LABEL: 'test_gather_16f32_var_mask'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX1-LABEL: 'test_gather_16f32_var_mask'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX2-LABEL: 'test_gather_16f32_var_mask'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SKL-LABEL: 'test_gather_16f32_var_mask'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
;
   %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
   ret <16 x float>%res
 }
 
 define <16 x float> @test_gather_16f32_ra_var_mask(<16 x float*> %ptrs, <16 x i32> %ind, <16 x i1>%mask) {
 ; SSE2-LABEL: 'test_gather_16f32_ra_var_mask'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 87 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 107 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SSE42-LABEL: 'test_gather_16f32_ra_var_mask'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX1-LABEL: 'test_gather_16f32_ra_var_mask'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX2-LABEL: 'test_gather_16f32_ra_var_mask'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SKL-LABEL: 'test_gather_16f32_ra_var_mask'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;

 }
 
 define <16 x float> @test_gather_16f32_const_mask2(float* %base, <16 x i32> %ind) {
 ; SSE2-LABEL: 'test_gather_16f32_const_mask2'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splatinsert = insertelement <16 x float*> poison, float* %base, i32 0
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> poison, <16 x i32> zeroinitializer
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SSE42-LABEL: 'test_gather_16f32_const_mask2'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> poison, float* %base, i32 0
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> poison, <16 x i32> zeroinitializer
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX1-LABEL: 'test_gather_16f32_const_mask2'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> poison, float* %base, i32 0
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> poison, <16 x i32> zeroinitializer
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX2-LABEL: 'test_gather_16f32_const_mask2'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> poison, float* %base, i32 0
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> poison, <16 x i32> zeroinitializer
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SKL-LABEL: 'test_gather_16f32_const_mask2'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> poison, float* %base, i32 0
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> poison, <16 x i32> zeroinitializer
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)

 }
 
 define void @test_scatter_16i32(i32* %base, <16 x i32> %ind, i16 %mask, <16 x i32>%val) {
 ; SSE2-LABEL: 'test_scatter_16i32'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> poison, <16 x i32> zeroinitializer
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 91 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 123 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SSE42-LABEL: 'test_scatter_16i32'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> poison, <16 x i32> zeroinitializer
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX1-LABEL: 'test_scatter_16i32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> poison, <16 x i32> zeroinitializer
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX2-LABEL: 'test_scatter_16i32'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> poison, <16 x i32> zeroinitializer
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SKL-LABEL: 'test_scatter_16i32'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> poison, <16 x i32> zeroinitializer
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
-; SKL-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512-LABEL: 'test_scatter_16i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> poison, <16 x i32> zeroinitializer
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
   %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> poison, <16 x i32> zeroinitializer
 
   %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
   %imask = bitcast i16 %mask to <16 x i1>
   call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32>%val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
   ret void
 }
 
 define void @test_scatter_8i32(<8 x i32>%a1, <8 x i32*> %ptr, <8 x i1>%mask) {
 ; SSE2-LABEL: 'test_scatter_8i32'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SSE42-LABEL: 'test_scatter_8i32'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX-LABEL: 'test_scatter_8i32'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512-LABEL: 'test_scatter_8i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
   ret void
 }
 
 define void @test_scatter_4i32(<4 x i32>%a1, <4 x i32*> %ptr, <4 x i1>%mask) {
 ; SSE2-LABEL: 'test_scatter_4i32'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SSE42-LABEL: 'test_scatter_4i32'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX-LABEL: 'test_scatter_4i32'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; KNL-LABEL: 'test_scatter_4i32'
-; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SKX-LABEL: 'test_scatter_4i32'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
   ret void
 }
 
 define <4 x float> @test_gather_4f32(float* %ptr, <4 x i32> %ind, <4 x i1>%mask) {
 ; SSE2-LABEL: 'test_gather_4f32'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; SSE42-LABEL: 'test_gather_4f32'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; AVX1-LABEL: 'test_gather_4f32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; AVX2-LABEL: 'test_gather_4f32'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; SKL-LABEL: 'test_gather_4f32'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; KNL-LABEL: 'test_gather_4f32'
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; KNL-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; SKX-LABEL: 'test_gather_4f32'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
   %sext_ind = sext <4 x i32> %ind to <4 x i64>
   %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
 
   %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
   ret <4 x float>%res
 }
 
 define <4 x float> @test_gather_4f32_const_mask(float* %ptr, <4 x i32> %ind) {
 ; SSE2-LABEL: 'test_gather_4f32_const_mask'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; SSE42-LABEL: 'test_gather_4f32_const_mask'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; AVX1-LABEL: 'test_gather_4f32_const_mask'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; AVX2-LABEL: 'test_gather_4f32_const_mask'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; SKL-LABEL: 'test_gather_4f32_const_mask'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; KNL-LABEL: 'test_gather_4f32_const_mask'
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; KNL-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; SKX-LABEL: 'test_gather_4f32_const_mask'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;

llvm/test/Analysis/CostModel/X86/masked-intrinsic-cost.ll

;
   call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
   call void @llvm.masked.store.v8i8.p0v8i8(<8 x i8> undef, <8 x i8>* undef, i32 1, <8 x i1> undef)
 
   ret i32 0
 }
 
 define i32 @masked_gather() {
 ; SSE2-LABEL: 'masked_gather'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 960 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 480 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)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 240 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)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 72 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)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 316 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 158 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)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 79 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)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 39 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)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; SSE42-LABEL: 'masked_gather'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 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)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 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)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 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)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 96 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)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 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)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 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)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; AVX1-LABEL: 'masked_gather'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 96 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)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 32 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)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 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)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 228 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 114 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)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 56 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)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 28 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)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; AVX2-LABEL: 'masked_gather'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 96 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)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 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)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 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)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 228 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 114 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)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 56 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)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 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)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; SKL-LABEL: 'masked_gather'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 96 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)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 32 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)
-; SKL-NEXT:  Cost Model: Found an estimated cost of 16 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)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 228 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 114 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)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 56 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)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 28 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)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; KNL-LABEL: 'masked_gather'
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 96 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)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 32 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)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 16 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)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 124 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 244 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 122 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)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 60 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)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 30 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)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; SKX-LABEL: 'masked_gather'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 96 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)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 32 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)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 16 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)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 124 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 244 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 122 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)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 60 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)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 30 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)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
   %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
   %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
   %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
   %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
 
   %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
;
   %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
   %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
 
   ret i32 0
 }
 
 define i32 @masked_scatter() {
 ; SSE2-LABEL: 'masked_scatter'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 188 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 316 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 158 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; SSE42-LABEL: 'masked_scatter'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; AVX-LABEL: 'masked_scatter'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
-; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; KNL-LABEL: 'masked_scatter'
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
-; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
 ; SKX-LABEL: 'masked_scatter'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
-; SKX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; SKX-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
 ;
   call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
   call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
   call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
   call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
 
   call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)

 ;
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
   %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1>%mask, <2 x i32>%dst)
   ret <2 x i32> %res
 }
 
 define <2 x double> @test_gather_2f64(<2 x double*> %ptrs, <2 x i1> %mask, <2 x double> %src0)  {
 ; SSE2-LABEL: 'test_gather_2f64'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
 ;
 ; SSE42-LABEL: 'test_gather_2f64'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
 ;
 ; AVX1-LABEL: 'test_gather_2f64'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
 ;
 ; AVX2-LABEL: 'test_gather_2f64'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
 ;
 ; SKL-LABEL: 'test_gather_2f64'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
 ;
 ; AVX512-LABEL: 'test_gather_2f64'
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
 ;
   %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
   ret <2 x double> %res
 }
 
 define <4 x i32> @test_gather_4i32(<4 x i32*> %ptrs, <4 x i1> %mask, <4 x i32> %src0)  {
 ; SSE2-LABEL: 'test_gather_4i32'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; SSE42-LABEL: 'test_gather_4i32'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; AVX1-LABEL: 'test_gather_4i32'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; AVX2-LABEL: 'test_gather_4i32'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; SKL-LABEL: 'test_gather_4i32'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; KNL-LABEL: 'test_gather_4i32'
-; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; SKX-LABEL: 'test_gather_4i32'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
   %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
   ret <4 x i32> %res
 }
 
 define <4 x i32> @test_gather_4i32_const_mask(<4 x i32*> %ptrs, <4 x i32> %src0)  {
 ; SSE2-LABEL: 'test_gather_4i32_const_mask'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; SSE42-LABEL: 'test_gather_4i32_const_mask'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; AVX1-LABEL: 'test_gather_4i32_const_mask'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; AVX2-LABEL: 'test_gather_4i32_const_mask'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; SKL-LABEL: 'test_gather_4i32_const_mask'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; KNL-LABEL: 'test_gather_4i32_const_mask'
-; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
 ; SKX-LABEL: 'test_gather_4i32_const_mask'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
 ;
   %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
   ret <4 x i32> %res
 }
 
 define <16 x float> @test_gather_16f32_const_mask(float* %base, <16 x i32> %ind) {
 ; SSE2-LABEL: 'test_gather_16f32_const_mask'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SSE42-LABEL: 'test_gather_16f32_const_mask'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX1-LABEL: 'test_gather_16f32_const_mask'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX2-LABEL: 'test_gather_16f32_const_mask'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SKL-LABEL: 'test_gather_16f32_const_mask'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
;
   %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
   ret <16 x float>%res
 }
 
 define <16 x float> @test_gather_16f32_var_mask(float* %base, <16 x i32> %ind, <16 x i1>%mask) {
 ; SSE2-LABEL: 'test_gather_16f32_var_mask'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 87 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 107 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SSE42-LABEL: 'test_gather_16f32_var_mask'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX1-LABEL: 'test_gather_16f32_var_mask'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX2-LABEL: 'test_gather_16f32_var_mask'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SKL-LABEL: 'test_gather_16f32_var_mask'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
;
   %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
   ret <16 x float>%res
 }
 
 define <16 x float> @test_gather_16f32_ra_var_mask(<16 x float*> %ptrs, <16 x i32> %ind, <16 x i1>%mask) {
 ; SSE2-LABEL: 'test_gather_16f32_ra_var_mask'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 87 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 107 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SSE42-LABEL: 'test_gather_16f32_ra_var_mask'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX1-LABEL: 'test_gather_16f32_ra_var_mask'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX2-LABEL: 'test_gather_16f32_ra_var_mask'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SKL-LABEL: 'test_gather_16f32_ra_var_mask'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;

 }
 
 define <16 x float> @test_gather_16f32_const_mask2(float* %base, <16 x i32> %ind) {
 ; SSE2-LABEL: 'test_gather_16f32_const_mask2'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SSE42-LABEL: 'test_gather_16f32_const_mask2'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX1-LABEL: 'test_gather_16f32_const_mask2'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; AVX2-LABEL: 'test_gather_16f32_const_mask2'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
 ;
 ; SKL-LABEL: 'test_gather_16f32_const_mask2'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)

 }
 
 define void @test_scatter_16i32(i32* %base, <16 x i32> %ind, i16 %mask, <16 x i32>%val) {
 ; SSE2-LABEL: 'test_scatter_16i32'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 91 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 123 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SSE42-LABEL: 'test_scatter_16i32'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX1-LABEL: 'test_scatter_16i32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX2-LABEL: 'test_scatter_16i32'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SKL-LABEL: 'test_scatter_16i32'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
-; SKL-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; SKL-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512-LABEL: 'test_scatter_16i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
   %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
 
   %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
   %imask = bitcast i16 %mask to <16 x i1>
   call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32>%val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
   ret void
 }
 
 define void @test_scatter_8i32(<8 x i32>%a1, <8 x i32*> %ptr, <8 x i1>%mask) {
 ; SSE2-LABEL: 'test_scatter_8i32'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SSE42-LABEL: 'test_scatter_8i32'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX-LABEL: 'test_scatter_8i32'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512-LABEL: 'test_scatter_8i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
   ret void
 }
 
 define void @test_scatter_4i32(<4 x i32>%a1, <4 x i32*> %ptr, <4 x i1>%mask) {
 ; SSE2-LABEL: 'test_scatter_4i32'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SSE42-LABEL: 'test_scatter_4i32'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX-LABEL: 'test_scatter_4i32'
-; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; AVX-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; KNL-LABEL: 'test_scatter_4i32'
-; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SKX-LABEL: 'test_scatter_4i32'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
   ret void
 }
 
 define <4 x float> @test_gather_4f32(float* %ptr, <4 x i32> %ind, <4 x i1>%mask) {
 ; SSE2-LABEL: 'test_gather_4f32'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; SSE42-LABEL: 'test_gather_4f32'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; AVX1-LABEL: 'test_gather_4f32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; AVX2-LABEL: 'test_gather_4f32'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; SKL-LABEL: 'test_gather_4f32'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; KNL-LABEL: 'test_gather_4f32'
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; KNL-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; SKX-LABEL: 'test_gather_4f32'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
   %sext_ind = sext <4 x i32> %ind to <4 x i64>
   %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
 
   %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
   ret <4 x float>%res
 }
 
 define <4 x float> @test_gather_4f32_const_mask(float* %ptr, <4 x i32> %ind) {
 ; SSE2-LABEL: 'test_gather_4f32_const_mask'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; SSE42-LABEL: 'test_gather_4f32_const_mask'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; AVX1-LABEL: 'test_gather_4f32_const_mask'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; AVX2-LABEL: 'test_gather_4f32_const_mask'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; SKL-LABEL: 'test_gather_4f32_const_mask'
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; KNL-LABEL: 'test_gather_4f32_const_mask'
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
-; KNL-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; KNL-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;
 ; SKX-LABEL: 'test_gather_4f32_const_mask'
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
 ; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
 ;

llvm/test/Analysis/CostModel/X86/masked-scatter-i32-with-i8-index.ll

 ; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 2 for VF 2 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 4 for VF 4 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 10 for VF 8 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 20 for VF 16 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 40 for VF 32 For instruction:   store i32 %valB, i32* %out, align 4
 ;
 ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 8 for VF 2 For instruction:   store i32 %valB, i32* %out, align 4
-; AVX512: LV: Found an estimated cost of 16 for VF 4 For instruction:   store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 10 for VF 2 For instruction:   store i32 %valB, i32* %out, align 4
+; AVX512: LV: Found an estimated cost of 22 for VF 4 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX512: LV: Found an estimated cost of 18 for VF 16 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX512: LV: Found an estimated cost of 72 for VF 64 For instruction:   store i32 %valB, i32* %out, align 4
 ;
 ; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction:   %valB = load i32, i32* %inB, align 4
 define void @test() {
 entry:

llvm/test/Analysis/CostModel/X86/scatter-i32-with-i8-index.ll

 ; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 26 for VF 2 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 54 for VF 4 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 112 for VF 8 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 224 for VF 16 For instruction:   store i32 %valB, i32* %out, align 4
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 448 for VF 32 For instruction:   store i32 %valB, i32* %out, align 4
 ;
 ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i32 %valB, i32* %out
-; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction:   store i32 %valB, i32* %out
-; AVX512: LV: Found an estimated cost of 8 for VF 4 For instruction:   store i32 %valB, i32* %out
+; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction:   store i32 %valB, i32* %out
+; AVX512: LV: Found an estimated cost of 14 for VF 4 For instruction:   store i32 %valB, i32* %out
 ; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction:   store i32 %valB, i32* %out
 ; AVX512: LV: Found an estimated cost of 18 for VF 16 For instruction:   store i32 %valB, i32* %out
 ; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction:   store i32 %valB, i32* %out
 ; AVX512: LV: Found an estimated cost of 72 for VF 64 For instruction:   store i32 %valB, i32* %out
 ;
 ; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction:   store i32 %valB, i32* %out
 define void @test() {
 entry:

llvm/test/Analysis/CostModel/X86/scatter-i64-with-i8-index.ll

 ; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i64 %valB, i64* %out, align 8
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 26 for VF 2 For instruction:   store i64 %valB, i64* %out, align 8
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 56 for VF 4 For instruction:   store i64 %valB, i64* %out, align 8
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 112 for VF 8 For instruction:   store i64 %valB, i64* %out, align 8
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 224 for VF 16 For instruction:   store i64 %valB, i64* %out, align 8
 ; AVX2-FASTGATHER: LV: Found an estimated cost of 448 for VF 32 For instruction:   store i64 %valB, i64* %out, align 8
 ;
 ; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction:   store i64 %valB, i64* %out, align 8
-; AVX512: LV: Found an estimated cost of 10 for VF 4 For instruction:   store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 6 for VF 2 For instruction:   store i64 %valB, i64* %out, align 8
+; AVX512: LV: Found an estimated cost of 16 for VF 4 For instruction:   store i64 %valB, i64* %out, align 8
 ; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction:   store i64 %valB, i64* %out, align 8
 ; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction:   store i64 %valB, i64* %out, align 8
 ; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction:   store i64 %valB, i64* %out, align 8
 ; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction:   store i64 %valB, i64* %out, align 8
 ;
 ; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction:   store i64 %valB, i64* %out
 define void @test() {
 entry:

llvm/test/Transforms/LoopVectorize/X86/gather_scatter.ll

 ; AVX512-NEXT:    [[TMP79:%.*]] = getelementptr inbounds float, float* [[OUT]], <16 x i64> <i64 3840, i64 3856, i64 3872, i64 3888, i64 3904, i64 3920, i64 3936, i64 3952, i64 3968, i64 3984, i64 4000, i64 4016, i64 4032, i64 4048, i64 4064, i64 4080>
 ; AVX512-NEXT:    call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> [[TMP78]], <16 x float*> [[TMP79]], i32 4, <16 x i1> [[TMP76]])
 ; AVX512-NEXT:    ret void
 ;
 ; FVW2-LABEL: @foo2(
 ; FVW2-NEXT:  entry:
 ; FVW2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; FVW2:       vector.body:
-; FVW2-NEXT:    [[INDEX6:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE30:%.*]] ]
-; FVW2-NEXT:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 0, i64 16>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE30]] ]
-; FVW2-NEXT:    [[STEP_ADD:%.*]] = add <2 x i64> [[VEC_IND]], <i64 32, i64 32>
-; FVW2-NEXT:    [[STEP_ADD7:%.*]] = add <2 x i64> [[VEC_IND]], <i64 64, i64 64>
-; FVW2-NEXT:    [[STEP_ADD8:%.*]] = add <2 x i64> [[VEC_IND]], <i64 96, i64 96>
+; FVW2-NEXT:    [[INDEX6:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE8:%.*]] ]
+; FVW2-NEXT:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 0, i64 16>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE8]] ]
 ; FVW2-NEXT:    [[OFFSET_IDX:%.*]] = shl i64 [[INDEX6]], 4
-; FVW2-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER:%.*]], <2 x i64> [[VEC_IND]]
-; FVW2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD]]
-; FVW2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD7]]
-; FVW2-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD8]]
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP0]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER10:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP1]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER11:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP2]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER12:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP3]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[TMP4:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER]], zeroinitializer
-; FVW2-NEXT:    [[TMP5:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER10]], zeroinitializer
-; FVW2-NEXT:    [[TMP6:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER11]], zeroinitializer
-; FVW2-NEXT:    [[TMP7:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER12]], zeroinitializer
+; FVW2-NEXT:    [[TMP0:%.*]] = or i64 [[OFFSET_IDX]], 16
+; FVW2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER:%.*]], i64 [[OFFSET_IDX]]
+; FVW2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
+; FVW2-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]], align 4
+; FVW2-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]], align 4
+; FVW2-NEXT:    [[TMP5:%.*]] = insertelement <2 x i32> poison, i32 [[TMP3]], i32 0
+; FVW2-NEXT:    [[TMP6:%.*]] = insertelement <2 x i32> [[TMP5]], i32 [[TMP4]], i32 1
+; FVW2-NEXT:    [[TMP7:%.*]] = icmp sgt <2 x i32> [[TMP6]], zeroinitializer
 ; FVW2-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_IN:%.*]], %struct.In* [[IN:%.*]], <2 x i64> [[VEC_IND]], i32 1
-; FVW2-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_IN]], %struct.In* [[IN]], <2 x i64> [[STEP_ADD]], i32 1
-; FVW2-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [[STRUCT_IN]], %struct.In* [[IN]], <2 x i64> [[STEP_ADD7]], i32 1
-; FVW2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_IN]], %struct.In* [[IN]], <2 x i64> [[STEP_ADD8]], i32 1
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER13:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP8]], i32 4, <2 x i1> [[TMP4]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER14:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP9]], i32 4, <2 x i1> [[TMP5]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER15:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP10]], i32 4, <2 x i1> [[TMP6]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER16:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP11]], i32 4, <2 x i1> [[TMP7]], <2 x float> undef)
-; FVW2-NEXT:    [[TMP12:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER13]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP13:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER14]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP14:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER15]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP15:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER16]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP16:%.*]] = extractelement <2 x i1> [[TMP4]], i32 0
-; FVW2-NEXT:    br i1 [[TMP16]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
+; FVW2-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP8]], i32 4, <2 x i1> [[TMP7]], <2 x float> undef)
+; FVW2-NEXT:    [[TMP9:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER]], <float 5.000000e-01, float 5.000000e-01>
+; FVW2-NEXT:    [[TMP10:%.*]] = extractelement <2 x i1> [[TMP7]], i32 0
+; FVW2-NEXT:    br i1 [[TMP10]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
 ; FVW2:       pred.store.if:
-; FVW2-NEXT:    [[TMP17:%.*]] = getelementptr inbounds float, float* [[OUT:%.*]], i64 [[OFFSET_IDX]]
-; FVW2-NEXT:    [[TMP18:%.*]] = extractelement <2 x float> [[TMP12]], i32 0
-; FVW2-NEXT:    store float [[TMP18]], float* [[TMP17]], align 4
+; FVW2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds float, float* [[OUT:%.*]], i64 [[OFFSET_IDX]]
+; FVW2-NEXT:    [[TMP12:%.*]] = extractelement <2 x float> [[TMP9]], i32 0
+; FVW2-NEXT:    store float [[TMP12]], float* [[TMP11]], align 4
 ; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE]]
 ; FVW2:       pred.store.continue:
-; FVW2-NEXT:    [[TMP19:%.*]] = extractelement <2 x i1> [[TMP4]], i32 1
-; FVW2-NEXT:    br i1 [[TMP19]], label [[PRED_STORE_IF17:%.*]], label [[PRED_STORE_CONTINUE18:%.*]]
-; FVW2:       pred.store.if17:
-; FVW2-NEXT:    [[TMP20:%.*]] = or i64 [[OFFSET_IDX]], 16
-; FVW2-NEXT:    [[TMP21:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP20]]
-; FVW2-NEXT:    [[TMP22:%.*]] = extractelement <2 x float> [[TMP12]], i32 1
-; FVW2-NEXT:    store float [[TMP22]], float* [[TMP21]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE18]]
-; FVW2:       pred.store.continue18:
-; FVW2-NEXT:    [[TMP23:%.*]] = extractelement <2 x i1> [[TMP5]], i32 0
-; FVW2-NEXT:    br i1 [[TMP23]], label [[PRED_STORE_IF19:%.*]], label [[PRED_STORE_CONTINUE20:%.*]]
-; FVW2:       pred.store.if19:
-; FVW2-NEXT:    [[TMP24:%.*]] = or i64 [[OFFSET_IDX]], 32
-; FVW2-NEXT:    [[TMP25:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP24]]
-; FVW2-NEXT:    [[TMP26:%.*]] = extractelement <2 x float> [[TMP13]], i32 0
-; FVW2-NEXT:    store float [[TMP26]], float* [[TMP25]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE20]]
-; FVW2:       pred.store.continue20:
-; FVW2-NEXT:    [[TMP27:%.*]] = extractelement <2 x i1> [[TMP5]], i32 1
-; FVW2-NEXT:    br i1 [[TMP27]], label [[PRED_STORE_IF21:%.*]], label [[PRED_STORE_CONTINUE22:%.*]]
-; FVW2:       pred.store.if21:
-; FVW2-NEXT:    [[TMP28:%.*]] = or i64 [[OFFSET_IDX]], 48
-; FVW2-NEXT:    [[TMP29:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP28]]
-; FVW2-NEXT:    [[TMP30:%.*]] = extractelement <2 x float> [[TMP13]], i32 1
-; FVW2-NEXT:    store float [[TMP30]], float* [[TMP29]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE22]]
-; FVW2:       pred.store.continue22:
-; FVW2-NEXT:    [[TMP31:%.*]] = extractelement <2 x i1> [[TMP6]], i32 0
-; FVW2-NEXT:    br i1 [[TMP31]], label [[PRED_STORE_IF23:%.*]], label [[PRED_STORE_CONTINUE24:%.*]]
-; FVW2:       pred.store.if23:
-; FVW2-NEXT:    [[TMP32:%.*]] = or i64 [[OFFSET_IDX]], 64
-; FVW2-NEXT:    [[TMP33:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP32]]
-; FVW2-NEXT:    [[TMP34:%.*]] = extractelement <2 x float> [[TMP14]], i32 0
-; FVW2-NEXT:    store float [[TMP34]], float* [[TMP33]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE24]]
-; FVW2:       pred.store.continue24:
-; FVW2-NEXT:    [[TMP35:%.*]] = extractelement <2 x i1> [[TMP6]], i32 1
-; FVW2-NEXT:    br i1 [[TMP35]], label [[PRED_STORE_IF25:%.*]], label [[PRED_STORE_CONTINUE26:%.*]]
-; FVW2:       pred.store.if25:
-; FVW2-NEXT:    [[TMP36:%.*]] = or i64 [[OFFSET_IDX]], 80
-; FVW2-NEXT:    [[TMP37:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP36]]
-; FVW2-NEXT:    [[TMP38:%.*]] = extractelement <2 x float> [[TMP14]], i32 1
-; FVW2-NEXT:    store float [[TMP38]], float* [[TMP37]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE26]]
-; FVW2:       pred.store.continue26:
-; FVW2-NEXT:    [[TMP39:%.*]] = extractelement <2 x i1> [[TMP7]], i32 0
-; FVW2-NEXT:    br i1 [[TMP39]], label [[PRED_STORE_IF27:%.*]], label [[PRED_STORE_CONTINUE28:%.*]]
-; FVW2:       pred.store.if27:
-; FVW2-NEXT:    [[TMP40:%.*]] = or i64 [[OFFSET_IDX]], 96
-; FVW2-NEXT:    [[TMP41:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP40]]
-; FVW2-NEXT:    [[TMP42:%.*]] = extractelement <2 x float> [[TMP15]], i32 0
-; FVW2-NEXT:    store float [[TMP42]], float* [[TMP41]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE28]]
-; FVW2:       pred.store.continue28:
-; FVW2-NEXT:    [[TMP43:%.*]] = extractelement <2 x i1> [[TMP7]], i32 1
-; FVW2-NEXT:    br i1 [[TMP43]], label [[PRED_STORE_IF29:%.*]], label [[PRED_STORE_CONTINUE30]]
-; FVW2:       pred.store.if29:
-; FVW2-NEXT:    [[TMP44:%.*]] = or i64 [[OFFSET_IDX]], 112
-; FVW2-NEXT:    [[TMP45:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP44]]
-; FVW2-NEXT:    [[TMP46:%.*]] = extractelement <2 x float> [[TMP15]], i32 1
-; FVW2-NEXT:    store float [[TMP46]], float* [[TMP45]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE30]]
-; FVW2:       pred.store.continue30:
-; FVW2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX6]], 8
-; FVW2-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 128, i64 128>
-; FVW2-NEXT:    [[TMP47:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
-; FVW2-NEXT:    br i1 [[TMP47]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
+; FVW2-NEXT:    [[TMP13:%.*]] = extractelement <2 x i1> [[TMP7]], i32 1
+; FVW2-NEXT:    br i1 [[TMP13]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8]]
+; FVW2:       pred.store.if7:
+; FVW2-NEXT:    [[TMP14:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP0]]
+; FVW2-NEXT:    [[TMP15:%.*]] = extractelement <2 x float> [[TMP9]], i32 1
+; FVW2-NEXT:    store float [[TMP15]], float* [[TMP14]], align 4
+; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE8]]
+; FVW2:       pred.store.continue8:
+; FVW2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX6]], 2
+; FVW2-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 32, i64 32>
+; FVW2-NEXT:    [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
+; FVW2-NEXT:    br i1 [[TMP16]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
 ; FVW2:       for.end:
 ; FVW2-NEXT:    ret void
 ;
 entry:
   %in.addr = alloca %struct.In*, align 8
   %out.addr = alloca float*, align 8
   %trigger.addr = alloca i32*, align 8
   %index.addr = alloca i32*, align 8

 ; AVX512-NEXT:    [[TMP79:%.*]] = getelementptr inbounds [[STRUCT_OUT]], %struct.Out* [[OUT]], <16 x i64> <i64 3840, i64 3856, i64 3872, i64 3888, i64 3904, i64 3920, i64 3936, i64 3952, i64 3968, i64 3984, i64 4000, i64 4016, i64 4032, i64 4048, i64 4064, i64 4080>, i32 1
 ; AVX512-NEXT:    call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> [[TMP78]], <16 x float*> [[TMP79]], i32 4, <16 x i1> [[TMP76]])
 ; AVX512-NEXT:    ret void
 ;
 ; FVW2-LABEL: @foo3(
 ; FVW2-NEXT:  entry:
 ; FVW2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; FVW2:       vector.body:
-; FVW2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE29:%.*]] ]
-; FVW2-NEXT:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 0, i64 16>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE29]] ]
-; FVW2-NEXT:    [[STEP_ADD:%.*]] = add <2 x i64> [[VEC_IND]], <i64 32, i64 32>
-; FVW2-NEXT:    [[STEP_ADD6:%.*]] = add <2 x i64> [[VEC_IND]], <i64 64, i64 64>
-; FVW2-NEXT:    [[STEP_ADD7:%.*]] = add <2 x i64> [[VEC_IND]], <i64 96, i64 96>
+; FVW2-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE7:%.*]] ]
+; FVW2-NEXT:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 0, i64 16>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE7]] ]
 ; FVW2-NEXT:    [[OFFSET_IDX:%.*]] = shl i64 [[INDEX]], 4
-; FVW2-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER:%.*]], <2 x i64> [[VEC_IND]]
-; FVW2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD]]
-; FVW2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD6]]
-; FVW2-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD7]]
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP0]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER9:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP1]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER10:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP2]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER11:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP3]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[TMP4:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER]], zeroinitializer
-; FVW2-NEXT:    [[TMP5:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER9]], zeroinitializer
-; FVW2-NEXT:    [[TMP6:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER10]], zeroinitializer
-; FVW2-NEXT:    [[TMP7:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER11]], zeroinitializer
+; FVW2-NEXT:    [[TMP0:%.*]] = or i64 [[OFFSET_IDX]], 16
+; FVW2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER:%.*]], i64 [[OFFSET_IDX]]
+; FVW2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
+; FVW2-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]], align 4
+; FVW2-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]], align 4
+; FVW2-NEXT:    [[TMP5:%.*]] = insertelement <2 x i32> poison, i32 [[TMP3]], i32 0
+; FVW2-NEXT:    [[TMP6:%.*]] = insertelement <2 x i32> [[TMP5]], i32 [[TMP4]], i32 1
+; FVW2-NEXT:    [[TMP7:%.*]] = icmp sgt <2 x i32> [[TMP6]], zeroinitializer
 ; FVW2-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_IN:%.*]], %struct.In* [[IN:%.*]], <2 x i64> [[VEC_IND]], i32 1
-; FVW2-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_IN]], %struct.In* [[IN]], <2 x i64> [[STEP_ADD]], i32 1
-; FVW2-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [[STRUCT_IN]], %struct.In* [[IN]], <2 x i64> [[STEP_ADD6]], i32 1
-; FVW2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_IN]], %struct.In* [[IN]], <2 x i64> [[STEP_ADD7]], i32 1
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER12:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP8]], i32 4, <2 x i1> [[TMP4]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER13:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP9]], i32 4, <2 x i1> [[TMP5]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER14:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP10]], i32 4, <2 x i1> [[TMP6]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER15:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP11]], i32 4, <2 x i1> [[TMP7]], <2 x float> undef)
-; FVW2-NEXT:    [[TMP12:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER12]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP13:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER13]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP14:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER14]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP15:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER15]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP16:%.*]] = extractelement <2 x i1> [[TMP4]], i32 0
-; FVW2-NEXT:    br i1 [[TMP16]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
+; FVW2-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP8]], i32 4, <2 x i1> [[TMP7]], <2 x float> undef)
+; FVW2-NEXT:    [[TMP9:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER]], <float 5.000000e-01, float 5.000000e-01>
+; FVW2-NEXT:    [[TMP10:%.*]] = extractelement <2 x i1> [[TMP7]], i32 0
+; FVW2-NEXT:    br i1 [[TMP10]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
 ; FVW2:       pred.store.if:
-; FVW2-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_OUT:%.*]], %struct.Out* [[OUT:%.*]], i64 [[OFFSET_IDX]], i32 1
-; FVW2-NEXT:    [[TMP18:%.*]] = extractelement <2 x float> [[TMP12]], i32 0
-; FVW2-NEXT:    store float [[TMP18]], float* [[TMP17]], align 4
+; FVW2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_OUT:%.*]], %struct.Out* [[OUT:%.*]], i64 [[OFFSET_IDX]], i32 1
+; FVW2-NEXT:    [[TMP12:%.*]] = extractelement <2 x float> [[TMP9]], i32 0
+; FVW2-NEXT:    store float [[TMP12]], float* [[TMP11]], align 4
 ; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE]]
 ; FVW2:       pred.store.continue:
-; FVW2-NEXT:    [[TMP19:%.*]] = extractelement <2 x i1> [[TMP4]], i32 1
-; FVW2-NEXT:    br i1 [[TMP19]], label [[PRED_STORE_IF16:%.*]], label [[PRED_STORE_CONTINUE17:%.*]]
-; FVW2:       pred.store.if16:
-; FVW2-NEXT:    [[TMP20:%.*]] = or i64 [[OFFSET_IDX]], 16
-; FVW2-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [[STRUCT_OUT]], %struct.Out* [[OUT]], i64 [[TMP20]], i32 1
-; FVW2-NEXT:    [[TMP22:%.*]] = extractelement <2 x float> [[TMP12]], i32 1
-; FVW2-NEXT:    store float [[TMP22]], float* [[TMP21]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE17]]
-; FVW2:       pred.store.continue17:
-; FVW2-NEXT:    [[TMP23:%.*]] = extractelement <2 x i1> [[TMP5]], i32 0
-; FVW2-NEXT:    br i1 [[TMP23]], label [[PRED_STORE_IF18:%.*]], label [[PRED_STORE_CONTINUE19:%.*]]
-; FVW2:       pred.store.if18:
-; FVW2-NEXT:    [[TMP24:%.*]] = or i64 [[OFFSET_IDX]], 32
-; FVW2-NEXT:    [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_OUT]], %struct.Out* [[OUT]], i64 [[TMP24]], i32 1
-; FVW2-NEXT:    [[TMP26:%.*]] = extractelement <2 x float> [[TMP13]], i32 0
-; FVW2-NEXT:    store float [[TMP26]], float* [[TMP25]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE19]]
-; FVW2:       pred.store.continue19:
-; FVW2-NEXT:    [[TMP27:%.*]] = extractelement <2 x i1> [[TMP5]], i32 1
-; FVW2-NEXT:    br i1 [[TMP27]], label [[PRED_STORE_IF20:%.*]], label [[PRED_STORE_CONTINUE21:%.*]]
-; FVW2:       pred.store.if20:
-; FVW2-NEXT:    [[TMP28:%.*]] = or i64 [[OFFSET_IDX]], 48
-; FVW2-NEXT:    [[TMP29:%.*]] = getelementptr inbounds [[STRUCT_OUT]], %struct.Out* [[OUT]], i64 [[TMP28]], i32 1
-; FVW2-NEXT:    [[TMP30:%.*]] = extractelement <2 x float> [[TMP13]], i32 1
-; FVW2-NEXT:    store float [[TMP30]], float* [[TMP29]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE21]]
-; FVW2:       pred.store.continue21:
-; FVW2-NEXT:    [[TMP31:%.*]] = extractelement <2 x i1> [[TMP6]], i32 0
-; FVW2-NEXT:    br i1 [[TMP31]], label [[PRED_STORE_IF22:%.*]], label [[PRED_STORE_CONTINUE23:%.*]]
-; FVW2:       pred.store.if22:
-; FVW2-NEXT:    [[TMP32:%.*]] = or i64 [[OFFSET_IDX]], 64
-; FVW2-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [[STRUCT_OUT]], %struct.Out* [[OUT]], i64 [[TMP32]], i32 1
-; FVW2-NEXT:    [[TMP34:%.*]] = extractelement <2 x float> [[TMP14]], i32 0
-; FVW2-NEXT:    store float [[TMP34]], float* [[TMP33]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE23]]
-; FVW2:       pred.store.continue23:
-; FVW2-NEXT:    [[TMP35:%.*]] = extractelement <2 x i1> [[TMP6]], i32 1
-; FVW2-NEXT:    br i1 [[TMP35]], label [[PRED_STORE_IF24:%.*]], label [[PRED_STORE_CONTINUE25:%.*]]
-; FVW2:       pred.store.if24:
-; FVW2-NEXT:    [[TMP36:%.*]] = or i64 [[OFFSET_IDX]], 80
-; FVW2-NEXT:    [[TMP37:%.*]] = getelementptr inbounds [[STRUCT_OUT]], %struct.Out* [[OUT]], i64 [[TMP36]], i32 1
-; FVW2-NEXT:    [[TMP38:%.*]] = extractelement <2 x float> [[TMP14]], i32 1
-; FVW2-NEXT:    store float [[TMP38]], float* [[TMP37]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE25]]
-; FVW2:       pred.store.continue25:
-; FVW2-NEXT:    [[TMP39:%.*]] = extractelement <2 x i1> [[TMP7]], i32 0
-; FVW2-NEXT:    br i1 [[TMP39]], label [[PRED_STORE_IF26:%.*]], label [[PRED_STORE_CONTINUE27:%.*]]
-; FVW2:       pred.store.if26:
-; FVW2-NEXT:    [[TMP40:%.*]] = or i64 [[OFFSET_IDX]], 96
-; FVW2-NEXT:    [[TMP41:%.*]] = getelementptr inbounds [[STRUCT_OUT]], %struct.Out* [[OUT]], i64 [[TMP40]], i32 1
-; FVW2-NEXT:    [[TMP42:%.*]] = extractelement <2 x float> [[TMP15]], i32 0
-; FVW2-NEXT:    store float [[TMP42]], float* [[TMP41]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE27]]
-; FVW2:       pred.store.continue27:
-; FVW2-NEXT:    [[TMP43:%.*]] = extractelement <2 x i1> [[TMP7]], i32 1
-; FVW2-NEXT:    br i1 [[TMP43]], label [[PRED_STORE_IF28:%.*]], label [[PRED_STORE_CONTINUE29]]
-; FVW2:       pred.store.if28:
-; FVW2-NEXT:    [[TMP44:%.*]] = or i64 [[OFFSET_IDX]], 112
-; FVW2-NEXT:    [[TMP45:%.*]] = getelementptr inbounds [[STRUCT_OUT]], %struct.Out* [[OUT]], i64 [[TMP44]], i32 1
-; FVW2-NEXT:    [[TMP46:%.*]] = extractelement <2 x float> [[TMP15]], i32 1
-; FVW2-NEXT:    store float [[TMP46]], float* [[TMP45]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE29]]
-; FVW2:       pred.store.continue29:
-; FVW2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
-; FVW2-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 128, i64 128>
-; FVW2-NEXT:    [[TMP47:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
-; FVW2-NEXT:    br i1 [[TMP47]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; FVW2-NEXT:    [[TMP13:%.*]] = extractelement <2 x i1> [[TMP7]], i32 1
+; FVW2-NEXT:    br i1 [[TMP13]], label [[PRED_STORE_IF6:%.*]], label [[PRED_STORE_CONTINUE7]]
+; FVW2:       pred.store.if6:
+; FVW2-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [[STRUCT_OUT]], %struct.Out* [[OUT]], i64 [[TMP0]], i32 1
+; FVW2-NEXT:    [[TMP15:%.*]] = extractelement <2 x float> [[TMP9]], i32 1
+; FVW2-NEXT:    store float [[TMP15]], float* [[TMP14]], align 4
+; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE7]]
+; FVW2:       pred.store.continue7:
+; FVW2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
+; FVW2-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 32, i64 32>
+; FVW2-NEXT:    [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
+; FVW2-NEXT:    br i1 [[TMP16]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
 ; FVW2:       for.end:
 ; FVW2-NEXT:    ret void
 ;
 entry:
   %in.addr = alloca %struct.In*, align 8
   %out.addr = alloca %struct.Out*, align 8
   %trigger.addr = alloca i32*, align 8
   %i = alloca i32, align 4

 ; AVX512-NEXT:    [[TMP79:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], <16 x i64> <i64 3840, i64 3856, i64 3872, i64 3888, i64 3904, i64 3920, i64 3936, i64 3952, i64 3968, i64 3984, i64 4000, i64 4016, i64 4032, i64 4048, i64 4064, i64 4080>
 ; AVX512-NEXT:    call void @llvm.masked.scatter.v16f32.v16p1f32(<16 x float> [[TMP78]], <16 x float addrspace(1)*> [[TMP79]], i32 4, <16 x i1> [[TMP76]])
 ; AVX512-NEXT:    ret void
 ;
 ; FVW2-LABEL: @foo2_addrspace(
 ; FVW2-NEXT:  entry:
 ; FVW2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; FVW2:       vector.body:
-; FVW2-NEXT:    [[INDEX6:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE30:%.*]] ]
-; FVW2-NEXT:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 0, i64 16>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE30]] ]
-; FVW2-NEXT:    [[STEP_ADD:%.*]] = add <2 x i64> [[VEC_IND]], <i64 32, i64 32>
-; FVW2-NEXT:    [[STEP_ADD7:%.*]] = add <2 x i64> [[VEC_IND]], <i64 64, i64 64>
-; FVW2-NEXT:    [[STEP_ADD8:%.*]] = add <2 x i64> [[VEC_IND]], <i64 96, i64 96>
+; FVW2-NEXT:    [[INDEX6:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE8:%.*]] ]
+; FVW2-NEXT:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 0, i64 16>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE8]] ]
 ; FVW2-NEXT:    [[OFFSET_IDX:%.*]] = shl i64 [[INDEX6]], 4
-; FVW2-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER:%.*]], <2 x i64> [[VEC_IND]]
-; FVW2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD]]
-; FVW2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD7]]
-; FVW2-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD8]]
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP0]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER10:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP1]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER11:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP2]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER12:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP3]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[TMP4:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER]], zeroinitializer
-; FVW2-NEXT:    [[TMP5:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER10]], zeroinitializer
-; FVW2-NEXT:    [[TMP6:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER11]], zeroinitializer
-; FVW2-NEXT:    [[TMP7:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER12]], zeroinitializer
+; FVW2-NEXT:    [[TMP0:%.*]] = or i64 [[OFFSET_IDX]], 16
+; FVW2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER:%.*]], i64 [[OFFSET_IDX]]
+; FVW2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
+; FVW2-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]], align 4
+; FVW2-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]], align 4
+; FVW2-NEXT:    [[TMP5:%.*]] = insertelement <2 x i32> poison, i32 [[TMP3]], i32 0
+; FVW2-NEXT:    [[TMP6:%.*]] = insertelement <2 x i32> [[TMP5]], i32 [[TMP4]], i32 1
+; FVW2-NEXT:    [[TMP7:%.*]] = icmp sgt <2 x i32> [[TMP6]], zeroinitializer
 ; FVW2-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_IN:%.*]], [[STRUCT_IN]] addrspace(1)* [[IN:%.*]], <2 x i64> [[VEC_IND]], i32 1
-; FVW2-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_IN]], [[STRUCT_IN]] addrspace(1)* [[IN]], <2 x i64> [[STEP_ADD]], i32 1
-; FVW2-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [[STRUCT_IN]], [[STRUCT_IN]] addrspace(1)* [[IN]], <2 x i64> [[STEP_ADD7]], i32 1
-; FVW2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_IN]], [[STRUCT_IN]] addrspace(1)* [[IN]], <2 x i64> [[STEP_ADD8]], i32 1
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER13:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p1f32(<2 x float addrspace(1)*> [[TMP8]], i32 4, <2 x i1> [[TMP4]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER14:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p1f32(<2 x float addrspace(1)*> [[TMP9]], i32 4, <2 x i1> [[TMP5]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER15:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p1f32(<2 x float addrspace(1)*> [[TMP10]], i32 4, <2 x i1> [[TMP6]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER16:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p1f32(<2 x float addrspace(1)*> [[TMP11]], i32 4, <2 x i1> [[TMP7]], <2 x float> undef)
-; FVW2-NEXT:    [[TMP12:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER13]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP13:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER14]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP14:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER15]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP15:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER16]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP16:%.*]] = extractelement <2 x i1> [[TMP4]], i32 0
-; FVW2-NEXT:    br i1 [[TMP16]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
+; FVW2-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p1f32(<2 x float addrspace(1)*> [[TMP8]], i32 4, <2 x i1> [[TMP7]], <2 x float> undef)
+; FVW2-NEXT:    [[TMP9:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER]], <float 5.000000e-01, float 5.000000e-01>
+; FVW2-NEXT:    [[TMP10:%.*]] = extractelement <2 x i1> [[TMP7]], i32 0
+; FVW2-NEXT:    br i1 [[TMP10]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
 ; FVW2:       pred.store.if:
-; FVW2-NEXT:    [[TMP17:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT:%.*]], i64 [[OFFSET_IDX]]
-; FVW2-NEXT:    [[TMP18:%.*]] = extractelement <2 x float> [[TMP12]], i32 0
-; FVW2-NEXT:    store float [[TMP18]], float addrspace(1)* [[TMP17]], align 4
+; FVW2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT:%.*]], i64 [[OFFSET_IDX]]
+; FVW2-NEXT:    [[TMP12:%.*]] = extractelement <2 x float> [[TMP9]], i32 0
+; FVW2-NEXT:    store float [[TMP12]], float addrspace(1)* [[TMP11]], align 4
 ; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE]]
 ; FVW2:       pred.store.continue:
-; FVW2-NEXT:    [[TMP19:%.*]] = extractelement <2 x i1> [[TMP4]], i32 1
-; FVW2-NEXT:    br i1 [[TMP19]], label [[PRED_STORE_IF17:%.*]], label [[PRED_STORE_CONTINUE18:%.*]]
-; FVW2:       pred.store.if17:
-; FVW2-NEXT:    [[TMP20:%.*]] = or i64 [[OFFSET_IDX]], 16
-; FVW2-NEXT:    [[TMP21:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP20]]
-; FVW2-NEXT:    [[TMP22:%.*]] = extractelement <2 x float> [[TMP12]], i32 1
-; FVW2-NEXT:    store float [[TMP22]], float addrspace(1)* [[TMP21]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE18]]
-; FVW2:       pred.store.continue18:
-; FVW2-NEXT:    [[TMP23:%.*]] = extractelement <2 x i1> [[TMP5]], i32 0
-; FVW2-NEXT:    br i1 [[TMP23]], label [[PRED_STORE_IF19:%.*]], label [[PRED_STORE_CONTINUE20:%.*]]
-; FVW2:       pred.store.if19:
-; FVW2-NEXT:    [[TMP24:%.*]] = or i64 [[OFFSET_IDX]], 32
-; FVW2-NEXT:    [[TMP25:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP24]]
-; FVW2-NEXT:    [[TMP26:%.*]] = extractelement <2 x float> [[TMP13]], i32 0
-; FVW2-NEXT:    store float [[TMP26]], float addrspace(1)* [[TMP25]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE20]]
-; FVW2:       pred.store.continue20:
-; FVW2-NEXT:    [[TMP27:%.*]] = extractelement <2 x i1> [[TMP5]], i32 1
-; FVW2-NEXT:    br i1 [[TMP27]], label [[PRED_STORE_IF21:%.*]], label [[PRED_STORE_CONTINUE22:%.*]]
-; FVW2:       pred.store.if21:
-; FVW2-NEXT:    [[TMP28:%.*]] = or i64 [[OFFSET_IDX]], 48
-; FVW2-NEXT:    [[TMP29:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP28]]
-; FVW2-NEXT:    [[TMP30:%.*]] = extractelement <2 x float> [[TMP13]], i32 1
-; FVW2-NEXT:    store float [[TMP30]], float addrspace(1)* [[TMP29]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE22]]
-; FVW2:       pred.store.continue22:
-; FVW2-NEXT:    [[TMP31:%.*]] = extractelement <2 x i1> [[TMP6]], i32 0
-; FVW2-NEXT:    br i1 [[TMP31]], label [[PRED_STORE_IF23:%.*]], label [[PRED_STORE_CONTINUE24:%.*]]
-; FVW2:       pred.store.if23:
-; FVW2-NEXT:    [[TMP32:%.*]] = or i64 [[OFFSET_IDX]], 64
-; FVW2-NEXT:    [[TMP33:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP32]]
-; FVW2-NEXT:    [[TMP34:%.*]] = extractelement <2 x float> [[TMP14]], i32 0
-; FVW2-NEXT:    store float [[TMP34]], float addrspace(1)* [[TMP33]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE24]]
-; FVW2:       pred.store.continue24:
-; FVW2-NEXT:    [[TMP35:%.*]] = extractelement <2 x i1> [[TMP6]], i32 1
-; FVW2-NEXT:    br i1 [[TMP35]], label [[PRED_STORE_IF25:%.*]], label [[PRED_STORE_CONTINUE26:%.*]]
-; FVW2:       pred.store.if25:
-; FVW2-NEXT:    [[TMP36:%.*]] = or i64 [[OFFSET_IDX]], 80
-; FVW2-NEXT:    [[TMP37:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP36]]
-; FVW2-NEXT:    [[TMP38:%.*]] = extractelement <2 x float> [[TMP14]], i32 1
-; FVW2-NEXT:    store float [[TMP38]], float addrspace(1)* [[TMP37]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE26]]
-; FVW2:       pred.store.continue26:
-; FVW2-NEXT:    [[TMP39:%.*]] = extractelement <2 x i1> [[TMP7]], i32 0
-; FVW2-NEXT:    br i1 [[TMP39]], label [[PRED_STORE_IF27:%.*]], label [[PRED_STORE_CONTINUE28:%.*]]
-; FVW2:       pred.store.if27:
-; FVW2-NEXT:    [[TMP40:%.*]] = or i64 [[OFFSET_IDX]], 96
-; FVW2-NEXT:    [[TMP41:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP40]]
-; FVW2-NEXT:    [[TMP42:%.*]] = extractelement <2 x float> [[TMP15]], i32 0
-; FVW2-NEXT:    store float [[TMP42]], float addrspace(1)* [[TMP41]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE28]]
-; FVW2:       pred.store.continue28:
-; FVW2-NEXT:    [[TMP43:%.*]] = extractelement <2 x i1> [[TMP7]], i32 1
-; FVW2-NEXT:    br i1 [[TMP43]], label [[PRED_STORE_IF29:%.*]], label [[PRED_STORE_CONTINUE30]]
-; FVW2:       pred.store.if29:
-; FVW2-NEXT:    [[TMP44:%.*]] = or i64 [[OFFSET_IDX]], 112
-; FVW2-NEXT:    [[TMP45:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP44]]
-; FVW2-NEXT:    [[TMP46:%.*]] = extractelement <2 x float> [[TMP15]], i32 1
-; FVW2-NEXT:    store float [[TMP46]], float addrspace(1)* [[TMP45]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE30]]
-; FVW2:       pred.store.continue30:
-; FVW2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX6]], 8
-; FVW2-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 128, i64 128>
-; FVW2-NEXT:    [[TMP47:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
-; FVW2-NEXT:    br i1 [[TMP47]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; FVW2-NEXT:    [[TMP13:%.*]] = extractelement <2 x i1> [[TMP7]], i32 1
+; FVW2-NEXT:    br i1 [[TMP13]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8]]
+; FVW2:       pred.store.if7:
+; FVW2-NEXT:    [[TMP14:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP0]]
+; FVW2-NEXT:    [[TMP15:%.*]] = extractelement <2 x float> [[TMP9]], i32 1
+; FVW2-NEXT:    store float [[TMP15]], float addrspace(1)* [[TMP14]], align 4
+; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE8]]
+; FVW2:       pred.store.continue8:
+; FVW2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX6]], 2
+; FVW2-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 32, i64 32>
+; FVW2-NEXT:    [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
+; FVW2-NEXT:    br i1 [[TMP16]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
 ; FVW2:       for.end:
 ; FVW2-NEXT:    ret void
 ;
 entry:
   %in.addr = alloca %struct.In addrspace(1)*, align 8
   %out.addr = alloca float addrspace(1)*, align 8
   %trigger.addr = alloca i32*, align 8
   %index.addr = alloca i32*, align 8

 ; AVX512-NEXT:    [[TMP79:%.*]] = getelementptr inbounds float, float* [[OUT]], <16 x i64> <i64 3840, i64 3856, i64 3872, i64 3888, i64 3904, i64 3920, i64 3936, i64 3952, i64 3968, i64 3984, i64 4000, i64 4016, i64 4032, i64 4048, i64 4064, i64 4080>
 ; AVX512-NEXT:    call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> [[TMP78]], <16 x float*> [[TMP79]], i32 4, <16 x i1> [[TMP76]])
 ; AVX512-NEXT:    ret void
 ;
 ; FVW2-LABEL: @foo2_addrspace2(
 ; FVW2-NEXT:  entry:
 ; FVW2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; FVW2:       vector.body:
-; FVW2-NEXT:    [[INDEX6:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE30:%.*]] ]
-; FVW2-NEXT:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 0, i64 16>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE30]] ]
-; FVW2-NEXT:    [[STEP_ADD:%.*]] = add <2 x i64> [[VEC_IND]], <i64 32, i64 32>
-; FVW2-NEXT:    [[STEP_ADD7:%.*]] = add <2 x i64> [[VEC_IND]], <i64 64, i64 64>
-; FVW2-NEXT:    [[STEP_ADD8:%.*]] = add <2 x i64> [[VEC_IND]], <i64 96, i64 96>
+; FVW2-NEXT:    [[INDEX6:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE8:%.*]] ]
+; FVW2-NEXT:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 0, i64 16>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE8]] ]
 ; FVW2-NEXT:    [[OFFSET_IDX:%.*]] = shl i64 [[INDEX6]], 4
-; FVW2-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER:%.*]], <2 x i64> [[VEC_IND]]
-; FVW2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD]]
-; FVW2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD7]]
-; FVW2-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD8]]
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP0]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER10:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP1]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER11:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP2]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER12:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP3]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[TMP4:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER]], zeroinitializer
-; FVW2-NEXT:    [[TMP5:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER10]], zeroinitializer
-; FVW2-NEXT:    [[TMP6:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER11]], zeroinitializer
-; FVW2-NEXT:    [[TMP7:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER12]], zeroinitializer
+; FVW2-NEXT:    [[TMP0:%.*]] = or i64 [[OFFSET_IDX]], 16
+; FVW2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER:%.*]], i64 [[OFFSET_IDX]]
+; FVW2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
+; FVW2-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]], align 4
+; FVW2-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]], align 4
+; FVW2-NEXT:    [[TMP5:%.*]] = insertelement <2 x i32> poison, i32 [[TMP3]], i32 0
+; FVW2-NEXT:    [[TMP6:%.*]] = insertelement <2 x i32> [[TMP5]], i32 [[TMP4]], i32 1
+; FVW2-NEXT:    [[TMP7:%.*]] = icmp sgt <2 x i32> [[TMP6]], zeroinitializer
 ; FVW2-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_IN:%.*]], [[STRUCT_IN]] addrspace(1)* [[IN:%.*]], <2 x i64> [[VEC_IND]], i32 1
-; FVW2-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_IN]], [[STRUCT_IN]] addrspace(1)* [[IN]], <2 x i64> [[STEP_ADD]], i32 1
-; FVW2-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [[STRUCT_IN]], [[STRUCT_IN]] addrspace(1)* [[IN]], <2 x i64> [[STEP_ADD7]], i32 1
-; FVW2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_IN]], [[STRUCT_IN]] addrspace(1)* [[IN]], <2 x i64> [[STEP_ADD8]], i32 1
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER13:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p1f32(<2 x float addrspace(1)*> [[TMP8]], i32 4, <2 x i1> [[TMP4]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER14:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p1f32(<2 x float addrspace(1)*> [[TMP9]], i32 4, <2 x i1> [[TMP5]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER15:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p1f32(<2 x float addrspace(1)*> [[TMP10]], i32 4, <2 x i1> [[TMP6]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER16:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p1f32(<2 x float addrspace(1)*> [[TMP11]], i32 4, <2 x i1> [[TMP7]], <2 x float> undef)
-; FVW2-NEXT:    [[TMP12:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER13]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP13:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER14]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP14:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER15]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP15:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER16]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP16:%.*]] = extractelement <2 x i1> [[TMP4]], i32 0
-; FVW2-NEXT:    br i1 [[TMP16]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
+; FVW2-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p1f32(<2 x float addrspace(1)*> [[TMP8]], i32 4, <2 x i1> [[TMP7]], <2 x float> undef)
+; FVW2-NEXT:    [[TMP9:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER]], <float 5.000000e-01, float 5.000000e-01>
+; FVW2-NEXT:    [[TMP10:%.*]] = extractelement <2 x i1> [[TMP7]], i32 0
+; FVW2-NEXT:    br i1 [[TMP10]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
 ; FVW2:       pred.store.if:
-; FVW2-NEXT:    [[TMP17:%.*]] = getelementptr inbounds float, float* [[OUT:%.*]], i64 [[OFFSET_IDX]]
-; FVW2-NEXT:    [[TMP18:%.*]] = extractelement <2 x float> [[TMP12]], i32 0
-; FVW2-NEXT:    store float [[TMP18]], float* [[TMP17]], align 4
+; FVW2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds float, float* [[OUT:%.*]], i64 [[OFFSET_IDX]]
+; FVW2-NEXT:    [[TMP12:%.*]] = extractelement <2 x float> [[TMP9]], i32 0
+; FVW2-NEXT:    store float [[TMP12]], float* [[TMP11]], align 4
 ; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE]]
 ; FVW2:       pred.store.continue:
-; FVW2-NEXT:    [[TMP19:%.*]] = extractelement <2 x i1> [[TMP4]], i32 1
-; FVW2-NEXT:    br i1 [[TMP19]], label [[PRED_STORE_IF17:%.*]], label [[PRED_STORE_CONTINUE18:%.*]]
-; FVW2:       pred.store.if17:
-; FVW2-NEXT:    [[TMP20:%.*]] = or i64 [[OFFSET_IDX]], 16
-; FVW2-NEXT:    [[TMP21:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP20]]
-; FVW2-NEXT:    [[TMP22:%.*]] = extractelement <2 x float> [[TMP12]], i32 1
-; FVW2-NEXT:    store float [[TMP22]], float* [[TMP21]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE18]]
-; FVW2:       pred.store.continue18:
-; FVW2-NEXT:    [[TMP23:%.*]] = extractelement <2 x i1> [[TMP5]], i32 0
-; FVW2-NEXT:    br i1 [[TMP23]], label [[PRED_STORE_IF19:%.*]], label [[PRED_STORE_CONTINUE20:%.*]]
-; FVW2:       pred.store.if19:
-; FVW2-NEXT:    [[TMP24:%.*]] = or i64 [[OFFSET_IDX]], 32
-; FVW2-NEXT:    [[TMP25:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP24]]
-; FVW2-NEXT:    [[TMP26:%.*]] = extractelement <2 x float> [[TMP13]], i32 0
-; FVW2-NEXT:    store float [[TMP26]], float* [[TMP25]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE20]]
-; FVW2:       pred.store.continue20:
-; FVW2-NEXT:    [[TMP27:%.*]] = extractelement <2 x i1> [[TMP5]], i32 1
-; FVW2-NEXT:    br i1 [[TMP27]], label [[PRED_STORE_IF21:%.*]], label [[PRED_STORE_CONTINUE22:%.*]]
-; FVW2:       pred.store.if21:
-; FVW2-NEXT:    [[TMP28:%.*]] = or i64 [[OFFSET_IDX]], 48
-; FVW2-NEXT:    [[TMP29:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP28]]
-; FVW2-NEXT:    [[TMP30:%.*]] = extractelement <2 x float> [[TMP13]], i32 1
-; FVW2-NEXT:    store float [[TMP30]], float* [[TMP29]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE22]]
-; FVW2:       pred.store.continue22:
-; FVW2-NEXT:    [[TMP31:%.*]] = extractelement <2 x i1> [[TMP6]], i32 0
-; FVW2-NEXT:    br i1 [[TMP31]], label [[PRED_STORE_IF23:%.*]], label [[PRED_STORE_CONTINUE24:%.*]]
-; FVW2:       pred.store.if23:
-; FVW2-NEXT:    [[TMP32:%.*]] = or i64 [[OFFSET_IDX]], 64
-; FVW2-NEXT:    [[TMP33:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP32]]
-; FVW2-NEXT:    [[TMP34:%.*]] = extractelement <2 x float> [[TMP14]], i32 0
-; FVW2-NEXT:    store float [[TMP34]], float* [[TMP33]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE24]]
-; FVW2:       pred.store.continue24:
-; FVW2-NEXT:    [[TMP35:%.*]] = extractelement <2 x i1> [[TMP6]], i32 1
-; FVW2-NEXT:    br i1 [[TMP35]], label [[PRED_STORE_IF25:%.*]], label [[PRED_STORE_CONTINUE26:%.*]]
-; FVW2:       pred.store.if25:
-; FVW2-NEXT:    [[TMP36:%.*]] = or i64 [[OFFSET_IDX]], 80
-; FVW2-NEXT:    [[TMP37:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP36]]
-; FVW2-NEXT:    [[TMP38:%.*]] = extractelement <2 x float> [[TMP14]], i32 1
-; FVW2-NEXT:    store float [[TMP38]], float* [[TMP37]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE26]]
-; FVW2:       pred.store.continue26:
-; FVW2-NEXT:    [[TMP39:%.*]] = extractelement <2 x i1> [[TMP7]], i32 0
-; FVW2-NEXT:    br i1 [[TMP39]], label [[PRED_STORE_IF27:%.*]], label [[PRED_STORE_CONTINUE28:%.*]]
-; FVW2:       pred.store.if27:
-; FVW2-NEXT:    [[TMP40:%.*]] = or i64 [[OFFSET_IDX]], 96
-; FVW2-NEXT:    [[TMP41:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP40]]
-; FVW2-NEXT:    [[TMP42:%.*]] = extractelement <2 x float> [[TMP15]], i32 0
-; FVW2-NEXT:    store float [[TMP42]], float* [[TMP41]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE28]]
-; FVW2:       pred.store.continue28:
-; FVW2-NEXT:    [[TMP43:%.*]] = extractelement <2 x i1> [[TMP7]], i32 1
-; FVW2-NEXT:    br i1 [[TMP43]], label [[PRED_STORE_IF29:%.*]], label [[PRED_STORE_CONTINUE30]]
-; FVW2:       pred.store.if29:
-; FVW2-NEXT:    [[TMP44:%.*]] = or i64 [[OFFSET_IDX]], 112
-; FVW2-NEXT:    [[TMP45:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP44]]
-; FVW2-NEXT:    [[TMP46:%.*]] = extractelement <2 x float> [[TMP15]], i32 1
-; FVW2-NEXT:    store float [[TMP46]], float* [[TMP45]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE30]]
-; FVW2:       pred.store.continue30:
-; FVW2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX6]], 8
-; FVW2-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 128, i64 128>
-; FVW2-NEXT:    [[TMP47:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
-; FVW2-NEXT:    br i1 [[TMP47]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; FVW2-NEXT:    [[TMP13:%.*]] = extractelement <2 x i1> [[TMP7]], i32 1
+; FVW2-NEXT:    br i1 [[TMP13]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8]]
+; FVW2:       pred.store.if7:
+; FVW2-NEXT:    [[TMP14:%.*]] = getelementptr inbounds float, float* [[OUT]], i64 [[TMP0]]
+; FVW2-NEXT:    [[TMP15:%.*]] = extractelement <2 x float> [[TMP9]], i32 1
+; FVW2-NEXT:    store float [[TMP15]], float* [[TMP14]], align 4
+; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE8]]
+; FVW2:       pred.store.continue8:
+; FVW2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX6]], 2
+; FVW2-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 32, i64 32>
+; FVW2-NEXT:    [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
+; FVW2-NEXT:    br i1 [[TMP16]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
 ; FVW2:       for.end:
 ; FVW2-NEXT:    ret void
 ;
 entry:
   %in.addr = alloca %struct.In addrspace(1)*, align 8
   %out.addr = alloca float addrspace(0)*, align 8
   %trigger.addr = alloca i32*, align 8
   %index.addr = alloca i32*, align 8

 ; AVX512-NEXT:    [[TMP79:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], <16 x i64> <i64 3840, i64 3856, i64 3872, i64 3888, i64 3904, i64 3920, i64 3936, i64 3952, i64 3968, i64 3984, i64 4000, i64 4016, i64 4032, i64 4048, i64 4064, i64 4080>
 ; AVX512-NEXT:    call void @llvm.masked.scatter.v16f32.v16p1f32(<16 x float> [[TMP78]], <16 x float addrspace(1)*> [[TMP79]], i32 4, <16 x i1> [[TMP76]])
 ; AVX512-NEXT:    ret void
 ;
 ; FVW2-LABEL: @foo2_addrspace3(
 ; FVW2-NEXT:  entry:
 ; FVW2-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; FVW2:       vector.body:
-; FVW2-NEXT:    [[INDEX6:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE30:%.*]] ]
-; FVW2-NEXT:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 0, i64 16>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE30]] ]
-; FVW2-NEXT:    [[STEP_ADD:%.*]] = add <2 x i64> [[VEC_IND]], <i64 32, i64 32>
-; FVW2-NEXT:    [[STEP_ADD7:%.*]] = add <2 x i64> [[VEC_IND]], <i64 64, i64 64>
-; FVW2-NEXT:    [[STEP_ADD8:%.*]] = add <2 x i64> [[VEC_IND]], <i64 96, i64 96>
+; FVW2-NEXT:    [[INDEX6:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE8:%.*]] ]
+; FVW2-NEXT:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 0, i64 16>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE8]] ]
 ; FVW2-NEXT:    [[OFFSET_IDX:%.*]] = shl i64 [[INDEX6]], 4
-; FVW2-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER:%.*]], <2 x i64> [[VEC_IND]]
-; FVW2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD]]
-; FVW2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD7]]
-; FVW2-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], <2 x i64> [[STEP_ADD8]]
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP0]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER10:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP1]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER11:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP2]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER12:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> [[TMP3]], i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
-; FVW2-NEXT:    [[TMP4:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER]], zeroinitializer
-; FVW2-NEXT:    [[TMP5:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER10]], zeroinitializer
-; FVW2-NEXT:    [[TMP6:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER11]], zeroinitializer
-; FVW2-NEXT:    [[TMP7:%.*]] = icmp sgt <2 x i32> [[WIDE_MASKED_GATHER12]], zeroinitializer
+; FVW2-NEXT:    [[TMP0:%.*]] = or i64 [[OFFSET_IDX]], 16
+; FVW2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER:%.*]], i64 [[OFFSET_IDX]]
+; FVW2-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TRIGGER]], i64 [[TMP0]]
+; FVW2-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]], align 4
+; FVW2-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]], align 4
+; FVW2-NEXT:    [[TMP5:%.*]] = insertelement <2 x i32> poison, i32 [[TMP3]], i32 0
+; FVW2-NEXT:    [[TMP6:%.*]] = insertelement <2 x i32> [[TMP5]], i32 [[TMP4]], i32 1
+; FVW2-NEXT:    [[TMP7:%.*]] = icmp sgt <2 x i32> [[TMP6]], zeroinitializer
 ; FVW2-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_IN:%.*]], %struct.In* [[IN:%.*]], <2 x i64> [[VEC_IND]], i32 1
-; FVW2-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_IN]], %struct.In* [[IN]], <2 x i64> [[STEP_ADD]], i32 1
-; FVW2-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [[STRUCT_IN]], %struct.In* [[IN]], <2 x i64> [[STEP_ADD7]], i32 1
-; FVW2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_IN]], %struct.In* [[IN]], <2 x i64> [[STEP_ADD8]], i32 1
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER13:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP8]], i32 4, <2 x i1> [[TMP4]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER14:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP9]], i32 4, <2 x i1> [[TMP5]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER15:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP10]], i32 4, <2 x i1> [[TMP6]], <2 x float> undef)
-; FVW2-NEXT:    [[WIDE_MASKED_GATHER16:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP11]], i32 4, <2 x i1> [[TMP7]], <2 x float> undef)
-; FVW2-NEXT:    [[TMP12:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER13]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP13:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER14]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP14:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER15]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP15:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER16]], <float 5.000000e-01, float 5.000000e-01>
-; FVW2-NEXT:    [[TMP16:%.*]] = extractelement <2 x i1> [[TMP4]], i32 0
-; FVW2-NEXT:    br i1 [[TMP16]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
+; FVW2-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> [[TMP8]], i32 4, <2 x i1> [[TMP7]], <2 x float> undef)
+; FVW2-NEXT:    [[TMP9:%.*]] = fadd <2 x float> [[WIDE_MASKED_GATHER]], <float 5.000000e-01, float 5.000000e-01>
+; FVW2-NEXT:    [[TMP10:%.*]] = extractelement <2 x i1> [[TMP7]], i32 0
+; FVW2-NEXT:    br i1 [[TMP10]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
 ; FVW2:       pred.store.if:
-; FVW2-NEXT:    [[TMP17:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT:%.*]], i64 [[OFFSET_IDX]]
-; FVW2-NEXT:    [[TMP18:%.*]] = extractelement <2 x float> [[TMP12]], i32 0
-; FVW2-NEXT:    store float [[TMP18]], float addrspace(1)* [[TMP17]], align 4
+; FVW2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT:%.*]], i64 [[OFFSET_IDX]]
+; FVW2-NEXT:    [[TMP12:%.*]] = extractelement <2 x float> [[TMP9]], i32 0
+; FVW2-NEXT:    store float [[TMP12]], float addrspace(1)* [[TMP11]], align 4
 ; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE]]
 ; FVW2:       pred.store.continue:
-; FVW2-NEXT:    [[TMP19:%.*]] = extractelement <2 x i1> [[TMP4]], i32 1
-; FVW2-NEXT:    br i1 [[TMP19]], label [[PRED_STORE_IF17:%.*]], label [[PRED_STORE_CONTINUE18:%.*]]
-; FVW2:       pred.store.if17:
-; FVW2-NEXT:    [[TMP20:%.*]] = or i64 [[OFFSET_IDX]], 16
-; FVW2-NEXT:    [[TMP21:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP20]]
-; FVW2-NEXT:    [[TMP22:%.*]] = extractelement <2 x float> [[TMP12]], i32 1
-; FVW2-NEXT:    store float [[TMP22]], float addrspace(1)* [[TMP21]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE18]]
-; FVW2:       pred.store.continue18:
-; FVW2-NEXT:    [[TMP23:%.*]] = extractelement <2 x i1> [[TMP5]], i32 0
-; FVW2-NEXT:    br i1 [[TMP23]], label [[PRED_STORE_IF19:%.*]], label [[PRED_STORE_CONTINUE20:%.*]]
-; FVW2:       pred.store.if19:
-; FVW2-NEXT:    [[TMP24:%.*]] = or i64 [[OFFSET_IDX]], 32
-; FVW2-NEXT:    [[TMP25:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP24]]
-; FVW2-NEXT:    [[TMP26:%.*]] = extractelement <2 x float> [[TMP13]], i32 0
-; FVW2-NEXT:    store float [[TMP26]], float addrspace(1)* [[TMP25]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE20]]
-; FVW2:       pred.store.continue20:
-; FVW2-NEXT:    [[TMP27:%.*]] = extractelement <2 x i1> [[TMP5]], i32 1
-; FVW2-NEXT:    br i1 [[TMP27]], label [[PRED_STORE_IF21:%.*]], label [[PRED_STORE_CONTINUE22:%.*]]
-; FVW2:       pred.store.if21:
-; FVW2-NEXT:    [[TMP28:%.*]] = or i64 [[OFFSET_IDX]], 48
-; FVW2-NEXT:    [[TMP29:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP28]]
-; FVW2-NEXT:    [[TMP30:%.*]] = extractelement <2 x float> [[TMP13]], i32 1
-; FVW2-NEXT:    store float [[TMP30]], float addrspace(1)* [[TMP29]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE22]]
-; FVW2:       pred.store.continue22:
-; FVW2-NEXT:    [[TMP31:%.*]] = extractelement <2 x i1> [[TMP6]], i32 0
-; FVW2-NEXT:    br i1 [[TMP31]], label [[PRED_STORE_IF23:%.*]], label [[PRED_STORE_CONTINUE24:%.*]]
-; FVW2:       pred.store.if23:
-; FVW2-NEXT:    [[TMP32:%.*]] = or i64 [[OFFSET_IDX]], 64
-; FVW2-NEXT:    [[TMP33:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP32]]
-; FVW2-NEXT:    [[TMP34:%.*]] = extractelement <2 x float> [[TMP14]], i32 0
-; FVW2-NEXT:    store float [[TMP34]], float addrspace(1)* [[TMP33]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE24]]
-; FVW2:       pred.store.continue24:
-; FVW2-NEXT:    [[TMP35:%.*]] = extractelement <2 x i1> [[TMP6]], i32 1
-; FVW2-NEXT:    br i1 [[TMP35]], label [[PRED_STORE_IF25:%.*]], label [[PRED_STORE_CONTINUE26:%.*]]
-; FVW2:       pred.store.if25:
-; FVW2-NEXT:    [[TMP36:%.*]] = or i64 [[OFFSET_IDX]], 80
-; FVW2-NEXT:    [[TMP37:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP36]]
-; FVW2-NEXT:    [[TMP38:%.*]] = extractelement <2 x float> [[TMP14]], i32 1
-; FVW2-NEXT:    store float [[TMP38]], float addrspace(1)* [[TMP37]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE26]]
-; FVW2:       pred.store.continue26:
-; FVW2-NEXT:    [[TMP39:%.*]] = extractelement <2 x i1> [[TMP7]], i32 0
-; FVW2-NEXT:    br i1 [[TMP39]], label [[PRED_STORE_IF27:%.*]], label [[PRED_STORE_CONTINUE28:%.*]]
-; FVW2:       pred.store.if27:
-; FVW2-NEXT:    [[TMP40:%.*]] = or i64 [[OFFSET_IDX]], 96
-; FVW2-NEXT:    [[TMP41:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP40]]
-; FVW2-NEXT:    [[TMP42:%.*]] = extractelement <2 x float> [[TMP15]], i32 0
-; FVW2-NEXT:    store float [[TMP42]], float addrspace(1)* [[TMP41]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE28]]
-; FVW2:       pred.store.continue28:
-; FVW2-NEXT:    [[TMP43:%.*]] = extractelement <2 x i1> [[TMP7]], i32 1
-; FVW2-NEXT:    br i1 [[TMP43]], label [[PRED_STORE_IF29:%.*]], label [[PRED_STORE_CONTINUE30]]
-; FVW2:       pred.store.if29:
-; FVW2-NEXT:    [[TMP44:%.*]] = or i64 [[OFFSET_IDX]], 112
-; FVW2-NEXT:    [[TMP45:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP44]]
-; FVW2-NEXT:    [[TMP46:%.*]] = extractelement <2 x float> [[TMP15]], i32 1
-; FVW2-NEXT:    store float [[TMP46]], float addrspace(1)* [[TMP45]], align 4
-; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE30]]
-; FVW2:       pred.store.continue30:
-; FVW2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX6]], 8
-; FVW2-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 128, i64 128>
-; FVW2-NEXT:    [[TMP47:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
-; FVW2-NEXT:    br i1 [[TMP47]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; FVW2-NEXT:    [[TMP13:%.*]] = extractelement <2 x i1> [[TMP7]], i32 1
+; FVW2-NEXT:    br i1 [[TMP13]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8]]
+; FVW2:       pred.store.if7:
+; FVW2-NEXT:    [[TMP14:%.*]] = getelementptr inbounds float, float addrspace(1)* [[OUT]], i64 [[TMP0]]
+; FVW2-NEXT:    [[TMP15:%.*]] = extractelement <2 x float> [[TMP9]], i32 1
+; FVW2-NEXT:    store float [[TMP15]], float addrspace(1)* [[TMP14]], align 4
+; FVW2-NEXT:    br label [[PRED_STORE_CONTINUE8]]
+; FVW2:       pred.store.continue8:
+; FVW2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX6]], 2
+; FVW2-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], <i64 32, i64 32>
+; FVW2-NEXT:    [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
+; FVW2-NEXT:    br i1 [[TMP16]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
 ; FVW2:       for.end:
 ; FVW2-NEXT:    ret void
 ;
 entry:
   %in.addr = alloca %struct.In addrspace(0)*, align 8
   %out.addr = alloca float addrspace(1)*, align 8
   %trigger.addr = alloca i32*, align 8
   %index.addr = alloca i32*, align 8

 ; FVW2-NEXT:    [[WIDE_LOAD16:%.*]] = load <2 x float>, <2 x float>* [[TMP18]], align 4, !alias.scope !7
 ; FVW2-NEXT:    call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> [[WIDE_LOAD]], <2 x float*> [[TMP13]], i32 4, <2 x i1> <i1 true, i1 true>), !alias.scope !10, !noalias !12
 ; FVW2-NEXT:    call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> [[WIDE_LOAD16]], <2 x float*> [[TMP14]], i32 4, <2 x i1> <i1 true, i1 true>), !alias.scope !10, !noalias !12
 ; FVW2-NEXT:    [[TMP19:%.*]] = bitcast float* [[NEXT_GEP]] to <2 x float>*
 ; FVW2-NEXT:    [[WIDE_LOAD17:%.*]] = load <2 x float>, <2 x float>* [[TMP19]], align 4, !alias.scope !14
 ; FVW2-NEXT:    [[TMP20:%.*]] = getelementptr float, float* [[NEXT_GEP]], i64 2
 ; FVW2-NEXT:    [[TMP21:%.*]] = bitcast float* [[TMP20]] to <2 x float>*
 ; FVW2-NEXT:    [[WIDE_LOAD18:%.*]] = load <2 x float>, <2 x float>* [[TMP21]], align 4, !alias.scope !14
-; FVW2-NEXT:    [[TMP22:%.*]] = getelementptr inbounds float, <2 x float*> [[TMP13]], i64 1
-; FVW2-NEXT:    [[TMP23:%.*]] = getelementptr inbounds float, <2 x float*> [[TMP14]], i64 1
-; FVW2-NEXT:    call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> [[WIDE_LOAD17]], <2 x float*> [[TMP22]], i32 4, <2 x i1> <i1 true, i1 true>), !alias.scope !10, !noalias !12
-; FVW2-NEXT:    call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> [[WIDE_LOAD18]], <2 x float*> [[TMP23]], i32 4, <2 x i1> <i1 true, i1 true>), !alias.scope !10, !noalias !12
+; FVW2-NEXT:    [[TMP22:%.*]] = extractelement <2 x float*> [[TMP13]], i32 0
+; FVW2-NEXT:    [[TMP23:%.*]] = getelementptr inbounds float, float* [[TMP22]], i64 1
+; FVW2-NEXT:    [[TMP24:%.*]] = extractelement <2 x float*> [[TMP13]], i32 1
+; FVW2-NEXT:    [[TMP25:%.*]] = getelementptr inbounds float, float* [[TMP24]], i64 1
+; FVW2-NEXT:    [[TMP26:%.*]] = extractelement <2 x float*> [[TMP14]], i32 0
+; FVW2-NEXT:    [[TMP27:%.*]] = getelementptr inbounds float, float* [[TMP26]], i64 1
+; FVW2-NEXT:    [[TMP28:%.*]] = extractelement <2 x float*> [[TMP14]], i32 1
+; FVW2-NEXT:    [[TMP29:%.*]] = getelementptr inbounds float, float* [[TMP28]], i64 1
+; FVW2-NEXT:    [[TMP30:%.*]] = extractelement <2 x float> [[WIDE_LOAD17]], i32 0
+; FVW2-NEXT:    store float [[TMP30]], float* [[TMP23]], align 4, !alias.scope !10, !noalias !12
+; FVW2-NEXT:    [[TMP31:%.*]] = extractelement <2 x float> [[WIDE_LOAD17]], i32 1
+; FVW2-NEXT:    store float [[TMP31]], float* [[TMP25]], align 4, !alias.scope !10, !noalias !12
+; FVW2-NEXT:    [[TMP32:%.*]] = extractelement <2 x float> [[WIDE_LOAD18]], i32 0
+; FVW2-NEXT:    store float [[TMP32]], float* [[TMP27]], align 4, !alias.scope !10, !noalias !12
+; FVW2-NEXT:    [[TMP33:%.*]] = extractelement <2 x float> [[WIDE_LOAD18]], i32 1
+; FVW2-NEXT:    store float [[TMP33]], float* [[TMP29]], align 4, !alias.scope !10, !noalias !12
 ; FVW2-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; FVW2-NEXT:    [[TMP24:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; FVW2-NEXT:    [[TMP34:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; FVW2-NEXT:    [[PTR_IND]] = getelementptr float, float* [[POINTER_PHI]], i64 64
-; FVW2-NEXT:    br i1 [[TMP24]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]]
+; FVW2-NEXT:    br i1 [[TMP34]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]]
 ; FVW2:       middle.block:
 ; FVW2-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP3]], [[N_VEC]]
 ; FVW2-NEXT:    br i1 [[CMP_N]], label [[FOR_END]], label [[FOR_BODY_PREHEADER]]
 ; FVW2:       for.body.preheader:
 ; FVW2-NEXT:    [[PTR_ADDR_012_PH:%.*]] = phi float* [ [[PTR]], [[VECTOR_MEMCHECK]] ], [ [[PTR]], [[FOR_BODY_LR_PH]] ], [ [[IND_END]], [[MIDDLE_BLOCK]] ]
 ; FVW2-NEXT:    [[DEST_ADDR_011_PH:%.*]] = phi float* [ [[DEST]], [[VECTOR_MEMCHECK]] ], [ [[DEST]], [[FOR_BODY_LR_PH]] ], [ [[IND_END14]], [[MIDDLE_BLOCK]] ]
 ; FVW2-NEXT:    br label [[FOR_BODY:%.*]]
 ; FVW2:       for.body:
 ; FVW2-NEXT:    [[PTR_ADDR_012:%.*]] = phi float* [ [[INCDEC_PTR:%.*]], [[FOR_BODY]] ], [ [[PTR_ADDR_012_PH]], [[FOR_BODY_PREHEADER]] ]
 ; FVW2-NEXT:    [[DEST_ADDR_011:%.*]] = phi float* [ [[ADD_PTR6:%.*]], [[FOR_BODY]] ], [ [[DEST_ADDR_011_PH]], [[FOR_BODY_PREHEADER]] ]
 ; FVW2-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[PTR_ADDR_012]], i64 [[IDXPROM]]
-; FVW2-NEXT:    [[TMP25:%.*]] = load float, float* [[ARRAYIDX]], align 4
-; FVW2-NEXT:    store float [[TMP25]], float* [[DEST_ADDR_011]], align 4
-; FVW2-NEXT:    [[TMP26:%.*]] = load float, float* [[PTR_ADDR_012]], align 4
+; FVW2-NEXT:    [[TMP35:%.*]] = load float, float* [[ARRAYIDX]], align 4
+; FVW2-NEXT:    store float [[TMP35]], float* [[DEST_ADDR_011]], align 4
+; FVW2-NEXT:    [[TMP36:%.*]] = load float, float* [[PTR_ADDR_012]], align 4
 ; FVW2-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds float, float* [[DEST_ADDR_011]], i64 1
-; FVW2-NEXT:    store float [[TMP26]], float* [[ARRAYIDX5]], align 4
+; FVW2-NEXT:    store float [[TMP36]], float* [[ARRAYIDX5]], align 4
 ; FVW2-NEXT:    [[INCDEC_PTR]] = getelementptr inbounds float, float* [[PTR_ADDR_012]], i64 1
 ; FVW2-NEXT:    [[ADD_PTR6]] = getelementptr inbounds float, float* [[DEST_ADDR_011]], i64 16
 ; FVW2-NEXT:    [[CMP_NOT:%.*]] = icmp eq float* [[INCDEC_PTR]], [[ADD_PTR]]
 ; FVW2-NEXT:    br i1 [[CMP_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
 ; FVW2:       for.end:
 ; FVW2-NEXT:    ret void
 ;
 entry: