; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mattr=+sse2 -cost-model -analyze | FileCheck %s --check-prefixes=SSE2
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mattr=+sse4.2 -cost-model -analyze | FileCheck %s --check-prefixes=SSE42
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mattr=+avx -cost-model -analyze | FileCheck %s --check-prefixes=AVX,AVX1
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mattr=+avx2 -cost-model -analyze | FileCheck %s --check-prefixes=AVX,AVX2
;
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mcpu=skylake -cost-model -analyze | FileCheck %s --check-prefixes=AVX,SKL
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mcpu=knl -cost-model -analyze | FileCheck %s --check-prefixes=AVX512,KNL
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mcpu=skx -cost-model -analyze | FileCheck %s --check-prefixes=AVX512,SKX

define i32 @masked_load() {
; SSE2-LABEL: 'masked_load'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V8F64 = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* undef, i32 1, <8 x i1> undef, <8 x double> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V7F64 = call <7 x double> @llvm.masked.load.v7f64.p0v7f64(<7 x double>* undef, i32 1, <7 x i1> undef, <7 x double> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V6F64 = call <6 x double> @llvm.masked.load.v6f64.p0v6f64(<6 x double>* undef, i32 1, <6 x i1> undef, <6 x double> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V5F64 = call <5 x double> @llvm.masked.load.v5f64.p0v5f64(<5 x double>* undef, i32 1, <5 x i1> undef, <5 x double> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V4F64 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* undef, i32 1, <4 x i1> undef, <4 x double> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V3F64 = call <3 x double> @llvm.masked.load.v3f64.p0v3f64(<3 x double>* undef, i32 1, <3 x i1> undef, <3 x double> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2F64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 1, <2 x i1> undef, <2 x double> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1F64 = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* undef, i32 1, <1 x i1> undef, <1 x double> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 75 for instruction: %V16F32 = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* undef, i32 1, <16 x i1> undef, <16 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 71 for instruction: %V15F32 = call <15 x float> @llvm.masked.load.v15f32.p0v15f32(<15 x float>* undef, i32 1, <15 x i1> undef, <15 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 67 for instruction: %V14F32 = call <14 x float> @llvm.masked.load.v14f32.p0v14f32(<14 x float>* undef, i32 1, <14 x i1> undef, <14 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 63 for instruction: %V13F32 = call <13 x float> @llvm.masked.load.v13f32.p0v13f32(<13 x float>* undef, i32 1, <13 x i1> undef, <13 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V12F32 = call <12 x float> @llvm.masked.load.v12f32.p0v12f32(<12 x float>* undef, i32 1, <12 x i1> undef, <12 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %V11F32 = call <11 x float> @llvm.masked.load.v11f32.p0v11f32(<11 x float>* undef, i32 1, <11 x i1> undef, <11 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V10F32 = call <10 x float> @llvm.masked.load.v10f32.p0v10f32(<10 x float>* undef, i32 1, <10 x i1> undef, <10 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V9F32 = call <9 x float> @llvm.masked.load.v9f32.p0v9f32(<9 x float>* undef, i32 1, <9 x i1> undef, <9 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8F32 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* undef, i32 1, <8 x i1> undef, <8 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V7F32 = call <7 x float> @llvm.masked.load.v7f32.p0v7f32(<7 x float>* undef, i32 1, <7 x i1> undef, <7 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V6F32 = call <6 x float> @llvm.masked.load.v6f32.p0v6f32(<6 x float>* undef, i32 1, <6 x i1> undef, <6 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V5F32 = call <5 x float> @llvm.masked.load.v5f32.p0v5f32(<5 x float>* undef, i32 1, <5 x i1> undef, <5 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V4F32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 1, <4 x i1> undef, <4 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V3F32 = call <3 x float> @llvm.masked.load.v3f32.p0v3f32(<3 x float>* undef, i32 1, <3 x i1> undef, <3 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2F32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 1, <2 x i1> undef, <2 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = call <1 x float> @llvm.masked.load.v1f32.p0v1f32(<1 x float>* undef, i32 1, <1 x i1> undef, <1 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V8I64 = call <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>* undef, i32 1, <8 x i1> undef, <8 x i64> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V7I64 = call <7 x i64> @llvm.masked.load.v7i64.p0v7i64(<7 x i64>* undef, i32 1, <7 x i1> undef, <7 x i64> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V6I64 = call <6 x i64> @llvm.masked.load.v6i64.p0v6i64(<6 x i64>* undef, i32 1, <6 x i1> undef, <6 x i64> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V5I64 = call <5 x i64> @llvm.masked.load.v5i64.p0v5i64(<5 x i64>* undef, i32 1, <5 x i1> undef, <5 x i64> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 1, <4 x i1> undef, <4 x i64> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V3I64 = call <3 x i64> @llvm.masked.load.v3i64.p0v3i64(<3 x i64>* undef, i32 1, <3 x i1> undef, <3 x i64> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2I64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 1, <2 x i1> undef, <2 x i64> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1I64 = call <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>* undef, i32 1, <1 x i1> undef, <1 x i64> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 91 for instruction: %V16I32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 1, <16 x i1> undef, <16 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V15I32 = call <15 x i32> @llvm.masked.load.v15i32.p0v15i32(<15 x i32>* undef, i32 1, <15 x i1> undef, <15 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 81 for instruction: %V14I32 = call <14 x i32> @llvm.masked.load.v14i32.p0v14i32(<14 x i32>* undef, i32 1, <14 x i1> undef, <14 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V13I32 = call <13 x i32> @llvm.masked.load.v13i32.p0v13i32(<13 x i32>* undef, i32 1, <13 x i1> undef, <13 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 71 for instruction: %V12I32 = call <12 x i32> @llvm.masked.load.v12i32.p0v12i32(<12 x i32>* undef, i32 1, <12 x i1> undef, <12 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V11I32 = call <11 x i32> @llvm.masked.load.v11i32.p0v11i32(<11 x i32>* undef, i32 1, <11 x i1> undef, <11 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %V10I32 = call <10 x i32> @llvm.masked.load.v10i32.p0v10i32(<10 x i32>* undef, i32 1, <10 x i1> undef, <10 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V9I32 = call <9 x i32> @llvm.masked.load.v9i32.p0v9i32(<9 x i32>* undef, i32 1, <9 x i1> undef, <9 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V8I32 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* undef, i32 1, <8 x i1> undef, <8 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V7I32 = call <7 x i32> @llvm.masked.load.v7i32.p0v7i32(<7 x i32>* undef, i32 1, <7 x i1> undef, <7 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V6I32 = call <6 x i32> @llvm.masked.load.v6i32.p0v6i32(<6 x i32>* undef, i32 1, <6 x i1> undef, <6 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V5I32 = call <5 x i32> @llvm.masked.load.v5i32.p0v5i32(<5 x i32>* undef, i32 1, <5 x i1> undef, <5 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V4I32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 1, <4 x i1> undef, <4 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V3I32 = call <3 x i32> @llvm.masked.load.v3i32.p0v3i32(<3 x i32>* undef, i32 1, <3 x i1> undef, <3 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 1, <2 x i1> undef, <2 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1I32 = call <1 x i32> @llvm.masked.load.v1i32.p0v1i32(<1 x i32>* undef, i32 1, <1 x i1> undef, <1 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 158 for instruction: %V32I16 = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* undef, i32 1, <32 x i1> undef, <32 x i16> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: %V16I16 = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* undef, i32 1, <16 x i1> undef, <16 x i16> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V8I16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 1, <8 x i1> undef, <8 x i16> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4I16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 1, <4 x i1> undef, <4 x i16> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 376 for instruction: %V64I8 = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* undef, i32 1, <64 x i1> undef, <64 x i8> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 188 for instruction: %V32I8 = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* undef, i32 1, <32 x i1> undef, <32 x i8> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V16I8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 1, <16 x i1> undef, <16 x i8> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V8I8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<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_load'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8F64 = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* undef, i32 1, <8 x i1> undef, <8 x double> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V7F64 = call <7 x double> @llvm.masked.load.v7f64.p0v7f64(<7 x double>* undef, i32 1, <7 x i1> undef, <7 x double> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V6F64 = call <6 x double> @llvm.masked.load.v6f64.p0v6f64(<6 x double>* undef, i32 1, <6 x i1> undef, <6 x double> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V5F64 = call <5 x double> @llvm.masked.load.v5f64.p0v5f64(<5 x double>* undef, i32 1, <5 x i1> undef, <5 x double> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4F64 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* undef, i32 1, <4 x i1> undef, <4 x double> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V3F64 = call <3 x double> @llvm.masked.load.v3f64.p0v3f64(<3 x double>* undef, i32 1, <3 x i1> undef, <3 x double> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2F64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 1, <2 x i1> undef, <2 x double> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1F64 = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* undef, i32 1, <1 x i1> undef, <1 x double> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V16F32 = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* undef, i32 1, <16 x i1> undef, <16 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V15F32 = call <15 x float> @llvm.masked.load.v15f32.p0v15f32(<15 x float>* undef, i32 1, <15 x i1> undef, <15 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V14F32 = call <14 x float> @llvm.masked.load.v14f32.p0v14f32(<14 x float>* undef, i32 1, <14 x i1> undef, <14 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V13F32 = call <13 x float> @llvm.masked.load.v13f32.p0v13f32(<13 x float>* undef, i32 1, <13 x i1> undef, <13 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V12F32 = call <12 x float> @llvm.masked.load.v12f32.p0v12f32(<12 x float>* undef, i32 1, <12 x i1> undef, <12 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 41 for instruction: %V11F32 = call <11 x float> @llvm.masked.load.v11f32.p0v11f32(<11 x float>* undef, i32 1, <11 x i1> undef, <11 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V10F32 = call <10 x float> @llvm.masked.load.v10f32.p0v10f32(<10 x float>* undef, i32 1, <10 x i1> undef, <10 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V9F32 = call <9 x float> @llvm.masked.load.v9f32.p0v9f32(<9 x float>* undef, i32 1, <9 x i1> undef, <9 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8F32 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* undef, i32 1, <8 x i1> undef, <8 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V7F32 = call <7 x float> @llvm.masked.load.v7f32.p0v7f32(<7 x float>* undef, i32 1, <7 x i1> undef, <7 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V6F32 = call <6 x float> @llvm.masked.load.v6f32.p0v6f32(<6 x float>* undef, i32 1, <6 x i1> undef, <6 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V5F32 = call <5 x float> @llvm.masked.load.v5f32.p0v5f32(<5 x float>* undef, i32 1, <5 x i1> undef, <5 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4F32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 1, <4 x i1> undef, <4 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V3F32 = call <3 x float> @llvm.masked.load.v3f32.p0v3f32(<3 x float>* undef, i32 1, <3 x i1> undef, <3 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2F32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 1, <2 x i1> undef, <2 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = call <1 x float> @llvm.masked.load.v1f32.p0v1f32(<1 x float>* undef, i32 1, <1 x i1> undef, <1 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>* undef, i32 1, <8 x i1> undef, <8 x i64> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V7I64 = call <7 x i64> @llvm.masked.load.v7i64.p0v7i64(<7 x i64>* undef, i32 1, <7 x i1> undef, <7 x i64> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V6I64 = call <6 x i64> @llvm.masked.load.v6i64.p0v6i64(<6 x i64>* undef, i32 1, <6 x i1> undef, <6 x i64> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V5I64 = call <5 x i64> @llvm.masked.load.v5i64.p0v5i64(<5 x i64>* undef, i32 1, <5 x i1> undef, <5 x i64> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 1, <4 x i1> undef, <4 x i64> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V3I64 = call <3 x i64> @llvm.masked.load.v3i64.p0v3i64(<3 x i64>* undef, i32 1, <3 x i1> undef, <3 x i64> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 1, <2 x i1> undef, <2 x i64> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1I64 = call <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>* undef, i32 1, <1 x i1> undef, <1 x i64> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V16I32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 1, <16 x i1> undef, <16 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V15I32 = call <15 x i32> @llvm.masked.load.v15i32.p0v15i32(<15 x i32>* undef, i32 1, <15 x i1> undef, <15 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V14I32 = call <14 x i32> @llvm.masked.load.v14i32.p0v14i32(<14 x i32>* undef, i32 1, <14 x i1> undef, <14 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V13I32 = call <13 x i32> @llvm.masked.load.v13i32.p0v13i32(<13 x i32>* undef, i32 1, <13 x i1> undef, <13 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V12I32 = call <12 x i32> @llvm.masked.load.v12i32.p0v12i32(<12 x i32>* undef, i32 1, <12 x i1> undef, <12 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V11I32 = call <11 x i32> @llvm.masked.load.v11i32.p0v11i32(<11 x i32>* undef, i32 1, <11 x i1> undef, <11 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V10I32 = call <10 x i32> @llvm.masked.load.v10i32.p0v10i32(<10 x i32>* undef, i32 1, <10 x i1> undef, <10 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V9I32 = call <9 x i32> @llvm.masked.load.v9i32.p0v9i32(<9 x i32>* undef, i32 1, <9 x i1> undef, <9 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I32 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* undef, i32 1, <8 x i1> undef, <8 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V7I32 = call <7 x i32> @llvm.masked.load.v7i32.p0v7i32(<7 x i32>* undef, i32 1, <7 x i1> undef, <7 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V6I32 = call <6 x i32> @llvm.masked.load.v6i32.p0v6i32(<6 x i32>* undef, i32 1, <6 x i1> undef, <6 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V5I32 = call <5 x i32> @llvm.masked.load.v5i32.p0v5i32(<5 x i32>* undef, i32 1, <5 x i1> undef, <5 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 1, <4 x i1> undef, <4 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V3I32 = call <3 x i32> @llvm.masked.load.v3i32.p0v3i32(<3 x i32>* undef, i32 1, <3 x i1> undef, <3 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 1, <2 x i1> undef, <2 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1I32 = call <1 x i32> @llvm.masked.load.v1i32.p0v1i32(<1 x i32>* undef, i32 1, <1 x i1> undef, <1 x i32> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V32I16 = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* undef, i32 1, <32 x i1> undef, <32 x i16> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V16I16 = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* undef, i32 1, <16 x i1> undef, <16 x i16> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 1, <8 x i1> undef, <8 x i16> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 1, <4 x i1> undef, <4 x i16> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %V64I8 = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* undef, i32 1, <64 x i1> undef, <64 x i8> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V32I8 = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* undef, i32 1, <32 x i1> undef, <32 x i8> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 1, <16 x i1> undef, <16 x i8> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<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
;
; AVX-LABEL: 'masked_load'
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* undef, i32 1, <8 x i1> undef, <8 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V7F64 = call <7 x double> @llvm.masked.load.v7f64.p0v7f64(<7 x double>* undef, i32 1, <7 x i1> undef, <7 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V6F64 = call <6 x double> @llvm.masked.load.v6f64.p0v6f64(<6 x double>* undef, i32 1, <6 x i1> undef, <6 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V5F64 = call <5 x double> @llvm.masked.load.v5f64.p0v5f64(<5 x double>* undef, i32 1, <5 x i1> undef, <5 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* undef, i32 1, <4 x i1> undef, <4 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V3F64 = call <3 x double> @llvm.masked.load.v3f64.p0v3f64(<3 x double>* undef, i32 1, <3 x i1> undef, <3 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 1, <2 x i1> undef, <2 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1F64 = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* undef, i32 1, <1 x i1> undef, <1 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* undef, i32 1, <16 x i1> undef, <16 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V15F32 = call <15 x float> @llvm.masked.load.v15f32.p0v15f32(<15 x float>* undef, i32 1, <15 x i1> undef, <15 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V14F32 = call <14 x float> @llvm.masked.load.v14f32.p0v14f32(<14 x float>* undef, i32 1, <14 x i1> undef, <14 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V13F32 = call <13 x float> @llvm.masked.load.v13f32.p0v13f32(<13 x float>* undef, i32 1, <13 x i1> undef, <13 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V12F32 = call <12 x float> @llvm.masked.load.v12f32.p0v12f32(<12 x float>* undef, i32 1, <12 x i1> undef, <12 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V11F32 = call <11 x float> @llvm.masked.load.v11f32.p0v11f32(<11 x float>* undef, i32 1, <11 x i1> undef, <11 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V10F32 = call <10 x float> @llvm.masked.load.v10f32.p0v10f32(<10 x float>* undef, i32 1, <10 x i1> undef, <10 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V9F32 = call <9 x float> @llvm.masked.load.v9f32.p0v9f32(<9 x float>* undef, i32 1, <9 x i1> undef, <9 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* undef, i32 1, <8 x i1> undef, <8 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V7F32 = call <7 x float> @llvm.masked.load.v7f32.p0v7f32(<7 x float>* undef, i32 1, <7 x i1> undef, <7 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V6F32 = call <6 x float> @llvm.masked.load.v6f32.p0v6f32(<6 x float>* undef, i32 1, <6 x i1> undef, <6 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V5F32 = call <5 x float> @llvm.masked.load.v5f32.p0v5f32(<5 x float>* undef, i32 1, <5 x i1> undef, <5 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 1, <4 x i1> undef, <4 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V3F32 = call <3 x float> @llvm.masked.load.v3f32.p0v3f32(<3 x float>* undef, i32 1, <3 x i1> undef, <3 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 1, <2 x i1> undef, <2 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = call <1 x float> @llvm.masked.load.v1f32.p0v1f32(<1 x float>* undef, i32 1, <1 x i1> undef, <1 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>* undef, i32 1, <8 x i1> undef, <8 x i64> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V7I64 = call <7 x i64> @llvm.masked.load.v7i64.p0v7i64(<7 x i64>* undef, i32 1, <7 x i1> undef, <7 x i64> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V6I64 = call <6 x i64> @llvm.masked.load.v6i64.p0v6i64(<6 x i64>* undef, i32 1, <6 x i1> undef, <6 x i64> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V5I64 = call <5 x i64> @llvm.masked.load.v5i64.p0v5i64(<5 x i64>* undef, i32 1, <5 x i1> undef, <5 x i64> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 1, <4 x i1> undef, <4 x i64> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V3I64 = call <3 x i64> @llvm.masked.load.v3i64.p0v3i64(<3 x i64>* undef, i32 1, <3 x i1> undef, <3 x i64> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 1, <2 x i1> undef, <2 x i64> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1I64 = call <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>* undef, i32 1, <1 x i1> undef, <1 x i64> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 1, <16 x i1> undef, <16 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V15I32 = call <15 x i32> @llvm.masked.load.v15i32.p0v15i32(<15 x i32>* undef, i32 1, <15 x i1> undef, <15 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V14I32 = call <14 x i32> @llvm.masked.load.v14i32.p0v14i32(<14 x i32>* undef, i32 1, <14 x i1> undef, <14 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V13I32 = call <13 x i32> @llvm.masked.load.v13i32.p0v13i32(<13 x i32>* undef, i32 1, <13 x i1> undef, <13 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V12I32 = call <12 x i32> @llvm.masked.load.v12i32.p0v12i32(<12 x i32>* undef, i32 1, <12 x i1> undef, <12 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V11I32 = call <11 x i32> @llvm.masked.load.v11i32.p0v11i32(<11 x i32>* undef, i32 1, <11 x i1> undef, <11 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V10I32 = call <10 x i32> @llvm.masked.load.v10i32.p0v10i32(<10 x i32>* undef, i32 1, <10 x i1> undef, <10 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V9I32 = call <9 x i32> @llvm.masked.load.v9i32.p0v9i32(<9 x i32>* undef, i32 1, <9 x i1> undef, <9 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* undef, i32 1, <8 x i1> undef, <8 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V7I32 = call <7 x i32> @llvm.masked.load.v7i32.p0v7i32(<7 x i32>* undef, i32 1, <7 x i1> undef, <7 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V6I32 = call <6 x i32> @llvm.masked.load.v6i32.p0v6i32(<6 x i32>* undef, i32 1, <6 x i1> undef, <6 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V5I32 = call <5 x i32> @llvm.masked.load.v5i32.p0v5i32(<5 x i32>* undef, i32 1, <5 x i1> undef, <5 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 1, <4 x i1> undef, <4 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V3I32 = call <3 x i32> @llvm.masked.load.v3i32.p0v3i32(<3 x i32>* undef, i32 1, <3 x i1> undef, <3 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 1, <2 x i1> undef, <2 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1I32 = call <1 x i32> @llvm.masked.load.v1i32.p0v1i32(<1 x i32>* undef, i32 1, <1 x i1> undef, <1 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 148 for instruction: %V32I16 = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* undef, i32 1, <32 x i1> undef, <32 x i16> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V16I16 = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* undef, i32 1, <16 x i1> undef, <16 x i16> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 1, <8 x i1> undef, <8 x i16> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 1, <4 x i1> undef, <4 x i16> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 292 for instruction: %V64I8 = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* undef, i32 1, <64 x i1> undef, <64 x i8> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %V32I8 = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* undef, i32 1, <32 x i1> undef, <32 x i8> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 1, <16 x i1> undef, <16 x i8> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* undef, i32 1, <8 x i1> undef, <8 x i8> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
;
; KNL-LABEL: 'masked_load'
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* undef, i32 1, <8 x i1> undef, <8 x double> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V7F64 = call <7 x double> @llvm.masked.load.v7f64.p0v7f64(<7 x double>* undef, i32 1, <7 x i1> undef, <7 x double> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V6F64 = call <6 x double> @llvm.masked.load.v6f64.p0v6f64(<6 x double>* undef, i32 1, <6 x i1> undef, <6 x double> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V5F64 = call <5 x double> @llvm.masked.load.v5f64.p0v5f64(<5 x double>* undef, i32 1, <5 x i1> undef, <5 x double> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* undef, i32 1, <4 x i1> undef, <4 x double> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V3F64 = call <3 x double> @llvm.masked.load.v3f64.p0v3f64(<3 x double>* undef, i32 1, <3 x i1> undef, <3 x double> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 1, <2 x i1> undef, <2 x double> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1F64 = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* undef, i32 1, <1 x i1> undef, <1 x double> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* undef, i32 1, <16 x i1> undef, <16 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V15F32 = call <15 x float> @llvm.masked.load.v15f32.p0v15f32(<15 x float>* undef, i32 1, <15 x i1> undef, <15 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V14F32 = call <14 x float> @llvm.masked.load.v14f32.p0v14f32(<14 x float>* undef, i32 1, <14 x i1> undef, <14 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V13F32 = call <13 x float> @llvm.masked.load.v13f32.p0v13f32(<13 x float>* undef, i32 1, <13 x i1> undef, <13 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V12F32 = call <12 x float> @llvm.masked.load.v12f32.p0v12f32(<12 x float>* undef, i32 1, <12 x i1> undef, <12 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V11F32 = call <11 x float> @llvm.masked.load.v11f32.p0v11f32(<11 x float>* undef, i32 1, <11 x i1> undef, <11 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V10F32 = call <10 x float> @llvm.masked.load.v10f32.p0v10f32(<10 x float>* undef, i32 1, <10 x i1> undef, <10 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V9F32 = call <9 x float> @llvm.masked.load.v9f32.p0v9f32(<9 x float>* undef, i32 1, <9 x i1> undef, <9 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* undef, i32 1, <8 x i1> undef, <8 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V7F32 = call <7 x float> @llvm.masked.load.v7f32.p0v7f32(<7 x float>* undef, i32 1, <7 x i1> undef, <7 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V6F32 = call <6 x float> @llvm.masked.load.v6f32.p0v6f32(<6 x float>* undef, i32 1, <6 x i1> undef, <6 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V5F32 = call <5 x float> @llvm.masked.load.v5f32.p0v5f32(<5 x float>* undef, i32 1, <5 x i1> undef, <5 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 1, <4 x i1> undef, <4 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V3F32 = call <3 x float> @llvm.masked.load.v3f32.p0v3f32(<3 x float>* undef, i32 1, <3 x i1> undef, <3 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 1, <2 x i1> undef, <2 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = call <1 x float> @llvm.masked.load.v1f32.p0v1f32(<1 x float>* undef, i32 1, <1 x i1> undef, <1 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>* undef, i32 1, <8 x i1> undef, <8 x i64> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V7I64 = call <7 x i64> @llvm.masked.load.v7i64.p0v7i64(<7 x i64>* undef, i32 1, <7 x i1> undef, <7 x i64> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V6I64 = call <6 x i64> @llvm.masked.load.v6i64.p0v6i64(<6 x i64>* undef, i32 1, <6 x i1> undef, <6 x i64> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V5I64 = call <5 x i64> @llvm.masked.load.v5i64.p0v5i64(<5 x i64>* undef, i32 1, <5 x i1> undef, <5 x i64> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 1, <4 x i1> undef, <4 x i64> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V3I64 = call <3 x i64> @llvm.masked.load.v3i64.p0v3i64(<3 x i64>* undef, i32 1, <3 x i1> undef, <3 x i64> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 1, <2 x i1> undef, <2 x i64> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1I64 = call <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>* undef, i32 1, <1 x i1> undef, <1 x i64> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 1, <16 x i1> undef, <16 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V15I32 = call <15 x i32> @llvm.masked.load.v15i32.p0v15i32(<15 x i32>* undef, i32 1, <15 x i1> undef, <15 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V14I32 = call <14 x i32> @llvm.masked.load.v14i32.p0v14i32(<14 x i32>* undef, i32 1, <14 x i1> undef, <14 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V13I32 = call <13 x i32> @llvm.masked.load.v13i32.p0v13i32(<13 x i32>* undef, i32 1, <13 x i1> undef, <13 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V12I32 = call <12 x i32> @llvm.masked.load.v12i32.p0v12i32(<12 x i32>* undef, i32 1, <12 x i1> undef, <12 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V11I32 = call <11 x i32> @llvm.masked.load.v11i32.p0v11i32(<11 x i32>* undef, i32 1, <11 x i1> undef, <11 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V10I32 = call <10 x i32> @llvm.masked.load.v10i32.p0v10i32(<10 x i32>* undef, i32 1, <10 x i1> undef, <10 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V9I32 = call <9 x i32> @llvm.masked.load.v9i32.p0v9i32(<9 x i32>* undef, i32 1, <9 x i1> undef, <9 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* undef, i32 1, <8 x i1> undef, <8 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V7I32 = call <7 x i32> @llvm.masked.load.v7i32.p0v7i32(<7 x i32>* undef, i32 1, <7 x i1> undef, <7 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V6I32 = call <6 x i32> @llvm.masked.load.v6i32.p0v6i32(<6 x i32>* undef, i32 1, <6 x i1> undef, <6 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V5I32 = call <5 x i32> @llvm.masked.load.v5i32.p0v5i32(<5 x i32>* undef, i32 1, <5 x i1> undef, <5 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 1, <4 x i1> undef, <4 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V3I32 = call <3 x i32> @llvm.masked.load.v3i32.p0v3i32(<3 x i32>* undef, i32 1, <3 x i1> undef, <3 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 1, <2 x i1> undef, <2 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1I32 = call <1 x i32> @llvm.masked.load.v1i32.p0v1i32(<1 x i32>* undef, i32 1, <1 x i1> undef, <1 x i32> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 148 for instruction: %V32I16 = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* undef, i32 1, <32 x i1> undef, <32 x i16> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V16I16 = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* undef, i32 1, <16 x i1> undef, <16 x i16> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 1, <8 x i1> undef, <8 x i16> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 1, <4 x i1> undef, <4 x i16> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 308 for instruction: %V64I8 = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* undef, i32 1, <64 x i1> undef, <64 x i8> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 146 for instruction: %V32I8 = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* undef, i32 1, <32 x i1> undef, <32 x i8> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 1, <16 x i1> undef, <16 x i8> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<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_load'
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* undef, i32 1, <8 x i1> undef, <8 x double> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V7F64 = call <7 x double> @llvm.masked.load.v7f64.p0v7f64(<7 x double>* undef, i32 1, <7 x i1> undef, <7 x double> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V6F64 = call <6 x double> @llvm.masked.load.v6f64.p0v6f64(<6 x double>* undef, i32 1, <6 x i1> undef, <6 x double> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V5F64 = call <5 x double> @llvm.masked.load.v5f64.p0v5f64(<5 x double>* undef, i32 1, <5 x i1> undef, <5 x double> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* undef, i32 1, <4 x i1> undef, <4 x double> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V3F64 = call <3 x double> @llvm.masked.load.v3f64.p0v3f64(<3 x double>* undef, i32 1, <3 x i1> undef, <3 x double> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 1, <2 x i1> undef, <2 x double> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1F64 = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* undef, i32 1, <1 x i1> undef, <1 x double> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* undef, i32 1, <16 x i1> undef, <16 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V15F32 = call <15 x float> @llvm.masked.load.v15f32.p0v15f32(<15 x float>* undef, i32 1, <15 x i1> undef, <15 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V14F32 = call <14 x float> @llvm.masked.load.v14f32.p0v14f32(<14 x float>* undef, i32 1, <14 x i1> undef, <14 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V13F32 = call <13 x float> @llvm.masked.load.v13f32.p0v13f32(<13 x float>* undef, i32 1, <13 x i1> undef, <13 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V12F32 = call <12 x float> @llvm.masked.load.v12f32.p0v12f32(<12 x float>* undef, i32 1, <12 x i1> undef, <12 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V11F32 = call <11 x float> @llvm.masked.load.v11f32.p0v11f32(<11 x float>* undef, i32 1, <11 x i1> undef, <11 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V10F32 = call <10 x float> @llvm.masked.load.v10f32.p0v10f32(<10 x float>* undef, i32 1, <10 x i1> undef, <10 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V9F32 = call <9 x float> @llvm.masked.load.v9f32.p0v9f32(<9 x float>* undef, i32 1, <9 x i1> undef, <9 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* undef, i32 1, <8 x i1> undef, <8 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V7F32 = call <7 x float> @llvm.masked.load.v7f32.p0v7f32(<7 x float>* undef, i32 1, <7 x i1> undef, <7 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V6F32 = call <6 x float> @llvm.masked.load.v6f32.p0v6f32(<6 x float>* undef, i32 1, <6 x i1> undef, <6 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V5F32 = call <5 x float> @llvm.masked.load.v5f32.p0v5f32(<5 x float>* undef, i32 1, <5 x i1> undef, <5 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 1, <4 x i1> undef, <4 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V3F32 = call <3 x float> @llvm.masked.load.v3f32.p0v3f32(<3 x float>* undef, i32 1, <3 x i1> undef, <3 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 1, <2 x i1> undef, <2 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = call <1 x float> @llvm.masked.load.v1f32.p0v1f32(<1 x float>* undef, i32 1, <1 x i1> undef, <1 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>* undef, i32 1, <8 x i1> undef, <8 x i64> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V7I64 = call <7 x i64> @llvm.masked.load.v7i64.p0v7i64(<7 x i64>* undef, i32 1, <7 x i1> undef, <7 x i64> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V6I64 = call <6 x i64> @llvm.masked.load.v6i64.p0v6i64(<6 x i64>* undef, i32 1, <6 x i1> undef, <6 x i64> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V5I64 = call <5 x i64> @llvm.masked.load.v5i64.p0v5i64(<5 x i64>* undef, i32 1, <5 x i1> undef, <5 x i64> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 1, <4 x i1> undef, <4 x i64> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V3I64 = call <3 x i64> @llvm.masked.load.v3i64.p0v3i64(<3 x i64>* undef, i32 1, <3 x i1> undef, <3 x i64> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 1, <2 x i1> undef, <2 x i64> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1I64 = call <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>* undef, i32 1, <1 x i1> undef, <1 x i64> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 1, <16 x i1> undef, <16 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V15I32 = call <15 x i32> @llvm.masked.load.v15i32.p0v15i32(<15 x i32>* undef, i32 1, <15 x i1> undef, <15 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V14I32 = call <14 x i32> @llvm.masked.load.v14i32.p0v14i32(<14 x i32>* undef, i32 1, <14 x i1> undef, <14 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V13I32 = call <13 x i32> @llvm.masked.load.v13i32.p0v13i32(<13 x i32>* undef, i32 1, <13 x i1> undef, <13 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V12I32 = call <12 x i32> @llvm.masked.load.v12i32.p0v12i32(<12 x i32>* undef, i32 1, <12 x i1> undef, <12 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V11I32 = call <11 x i32> @llvm.masked.load.v11i32.p0v11i32(<11 x i32>* undef, i32 1, <11 x i1> undef, <11 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V10I32 = call <10 x i32> @llvm.masked.load.v10i32.p0v10i32(<10 x i32>* undef, i32 1, <10 x i1> undef, <10 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V9I32 = call <9 x i32> @llvm.masked.load.v9i32.p0v9i32(<9 x i32>* undef, i32 1, <9 x i1> undef, <9 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* undef, i32 1, <8 x i1> undef, <8 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V7I32 = call <7 x i32> @llvm.masked.load.v7i32.p0v7i32(<7 x i32>* undef, i32 1, <7 x i1> undef, <7 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V6I32 = call <6 x i32> @llvm.masked.load.v6i32.p0v6i32(<6 x i32>* undef, i32 1, <6 x i1> undef, <6 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V5I32 = call <5 x i32> @llvm.masked.load.v5i32.p0v5i32(<5 x i32>* undef, i32 1, <5 x i1> undef, <5 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 1, <4 x i1> undef, <4 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V3I32 = call <3 x i32> @llvm.masked.load.v3i32.p0v3i32(<3 x i32>* undef, i32 1, <3 x i1> undef, <3 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 1, <2 x i1> undef, <2 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1I32 = call <1 x i32> @llvm.masked.load.v1i32.p0v1i32(<1 x i32>* undef, i32 1, <1 x i1> undef, <1 x i32> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* undef, i32 1, <32 x i1> undef, <32 x i16> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* undef, i32 1, <16 x i1> undef, <16 x i16> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 1, <8 x i1> undef, <8 x i16> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 1, <4 x i1> undef, <4 x i16> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* undef, i32 1, <64 x i1> undef, <64 x i8> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* undef, i32 1, <32 x i1> undef, <32 x i8> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 1, <16 x i1> undef, <16 x i8> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<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.load.v8f64.p0v8f64(<8 x double>* undef, i32 1, <8 x i1> undef, <8 x double> undef)
  %V7F64 = call <7 x double> @llvm.masked.load.v7f64.p0v7f64(<7 x double>* undef, i32 1, <7 x i1> undef, <7 x double> undef)
  %V6F64 = call <6 x double> @llvm.masked.load.v6f64.p0v6f64(<6 x double>* undef, i32 1, <6 x i1> undef, <6 x double> undef)
  %V5F64 = call <5 x double> @llvm.masked.load.v5f64.p0v5f64(<5 x double>* undef, i32 1, <5 x i1> undef, <5 x double> undef)
  %V4F64 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* undef, i32 1, <4 x i1> undef, <4 x double> undef)
  %V3F64 = call <3 x double> @llvm.masked.load.v3f64.p0v3f64(<3 x double>* undef, i32 1, <3 x i1> undef, <3 x double> undef)
  %V2F64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 1, <2 x i1> undef, <2 x double> undef)
  %V1F64 = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* undef, i32 1, <1 x i1> undef, <1 x double> undef)

  %V16F32 = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* undef, i32 1, <16 x i1> undef, <16 x float> undef)
  %V15F32 = call <15 x float> @llvm.masked.load.v15f32.p0v15f32(<15 x float>* undef, i32 1, <15 x i1> undef, <15 x float> undef)
  %V14F32 = call <14 x float> @llvm.masked.load.v14f32.p0v14f32(<14 x float>* undef, i32 1, <14 x i1> undef, <14 x float> undef)
  %V13F32 = call <13 x float> @llvm.masked.load.v13f32.p0v13f32(<13 x float>* undef, i32 1, <13 x i1> undef, <13 x float> undef)
  %V12F32 = call <12 x float> @llvm.masked.load.v12f32.p0v12f32(<12 x float>* undef, i32 1, <12 x i1> undef, <12 x float> undef)
  %V11F32 = call <11 x float> @llvm.masked.load.v11f32.p0v11f32(<11 x float>* undef, i32 1, <11 x i1> undef, <11 x float> undef)
  %V10F32 = call <10 x float> @llvm.masked.load.v10f32.p0v10f32(<10 x float>* undef, i32 1, <10 x i1> undef, <10 x float> undef)
  %V9F32 = call <9 x float> @llvm.masked.load.v9f32.p0v9f32(<9 x float>* undef, i32 1, <9 x i1> undef, <9 x float> undef)
  %V8F32 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* undef, i32 1, <8 x i1> undef, <8 x float> undef)
  %V7F32 = call <7 x float> @llvm.masked.load.v7f32.p0v7f32(<7 x float>* undef, i32 1, <7 x i1> undef, <7 x float> undef)
  %V6F32 = call <6 x float> @llvm.masked.load.v6f32.p0v6f32(<6 x float>* undef, i32 1, <6 x i1> undef, <6 x float> undef)
  %V5F32 = call <5 x float> @llvm.masked.load.v5f32.p0v5f32(<5 x float>* undef, i32 1, <5 x i1> undef, <5 x float> undef)
  %V4F32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 1, <4 x i1> undef, <4 x float> undef)
  %V3F32 = call <3 x float> @llvm.masked.load.v3f32.p0v3f32(<3 x float>* undef, i32 1, <3 x i1> undef, <3 x float> undef)
  %V2F32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 1, <2 x i1> undef, <2 x float> undef)
  %V1F32 = call <1 x float> @llvm.masked.load.v1f32.p0v1f32(<1 x float>* undef, i32 1, <1 x i1> undef, <1 x float> undef)

  %V8I64 = call <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>* undef, i32 1, <8 x i1> undef, <8 x i64> undef)
  %V7I64 = call <7 x i64> @llvm.masked.load.v7i64.p0v7i64(<7 x i64>* undef, i32 1, <7 x i1> undef, <7 x i64> undef)
  %V6I64 = call <6 x i64> @llvm.masked.load.v6i64.p0v6i64(<6 x i64>* undef, i32 1, <6 x i1> undef, <6 x i64> undef)
  %V5I64 = call <5 x i64> @llvm.masked.load.v5i64.p0v5i64(<5 x i64>* undef, i32 1, <5 x i1> undef, <5 x i64> undef)
  %V4I64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 1, <4 x i1> undef, <4 x i64> undef)
  %V3I64 = call <3 x i64> @llvm.masked.load.v3i64.p0v3i64(<3 x i64>* undef, i32 1, <3 x i1> undef, <3 x i64> undef)
  %V2I64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 1, <2 x i1> undef, <2 x i64> undef)
  %V1I64 = call <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>* undef, i32 1, <1 x i1> undef, <1 x i64> undef)

  %V16I32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 1, <16 x i1> undef, <16 x i32> undef)
  %V15I32 = call <15 x i32> @llvm.masked.load.v15i32.p0v15i32(<15 x i32>* undef, i32 1, <15 x i1> undef, <15 x i32> undef)
  %V14I32 = call <14 x i32> @llvm.masked.load.v14i32.p0v14i32(<14 x i32>* undef, i32 1, <14 x i1> undef, <14 x i32> undef)
  %V13I32 = call <13 x i32> @llvm.masked.load.v13i32.p0v13i32(<13 x i32>* undef, i32 1, <13 x i1> undef, <13 x i32> undef)
  %V12I32 = call <12 x i32> @llvm.masked.load.v12i32.p0v12i32(<12 x i32>* undef, i32 1, <12 x i1> undef, <12 x i32> undef)
  %V11I32 = call <11 x i32> @llvm.masked.load.v11i32.p0v11i32(<11 x i32>* undef, i32 1, <11 x i1> undef, <11 x i32> undef)
  %V10I32 = call <10 x i32> @llvm.masked.load.v10i32.p0v10i32(<10 x i32>* undef, i32 1, <10 x i1> undef, <10 x i32> undef)
  %V9I32 = call <9 x i32> @llvm.masked.load.v9i32.p0v9i32(<9 x i32>* undef, i32 1, <9 x i1> undef, <9 x i32> undef)
  %V8I32 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* undef, i32 1, <8 x i1> undef, <8 x i32> undef)
  %V7I32 = call <7 x i32> @llvm.masked.load.v7i32.p0v7i32(<7 x i32>* undef, i32 1, <7 x i1> undef, <7 x i32> undef)
  %V6I32 = call <6 x i32> @llvm.masked.load.v6i32.p0v6i32(<6 x i32>* undef, i32 1, <6 x i1> undef, <6 x i32> undef)
  %V5I32 = call <5 x i32> @llvm.masked.load.v5i32.p0v5i32(<5 x i32>* undef, i32 1, <5 x i1> undef, <5 x i32> undef)
  %V4I32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 1, <4 x i1> undef, <4 x i32> undef)
  %V3I32 = call <3 x i32> @llvm.masked.load.v3i32.p0v3i32(<3 x i32>* undef, i32 1, <3 x i1> undef, <3 x i32> undef)
  %V2I32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 1, <2 x i1> undef, <2 x i32> undef)
  %V1I32 = call <1 x i32> @llvm.masked.load.v1i32.p0v1i32(<1 x i32>* undef, i32 1, <1 x i1> undef, <1 x i32> undef)

  %V32I16 = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* undef, i32 1, <32 x i1> undef, <32 x i16> undef)
  %V16I16 = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* undef, i32 1, <16 x i1> undef, <16 x i16> undef)
  %V8I16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 1, <8 x i1> undef, <8 x i16> undef)
  %V4I16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 1, <4 x i1> undef, <4 x i16> undef)

  %V64I8 = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* undef, i32 1, <64 x i1> undef, <64 x i8> undef)
  %V32I8 = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* undef, i32 1, <32 x i1> undef, <32 x i8> undef)
  %V16I8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 1, <16 x i1> undef, <16 x i8> undef)
  %V8I8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* undef, i32 1, <8 x i1> undef, <8 x i8> undef)

  ret i32 0
}

define i32 @masked_store() {
; SSE2-LABEL: 'masked_store'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> undef, <8 x double>* undef, i32 1, <8 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.store.v7f64.p0v7f64(<7 x double> undef, <7 x double>* undef, i32 1, <7 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.masked.store.v6f64.p0v6f64(<6 x double> undef, <6 x double>* undef, i32 1, <6 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: call void @llvm.masked.store.v5f64.p0v5f64(<5 x double> undef, <5 x double>* undef, i32 1, <5 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> undef, <4 x double>* undef, i32 1, <4 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.store.v3f64.p0v3f64(<3 x double> undef, <3 x double>* undef, i32 1, <3 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> undef, <2 x double>* undef, i32 1, <2 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f64.p0v1f64(<1 x double> undef, <1 x double>* undef, i32 1, <1 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 75 for instruction: call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> undef, <16 x float>* undef, i32 1, <16 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: call void @llvm.masked.store.v15f32.p0v15f32(<15 x float> undef, <15 x float>* undef, i32 1, <15 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 65 for instruction: call void @llvm.masked.store.v14f32.p0v14f32(<14 x float> undef, <14 x float>* undef, i32 1, <14 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.store.v13f32.p0v13f32(<13 x float> undef, <13 x float>* undef, i32 1, <13 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: call void @llvm.masked.store.v12f32.p0v12f32(<12 x float> undef, <12 x float>* undef, i32 1, <12 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: call void @llvm.masked.store.v11f32.p0v11f32(<11 x float> undef, <11 x float>* undef, i32 1, <11 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: call void @llvm.masked.store.v10f32.p0v10f32(<10 x float> undef, <10 x float>* undef, i32 1, <10 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 41 for instruction: call void @llvm.masked.store.v9f32.p0v9f32(<9 x float> undef, <9 x float>* undef, i32 1, <9 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> undef, <8 x float>* undef, i32 1, <8 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v7f32.p0v7f32(<7 x float> undef, <7 x float>* undef, i32 1, <7 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: call void @llvm.masked.store.v6f32.p0v6f32(<6 x float> undef, <6 x float>* undef, i32 1, <6 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.store.v5f32.p0v5f32(<5 x float> undef, <5 x float>* undef, i32 1, <5 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> undef, <4 x float>* undef, i32 1, <4 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: call void @llvm.masked.store.v3f32.p0v3f32(<3 x float> undef, <3 x float>* undef, i32 1, <3 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> undef, <2 x float>* undef, i32 1, <2 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f32.p0v1f32(<1 x float> undef, <1 x float>* undef, i32 1, <1 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: call void @llvm.masked.store.v8i64.p0v8i64(<8 x i64> undef, <8 x i64>* undef, i32 1, <8 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: call void @llvm.masked.store.v7i64.p0v7i64(<7 x i64> undef, <7 x i64>* undef, i32 1, <7 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v6i64.p0v6i64(<6 x i64> undef, <6 x i64>* undef, i32 1, <6 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.masked.store.v5i64.p0v5i64(<5 x i64> undef, <5 x i64>* undef, i32 1, <5 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> undef, <4 x i64>* undef, i32 1, <4 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: call void @llvm.masked.store.v3i64.p0v3i64(<3 x i64> undef, <3 x i64>* undef, i32 1, <3 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> undef, <2 x i64>* undef, i32 1, <2 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i64.p0v1i64(<1 x i64> undef, <1 x i64>* undef, i32 1, <1 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 91 for instruction: call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> undef, <16 x i32>* undef, i32 1, <16 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 85 for instruction: call void @llvm.masked.store.v15i32.p0v15i32(<15 x i32> undef, <15 x i32>* undef, i32 1, <15 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: call void @llvm.masked.store.v14i32.p0v14i32(<14 x i32> undef, <14 x i32>* undef, i32 1, <14 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 73 for instruction: call void @llvm.masked.store.v13i32.p0v13i32(<13 x i32> undef, <13 x i32>* undef, i32 1, <13 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: call void @llvm.masked.store.v12i32.p0v12i32(<12 x i32> undef, <12 x i32>* undef, i32 1, <12 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: call void @llvm.masked.store.v11i32.p0v11i32(<11 x i32> undef, <11 x i32>* undef, i32 1, <11 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: call void @llvm.masked.store.v10i32.p0v10i32(<10 x i32> undef, <10 x i32>* undef, i32 1, <10 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: call void @llvm.masked.store.v9i32.p0v9i32(<9 x i32> undef, <9 x i32>* undef, i32 1, <9 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> undef, <8 x i32>* undef, i32 1, <8 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: call void @llvm.masked.store.v7i32.p0v7i32(<7 x i32> undef, <7 x i32>* undef, i32 1, <7 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: call void @llvm.masked.store.v6i32.p0v6i32(<6 x i32> undef, <6 x i32>* undef, i32 1, <6 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: call void @llvm.masked.store.v5i32.p0v5i32(<5 x i32> undef, <5 x i32>* undef, i32 1, <5 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> undef, <4 x i32>* undef, i32 1, <4 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v3i32.p0v3i32(<3 x i32> undef, <3 x i32>* undef, i32 1, <3 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> undef, <2 x i32>* undef, i32 1, <2 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i32.p0v1i32(<1 x i32> undef, <1 x i32>* undef, i32 1, <1 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 158 for instruction: call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> undef, <32 x i16>* undef, i32 1, <32 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> undef, <16 x i16>* undef, i32 1, <16 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> undef, <8 x i16>* undef, i32 1, <8 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> undef, <4 x i16>* undef, i32 1, <4 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 376 for instruction: call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> undef, <64 x i8>* undef, i32 1, <64 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 188 for instruction: call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> undef, <32 x i8>* undef, i32 1, <32 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: call void @llvm.masked.store.v8i8.p0v8i8(<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_store'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> undef, <8 x double>* undef, i32 1, <8 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.store.v7f64.p0v7f64(<7 x double> undef, <7 x double>* undef, i32 1, <7 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: call void @llvm.masked.store.v6f64.p0v6f64(<6 x double> undef, <6 x double>* undef, i32 1, <6 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v5f64.p0v5f64(<5 x double> undef, <5 x double>* undef, i32 1, <5 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> undef, <4 x double>* undef, i32 1, <4 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.store.v3f64.p0v3f64(<3 x double> undef, <3 x double>* undef, i32 1, <3 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> undef, <2 x double>* undef, i32 1, <2 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f64.p0v1f64(<1 x double> undef, <1 x double>* undef, i32 1, <1 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> undef, <16 x float>* undef, i32 1, <16 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: call void @llvm.masked.store.v15f32.p0v15f32(<15 x float> undef, <15 x float>* undef, i32 1, <15 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: call void @llvm.masked.store.v14f32.p0v14f32(<14 x float> undef, <14 x float>* undef, i32 1, <14 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.store.v13f32.p0v13f32(<13 x float> undef, <13 x float>* undef, i32 1, <13 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: call void @llvm.masked.store.v12f32.p0v12f32(<12 x float> undef, <12 x float>* undef, i32 1, <12 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 41 for instruction: call void @llvm.masked.store.v11f32.p0v11f32(<11 x float> undef, <11 x float>* undef, i32 1, <11 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: call void @llvm.masked.store.v10f32.p0v10f32(<10 x float> undef, <10 x float>* undef, i32 1, <10 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: call void @llvm.masked.store.v9f32.p0v9f32(<9 x float> undef, <9 x float>* undef, i32 1, <9 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> undef, <8 x float>* undef, i32 1, <8 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.masked.store.v7f32.p0v7f32(<7 x float> undef, <7 x float>* undef, i32 1, <7 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.store.v6f32.p0v6f32(<6 x float> undef, <6 x float>* undef, i32 1, <6 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.store.v5f32.p0v5f32(<5 x float> undef, <5 x float>* undef, i32 1, <5 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> undef, <4 x float>* undef, i32 1, <4 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.store.v3f32.p0v3f32(<3 x float> undef, <3 x float>* undef, i32 1, <3 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> undef, <2 x float>* undef, i32 1, <2 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f32.p0v1f32(<1 x float> undef, <1 x float>* undef, i32 1, <1 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i64.p0v8i64(<8 x i64> undef, <8 x i64>* undef, i32 1, <8 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.store.v7i64.p0v7i64(<7 x i64> undef, <7 x i64>* undef, i32 1, <7 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.store.v6i64.p0v6i64(<6 x i64> undef, <6 x i64>* undef, i32 1, <6 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.store.v5i64.p0v5i64(<5 x i64> undef, <5 x i64>* undef, i32 1, <5 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> undef, <4 x i64>* undef, i32 1, <4 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.store.v3i64.p0v3i64(<3 x i64> undef, <3 x i64>* undef, i32 1, <3 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> undef, <2 x i64>* undef, i32 1, <2 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i64.p0v1i64(<1 x i64> undef, <1 x i64>* undef, i32 1, <1 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> undef, <16 x i32>* undef, i32 1, <16 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.store.v15i32.p0v15i32(<15 x i32> undef, <15 x i32>* undef, i32 1, <15 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: call void @llvm.masked.store.v14i32.p0v14i32(<14 x i32> undef, <14 x i32>* undef, i32 1, <14 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: call void @llvm.masked.store.v13i32.p0v13i32(<13 x i32> undef, <13 x i32>* undef, i32 1, <13 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.store.v12i32.p0v12i32(<12 x i32> undef, <12 x i32>* undef, i32 1, <12 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: call void @llvm.masked.store.v11i32.p0v11i32(<11 x i32> undef, <11 x i32>* undef, i32 1, <11 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.store.v10i32.p0v10i32(<10 x i32> undef, <10 x i32>* undef, i32 1, <10 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.store.v9i32.p0v9i32(<9 x i32> undef, <9 x i32>* undef, i32 1, <9 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> undef, <8 x i32>* undef, i32 1, <8 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.store.v7i32.p0v7i32(<7 x i32> undef, <7 x i32>* undef, i32 1, <7 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.store.v6i32.p0v6i32(<6 x i32> undef, <6 x i32>* undef, i32 1, <6 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.store.v5i32.p0v5i32(<5 x i32> undef, <5 x i32>* undef, i32 1, <5 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> undef, <4 x i32>* undef, i32 1, <4 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.store.v3i32.p0v3i32(<3 x i32> undef, <3 x i32>* undef, i32 1, <3 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> undef, <2 x i32>* undef, i32 1, <2 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i32.p0v1i32(<1 x i32> undef, <1 x i32>* undef, i32 1, <1 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> undef, <32 x i16>* undef, i32 1, <32 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> undef, <16 x i16>* undef, i32 1, <16 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> undef, <8 x i16>* undef, i32 1, <8 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> undef, <4 x i16>* undef, i32 1, <4 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> undef, <64 x i8>* undef, i32 1, <64 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> undef, <32 x i8>* undef, i32 1, <32 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i8.p0v8i8(<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_store'
; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> undef, <8 x double>* undef, i32 1, <8 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v7f64.p0v7f64(<7 x double> undef, <7 x double>* undef, i32 1, <7 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v6f64.p0v6f64(<6 x double> undef, <6 x double>* undef, i32 1, <6 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v5f64.p0v5f64(<5 x double> undef, <5 x double>* undef, i32 1, <5 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> undef, <4 x double>* undef, i32 1, <4 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v3f64.p0v3f64(<3 x double> undef, <3 x double>* undef, i32 1, <3 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> undef, <2 x double>* undef, i32 1, <2 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f64.p0v1f64(<1 x double> undef, <1 x double>* undef, i32 1, <1 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> undef, <16 x float>* undef, i32 1, <16 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v15f32.p0v15f32(<15 x float> undef, <15 x float>* undef, i32 1, <15 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v14f32.p0v14f32(<14 x float> undef, <14 x float>* undef, i32 1, <14 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v13f32.p0v13f32(<13 x float> undef, <13 x float>* undef, i32 1, <13 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v12f32.p0v12f32(<12 x float> undef, <12 x float>* undef, i32 1, <12 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v11f32.p0v11f32(<11 x float> undef, <11 x float>* undef, i32 1, <11 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v10f32.p0v10f32(<10 x float> undef, <10 x float>* undef, i32 1, <10 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v9f32.p0v9f32(<9 x float> undef, <9 x float>* undef, i32 1, <9 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> undef, <8 x float>* undef, i32 1, <8 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v7f32.p0v7f32(<7 x float> undef, <7 x float>* undef, i32 1, <7 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v6f32.p0v6f32(<6 x float> undef, <6 x float>* undef, i32 1, <6 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v5f32.p0v5f32(<5 x float> undef, <5 x float>* undef, i32 1, <5 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> undef, <4 x float>* undef, i32 1, <4 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v3f32.p0v3f32(<3 x float> undef, <3 x float>* undef, i32 1, <3 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> undef, <2 x float>* undef, i32 1, <2 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f32.p0v1f32(<1 x float> undef, <1 x float>* undef, i32 1, <1 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v8i64.p0v8i64(<8 x i64> undef, <8 x i64>* undef, i32 1, <8 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v7i64.p0v7i64(<7 x i64> undef, <7 x i64>* undef, i32 1, <7 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v6i64.p0v6i64(<6 x i64> undef, <6 x i64>* undef, i32 1, <6 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v5i64.p0v5i64(<5 x i64> undef, <5 x i64>* undef, i32 1, <5 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> undef, <4 x i64>* undef, i32 1, <4 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v3i64.p0v3i64(<3 x i64> undef, <3 x i64>* undef, i32 1, <3 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> undef, <2 x i64>* undef, i32 1, <2 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i64.p0v1i64(<1 x i64> undef, <1 x i64>* undef, i32 1, <1 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> undef, <16 x i32>* undef, i32 1, <16 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v15i32.p0v15i32(<15 x i32> undef, <15 x i32>* undef, i32 1, <15 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v14i32.p0v14i32(<14 x i32> undef, <14 x i32>* undef, i32 1, <14 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v13i32.p0v13i32(<13 x i32> undef, <13 x i32>* undef, i32 1, <13 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v12i32.p0v12i32(<12 x i32> undef, <12 x i32>* undef, i32 1, <12 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v11i32.p0v11i32(<11 x i32> undef, <11 x i32>* undef, i32 1, <11 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v10i32.p0v10i32(<10 x i32> undef, <10 x i32>* undef, i32 1, <10 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v9i32.p0v9i32(<9 x i32> undef, <9 x i32>* undef, i32 1, <9 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> undef, <8 x i32>* undef, i32 1, <8 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v7i32.p0v7i32(<7 x i32> undef, <7 x i32>* undef, i32 1, <7 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v6i32.p0v6i32(<6 x i32> undef, <6 x i32>* undef, i32 1, <6 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v5i32.p0v5i32(<5 x i32> undef, <5 x i32>* undef, i32 1, <5 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> undef, <4 x i32>* undef, i32 1, <4 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v3i32.p0v3i32(<3 x i32> undef, <3 x i32>* undef, i32 1, <3 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> undef, <2 x i32>* undef, i32 1, <2 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i32.p0v1i32(<1 x i32> undef, <1 x i32>* undef, i32 1, <1 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> undef, <32 x i16>* undef, i32 1, <32 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> undef, <16 x i16>* undef, i32 1, <16 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> undef, <8 x i16>* undef, i32 1, <8 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> undef, <4 x i16>* undef, i32 1, <4 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> undef, <64 x i8>* undef, i32 1, <64 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> undef, <32 x i8>* undef, i32 1, <32 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i8.p0v8i8(<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_store'
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> undef, <8 x double>* undef, i32 1, <8 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v7f64.p0v7f64(<7 x double> undef, <7 x double>* undef, i32 1, <7 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v6f64.p0v6f64(<6 x double> undef, <6 x double>* undef, i32 1, <6 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v5f64.p0v5f64(<5 x double> undef, <5 x double>* undef, i32 1, <5 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> undef, <4 x double>* undef, i32 1, <4 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v3f64.p0v3f64(<3 x double> undef, <3 x double>* undef, i32 1, <3 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> undef, <2 x double>* undef, i32 1, <2 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f64.p0v1f64(<1 x double> undef, <1 x double>* undef, i32 1, <1 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> undef, <16 x float>* undef, i32 1, <16 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v15f32.p0v15f32(<15 x float> undef, <15 x float>* undef, i32 1, <15 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v14f32.p0v14f32(<14 x float> undef, <14 x float>* undef, i32 1, <14 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v13f32.p0v13f32(<13 x float> undef, <13 x float>* undef, i32 1, <13 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v12f32.p0v12f32(<12 x float> undef, <12 x float>* undef, i32 1, <12 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v11f32.p0v11f32(<11 x float> undef, <11 x float>* undef, i32 1, <11 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v10f32.p0v10f32(<10 x float> undef, <10 x float>* undef, i32 1, <10 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v9f32.p0v9f32(<9 x float> undef, <9 x float>* undef, i32 1, <9 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> undef, <8 x float>* undef, i32 1, <8 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v7f32.p0v7f32(<7 x float> undef, <7 x float>* undef, i32 1, <7 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v6f32.p0v6f32(<6 x float> undef, <6 x float>* undef, i32 1, <6 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v5f32.p0v5f32(<5 x float> undef, <5 x float>* undef, i32 1, <5 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> undef, <4 x float>* undef, i32 1, <4 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v3f32.p0v3f32(<3 x float> undef, <3 x float>* undef, i32 1, <3 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> undef, <2 x float>* undef, i32 1, <2 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f32.p0v1f32(<1 x float> undef, <1 x float>* undef, i32 1, <1 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8i64.p0v8i64(<8 x i64> undef, <8 x i64>* undef, i32 1, <8 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v7i64.p0v7i64(<7 x i64> undef, <7 x i64>* undef, i32 1, <7 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v6i64.p0v6i64(<6 x i64> undef, <6 x i64>* undef, i32 1, <6 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v5i64.p0v5i64(<5 x i64> undef, <5 x i64>* undef, i32 1, <5 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> undef, <4 x i64>* undef, i32 1, <4 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v3i64.p0v3i64(<3 x i64> undef, <3 x i64>* undef, i32 1, <3 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> undef, <2 x i64>* undef, i32 1, <2 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i64.p0v1i64(<1 x i64> undef, <1 x i64>* undef, i32 1, <1 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> undef, <16 x i32>* undef, i32 1, <16 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v15i32.p0v15i32(<15 x i32> undef, <15 x i32>* undef, i32 1, <15 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v14i32.p0v14i32(<14 x i32> undef, <14 x i32>* undef, i32 1, <14 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v13i32.p0v13i32(<13 x i32> undef, <13 x i32>* undef, i32 1, <13 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v12i32.p0v12i32(<12 x i32> undef, <12 x i32>* undef, i32 1, <12 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v11i32.p0v11i32(<11 x i32> undef, <11 x i32>* undef, i32 1, <11 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v10i32.p0v10i32(<10 x i32> undef, <10 x i32>* undef, i32 1, <10 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v9i32.p0v9i32(<9 x i32> undef, <9 x i32>* undef, i32 1, <9 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> undef, <8 x i32>* undef, i32 1, <8 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v7i32.p0v7i32(<7 x i32> undef, <7 x i32>* undef, i32 1, <7 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v6i32.p0v6i32(<6 x i32> undef, <6 x i32>* undef, i32 1, <6 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v5i32.p0v5i32(<5 x i32> undef, <5 x i32>* undef, i32 1, <5 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> undef, <4 x i32>* undef, i32 1, <4 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v3i32.p0v3i32(<3 x i32> undef, <3 x i32>* undef, i32 1, <3 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> undef, <2 x i32>* undef, i32 1, <2 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i32.p0v1i32(<1 x i32> undef, <1 x i32>* undef, i32 1, <1 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 168 for instruction: call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> undef, <32 x i16>* undef, i32 1, <32 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> undef, <16 x i16>* undef, i32 1, <16 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> undef, <8 x i16>* undef, i32 1, <8 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> undef, <4 x i16>* undef, i32 1, <4 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 352 for instruction: call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> undef, <64 x i8>* undef, i32 1, <64 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> undef, <32 x i8>* undef, i32 1, <32 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i8.p0v8i8(<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_store'
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> undef, <8 x double>* undef, i32 1, <8 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v7f64.p0v7f64(<7 x double> undef, <7 x double>* undef, i32 1, <7 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v6f64.p0v6f64(<6 x double> undef, <6 x double>* undef, i32 1, <6 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v5f64.p0v5f64(<5 x double> undef, <5 x double>* undef, i32 1, <5 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> undef, <4 x double>* undef, i32 1, <4 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v3f64.p0v3f64(<3 x double> undef, <3 x double>* undef, i32 1, <3 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> undef, <2 x double>* undef, i32 1, <2 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f64.p0v1f64(<1 x double> undef, <1 x double>* undef, i32 1, <1 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> undef, <16 x float>* undef, i32 1, <16 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v15f32.p0v15f32(<15 x float> undef, <15 x float>* undef, i32 1, <15 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v14f32.p0v14f32(<14 x float> undef, <14 x float>* undef, i32 1, <14 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v13f32.p0v13f32(<13 x float> undef, <13 x float>* undef, i32 1, <13 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v12f32.p0v12f32(<12 x float> undef, <12 x float>* undef, i32 1, <12 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v11f32.p0v11f32(<11 x float> undef, <11 x float>* undef, i32 1, <11 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v10f32.p0v10f32(<10 x float> undef, <10 x float>* undef, i32 1, <10 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v9f32.p0v9f32(<9 x float> undef, <9 x float>* undef, i32 1, <9 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> undef, <8 x float>* undef, i32 1, <8 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v7f32.p0v7f32(<7 x float> undef, <7 x float>* undef, i32 1, <7 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v6f32.p0v6f32(<6 x float> undef, <6 x float>* undef, i32 1, <6 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v5f32.p0v5f32(<5 x float> undef, <5 x float>* undef, i32 1, <5 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> undef, <4 x float>* undef, i32 1, <4 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v3f32.p0v3f32(<3 x float> undef, <3 x float>* undef, i32 1, <3 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> undef, <2 x float>* undef, i32 1, <2 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f32.p0v1f32(<1 x float> undef, <1 x float>* undef, i32 1, <1 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8i64.p0v8i64(<8 x i64> undef, <8 x i64>* undef, i32 1, <8 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v7i64.p0v7i64(<7 x i64> undef, <7 x i64>* undef, i32 1, <7 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v6i64.p0v6i64(<6 x i64> undef, <6 x i64>* undef, i32 1, <6 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v5i64.p0v5i64(<5 x i64> undef, <5 x i64>* undef, i32 1, <5 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> undef, <4 x i64>* undef, i32 1, <4 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v3i64.p0v3i64(<3 x i64> undef, <3 x i64>* undef, i32 1, <3 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> undef, <2 x i64>* undef, i32 1, <2 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i64.p0v1i64(<1 x i64> undef, <1 x i64>* undef, i32 1, <1 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> undef, <16 x i32>* undef, i32 1, <16 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v15i32.p0v15i32(<15 x i32> undef, <15 x i32>* undef, i32 1, <15 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v14i32.p0v14i32(<14 x i32> undef, <14 x i32>* undef, i32 1, <14 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v13i32.p0v13i32(<13 x i32> undef, <13 x i32>* undef, i32 1, <13 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v12i32.p0v12i32(<12 x i32> undef, <12 x i32>* undef, i32 1, <12 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v11i32.p0v11i32(<11 x i32> undef, <11 x i32>* undef, i32 1, <11 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v10i32.p0v10i32(<10 x i32> undef, <10 x i32>* undef, i32 1, <10 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v9i32.p0v9i32(<9 x i32> undef, <9 x i32>* undef, i32 1, <9 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> undef, <8 x i32>* undef, i32 1, <8 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v7i32.p0v7i32(<7 x i32> undef, <7 x i32>* undef, i32 1, <7 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v6i32.p0v6i32(<6 x i32> undef, <6 x i32>* undef, i32 1, <6 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v5i32.p0v5i32(<5 x i32> undef, <5 x i32>* undef, i32 1, <5 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> undef, <4 x i32>* undef, i32 1, <4 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v3i32.p0v3i32(<3 x i32> undef, <3 x i32>* undef, i32 1, <3 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> undef, <2 x i32>* undef, i32 1, <2 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i32.p0v1i32(<1 x i32> undef, <1 x i32>* undef, i32 1, <1 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> undef, <32 x i16>* undef, i32 1, <32 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> undef, <16 x i16>* undef, i32 1, <16 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> undef, <8 x i16>* undef, i32 1, <8 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> undef, <4 x i16>* undef, i32 1, <4 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> undef, <64 x i8>* undef, i32 1, <64 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> undef, <32 x i8>* undef, i32 1, <32 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v8i8.p0v8i8(<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.store.v8f64.p0v8f64(<8 x double> undef, <8 x double>* undef, i32 1, <8 x i1> undef)
  call void @llvm.masked.store.v7f64.p0v7f64(<7 x double> undef, <7 x double>* undef, i32 1, <7 x i1> undef)
  call void @llvm.masked.store.v6f64.p0v6f64(<6 x double> undef, <6 x double>* undef, i32 1, <6 x i1> undef)
  call void @llvm.masked.store.v5f64.p0v5f64(<5 x double> undef, <5 x double>* undef, i32 1, <5 x i1> undef)
  call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> undef, <4 x double>* undef, i32 1, <4 x i1> undef)
  call void @llvm.masked.store.v3f64.p0v3f64(<3 x double> undef, <3 x double>* undef, i32 1, <3 x i1> undef)
  call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> undef, <2 x double>* undef, i32 1, <2 x i1> undef)
  call void @llvm.masked.store.v1f64.p0v1f64(<1 x double> undef, <1 x double>* undef, i32 1, <1 x i1> undef)

  call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> undef, <16 x float>* undef, i32 1, <16 x i1> undef)
  call void @llvm.masked.store.v15f32.p0v15f32(<15 x float> undef, <15 x float>* undef, i32 1, <15 x i1> undef)
  call void @llvm.masked.store.v14f32.p0v14f32(<14 x float> undef, <14 x float>* undef, i32 1, <14 x i1> undef)
  call void @llvm.masked.store.v13f32.p0v13f32(<13 x float> undef, <13 x float>* undef, i32 1, <13 x i1> undef)
  call void @llvm.masked.store.v12f32.p0v12f32(<12 x float> undef, <12 x float>* undef, i32 1, <12 x i1> undef)
  call void @llvm.masked.store.v11f32.p0v11f32(<11 x float> undef, <11 x float>* undef, i32 1, <11 x i1> undef)
  call void @llvm.masked.store.v10f32.p0v10f32(<10 x float> undef, <10 x float>* undef, i32 1, <10 x i1> undef)
  call void @llvm.masked.store.v9f32.p0v9f32(<9 x float> undef, <9 x float>* undef, i32 1, <9 x i1> undef)
  call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> undef, <8 x float>* undef, i32 1, <8 x i1> undef)
  call void @llvm.masked.store.v7f32.p0v7f32(<7 x float> undef, <7 x float>* undef, i32 1, <7 x i1> undef)
  call void @llvm.masked.store.v6f32.p0v6f32(<6 x float> undef, <6 x float>* undef, i32 1, <6 x i1> undef)
  call void @llvm.masked.store.v5f32.p0v5f32(<5 x float> undef, <5 x float>* undef, i32 1, <5 x i1> undef)
  call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> undef, <4 x float>* undef, i32 1, <4 x i1> undef)
  call void @llvm.masked.store.v3f32.p0v3f32(<3 x float> undef, <3 x float>* undef, i32 1, <3 x i1> undef)
  call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> undef, <2 x float>* undef, i32 1, <2 x i1> undef)
  call void @llvm.masked.store.v1f32.p0v1f32(<1 x float> undef, <1 x float>* undef, i32 1, <1 x i1> undef)

  call void @llvm.masked.store.v8i64.p0v8i64(<8 x i64> undef, <8 x i64>* undef, i32 1, <8 x i1> undef)
  call void @llvm.masked.store.v7i64.p0v7i64(<7 x i64> undef, <7 x i64>* undef, i32 1, <7 x i1> undef)
  call void @llvm.masked.store.v6i64.p0v6i64(<6 x i64> undef, <6 x i64>* undef, i32 1, <6 x i1> undef)
  call void @llvm.masked.store.v5i64.p0v5i64(<5 x i64> undef, <5 x i64>* undef, i32 1, <5 x i1> undef)
  call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> undef, <4 x i64>* undef, i32 1, <4 x i1> undef)
  call void @llvm.masked.store.v3i64.p0v3i64(<3 x i64> undef, <3 x i64>* undef, i32 1, <3 x i1> undef)
  call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> undef, <2 x i64>* undef, i32 1, <2 x i1> undef)
  call void @llvm.masked.store.v1i64.p0v1i64(<1 x i64> undef, <1 x i64>* undef, i32 1, <1 x i1> undef)

  call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> undef, <16 x i32>* undef, i32 1, <16 x i1> undef)
  call void @llvm.masked.store.v15i32.p0v15i32(<15 x i32> undef, <15 x i32>* undef, i32 1, <15 x i1> undef)
  call void @llvm.masked.store.v14i32.p0v14i32(<14 x i32> undef, <14 x i32>* undef, i32 1, <14 x i1> undef)
  call void @llvm.masked.store.v13i32.p0v13i32(<13 x i32> undef, <13 x i32>* undef, i32 1, <13 x i1> undef)
  call void @llvm.masked.store.v12i32.p0v12i32(<12 x i32> undef, <12 x i32>* undef, i32 1, <12 x i1> undef)
  call void @llvm.masked.store.v11i32.p0v11i32(<11 x i32> undef, <11 x i32>* undef, i32 1, <11 x i1> undef)
  call void @llvm.masked.store.v10i32.p0v10i32(<10 x i32> undef, <10 x i32>* undef, i32 1, <10 x i1> undef)
  call void @llvm.masked.store.v9i32.p0v9i32(<9 x i32> undef, <9 x i32>* undef, i32 1, <9 x i1> undef)
  call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> undef, <8 x i32>* undef, i32 1, <8 x i1> undef)
  call void @llvm.masked.store.v7i32.p0v7i32(<7 x i32> undef, <7 x i32>* undef, i32 1, <7 x i1> undef)
  call void @llvm.masked.store.v6i32.p0v6i32(<6 x i32> undef, <6 x i32>* undef, i32 1, <6 x i1> undef)
  call void @llvm.masked.store.v5i32.p0v5i32(<5 x i32> undef, <5 x i32>* undef, i32 1, <5 x i1> undef)
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> undef, <4 x i32>* undef, i32 1, <4 x i1> undef)
  call void @llvm.masked.store.v3i32.p0v3i32(<3 x i32> undef, <3 x i32>* undef, i32 1, <3 x i1> undef)
  call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> undef, <2 x i32>* undef, i32 1, <2 x i1> undef)
  call void @llvm.masked.store.v1i32.p0v1i32(<1 x i32> undef, <1 x i32>* undef, i32 1, <1 x i1> undef)

  call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> undef, <32 x i16>* undef, i32 1, <32 x i1> undef)
  call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> undef, <16 x i16>* undef, i32 1, <16 x i1> undef)
  call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> undef, <8 x i16>* undef, i32 1, <8 x i1> undef)
  call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> undef, <4 x i16>* undef, i32 1, <4 x i1> undef)

  call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> undef, <64 x i8>* undef, i32 1, <64 x i1> undef)
  call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> undef, <32 x i8>* undef, i32 1, <32 x i1> undef)
  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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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)
  %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
  %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
  %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)

  %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
  %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
  %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
  %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)

  %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
  %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
  %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
  %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)

  %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
  %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
  %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
  %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)

  %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
  %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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)
  call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
  call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
  call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)

  call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
  call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
  call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
  call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)

  call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
  call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
  call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
  call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)

  call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
  call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
  call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
  call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)

  call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
  call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
  call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
  call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)

  ret i32 0
}

define i32 @masked_expandload() {
; SSE2-LABEL: 'masked_expandload'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.expandload.v8f64(double* undef, <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.expandload.v4f64(double* undef, <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.expandload.v2f64(double* undef, <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.expandload.v1f64(double* undef, <1 x i1> undef, <1 x double> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V16F32 = call <16 x float> @llvm.masked.expandload.v16f32(float* undef, <16 x i1> undef, <16 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = call <8 x float> @llvm.masked.expandload.v8f32(float* undef, <8 x i1> undef, <8 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.expandload.v4f32(float* undef, <4 x i1> undef, <4 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.expandload.v2f32(float* undef, <2 x i1> undef, <2 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8I64 = call <8 x i64> @llvm.masked.expandload.v8i64(i64* undef, <8 x i1> undef, <8 x i64> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.masked.expandload.v4i64(i64* undef, <4 x i1> undef, <4 x i64> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2I64 = call <2 x i64> @llvm.masked.expandload.v2i64(i64* undef, <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.expandload.v1i64(i64* undef, <1 x i1> undef, <1 x i64> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16I32 = call <16 x i32> @llvm.masked.expandload.v16i32(i32* undef, <16 x i1> undef, <16 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8I32 = call <8 x i32> @llvm.masked.expandload.v8i32(i32* undef, <8 x i1> undef, <8 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4I32 = call <4 x i32> @llvm.masked.expandload.v4i32(i32* undef, <4 x i1> undef, <4 x i32> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2I32 = call <2 x i32> @llvm.masked.expandload.v2i32(i32* undef, <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.expandload.v32i16(i16* undef, <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.expandload.v16i16(i16* undef, <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.expandload.v8i16(i16* undef, <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.expandload.v4i16(i16* undef, <4 x i1> undef, <4 x i16> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 188 for instruction: %V64I8 = call <64 x i8> @llvm.masked.expandload.v64i8(i8* undef, <64 x i1> undef, <64 x i8> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V32I8 = call <32 x i8> @llvm.masked.expandload.v32i8(i8* undef, <32 x i1> undef, <32 x i8> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V16I8 = call <16 x i8> @llvm.masked.expandload.v16i8(i8* undef, <16 x i1> undef, <16 x i8> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V8I8 = call <8 x i8> @llvm.masked.expandload.v8i8(i8* undef, <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_expandload'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.expandload.v8f64(double* undef, <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.expandload.v4f64(double* undef, <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.expandload.v2f64(double* undef, <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.expandload.v1f64(double* undef, <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.expandload.v16f32(float* undef, <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.expandload.v8f32(float* undef, <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.expandload.v4f32(float* undef, <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.expandload.v2f32(float* undef, <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.expandload.v8i64(i64* undef, <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.expandload.v4i64(i64* undef, <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.expandload.v2i64(i64* undef, <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.expandload.v1i64(i64* undef, <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.expandload.v16i32(i32* undef, <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.expandload.v8i32(i32* undef, <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.expandload.v4i32(i32* undef, <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.expandload.v2i32(i32* undef, <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.expandload.v32i16(i16* undef, <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.expandload.v16i16(i16* undef, <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.expandload.v8i16(i16* undef, <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.expandload.v4i16(i16* undef, <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.expandload.v64i8(i8* undef, <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.expandload.v32i8(i8* undef, <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.expandload.v16i8(i8* undef, <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.expandload.v8i8(i8* undef, <8 x i1> undef, <8 x i8> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
;
; AVX-LABEL: 'masked_expandload'
; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8F64 = call <8 x double> @llvm.masked.expandload.v8f64(double* undef, <8 x i1> undef, <8 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F64 = call <4 x double> @llvm.masked.expandload.v4f64(double* undef, <4 x i1> undef, <4 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.expandload.v2f64(double* undef, <2 x i1> undef, <2 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.expandload.v1f64(double* undef, <1 x i1> undef, <1 x double> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x float> @llvm.masked.expandload.v16f32(float* undef, <16 x i1> undef, <16 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x float> @llvm.masked.expandload.v8f32(float* undef, <8 x i1> undef, <8 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.expandload.v4f32(float* undef, <4 x i1> undef, <4 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.expandload.v2f32(float* undef, <2 x i1> undef, <2 x float> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8I64 = call <8 x i64> @llvm.masked.expandload.v8i64(i64* undef, <8 x i1> undef, <8 x i64> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.masked.expandload.v4i64(i64* undef, <4 x i1> undef, <4 x i64> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.expandload.v2i64(i64* undef, <2 x i1> undef, <2 x i64> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.expandload.v1i64(i64* undef, <1 x i1> undef, <1 x i64> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16I32 = call <16 x i32> @llvm.masked.expandload.v16i32(i32* undef, <16 x i1> undef, <16 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8I32 = call <8 x i32> @llvm.masked.expandload.v8i32(i32* undef, <8 x i1> undef, <8 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.expandload.v4i32(i32* undef, <4 x i1> undef, <4 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.expandload.v2i32(i32* undef, <2 x i1> undef, <2 x i32> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V32I16 = call <32 x i16> @llvm.masked.expandload.v32i16(i16* undef, <32 x i1> undef, <32 x i16> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call <16 x i16> @llvm.masked.expandload.v16i16(i16* undef, <16 x i1> undef, <16 x i16> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.expandload.v8i16(i16* undef, <8 x i1> undef, <8 x i16> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.expandload.v4i16(i16* undef, <4 x i1> undef, <4 x i16> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 132 for instruction: %V64I8 = call <64 x i8> @llvm.masked.expandload.v64i8(i8* undef, <64 x i1> undef, <64 x i8> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V32I8 = call <32 x i8> @llvm.masked.expandload.v32i8(i8* undef, <32 x i1> undef, <32 x i8> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.masked.expandload.v16i8(i8* undef, <16 x i1> undef, <16 x i8> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.masked.expandload.v8i8(i8* undef, <8 x i1> undef, <8 x i8> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
;
; AVX512-LABEL: 'masked_expandload'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V8F64 = call <8 x double> @llvm.masked.expandload.v8f64(double* undef, <8 x i1> undef, <8 x double> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F64 = call <4 x double> @llvm.masked.expandload.v4f64(double* undef, <4 x i1> undef, <4 x double> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.expandload.v2f64(double* undef, <2 x i1> undef, <2 x double> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.expandload.v1f64(double* undef, <1 x i1> undef, <1 x double> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x float> @llvm.masked.expandload.v16f32(float* undef, <16 x i1> undef, <16 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x float> @llvm.masked.expandload.v8f32(float* undef, <8 x i1> undef, <8 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.expandload.v4f32(float* undef, <4 x i1> undef, <4 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.expandload.v2f32(float* undef, <2 x i1> undef, <2 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8I64 = call <8 x i64> @llvm.masked.expandload.v8i64(i64* undef, <8 x i1> undef, <8 x i64> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.masked.expandload.v4i64(i64* undef, <4 x i1> undef, <4 x i64> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.expandload.v2i64(i64* undef, <2 x i1> undef, <2 x i64> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.expandload.v1i64(i64* undef, <1 x i1> undef, <1 x i64> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16I32 = call <16 x i32> @llvm.masked.expandload.v16i32(i32* undef, <16 x i1> undef, <16 x i32> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8I32 = call <8 x i32> @llvm.masked.expandload.v8i32(i32* undef, <8 x i1> undef, <8 x i32> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.expandload.v4i32(i32* undef, <4 x i1> undef, <4 x i32> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.expandload.v2i32(i32* undef, <2 x i1> undef, <2 x i32> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V32I16 = call <32 x i16> @llvm.masked.expandload.v32i16(i16* undef, <32 x i1> undef, <32 x i16> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call <16 x i16> @llvm.masked.expandload.v16i16(i16* undef, <16 x i1> undef, <16 x i16> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.expandload.v8i16(i16* undef, <8 x i1> undef, <8 x i16> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.expandload.v4i16(i16* undef, <4 x i1> undef, <4 x i16> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 132 for instruction: %V64I8 = call <64 x i8> @llvm.masked.expandload.v64i8(i8* undef, <64 x i1> undef, <64 x i8> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V32I8 = call <32 x i8> @llvm.masked.expandload.v32i8(i8* undef, <32 x i1> undef, <32 x i8> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.masked.expandload.v16i8(i8* undef, <16 x i1> undef, <16 x i8> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.masked.expandload.v8i8(i8* undef, <8 x i1> undef, <8 x i8> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
;
  %V8F64 = call <8 x double> @llvm.masked.expandload.v8f64(double* undef, <8 x i1> undef, <8 x double> undef)
  %V4F64 = call <4 x double> @llvm.masked.expandload.v4f64(double* undef, <4 x i1> undef, <4 x double> undef)
  %V2F64 = call <2 x double> @llvm.masked.expandload.v2f64(double* undef, <2 x i1> undef, <2 x double> undef)
  %V1F64 = call <1 x double> @llvm.masked.expandload.v1f64(double* undef, <1 x i1> undef, <1 x double> undef)

  %V16F32 = call <16 x float> @llvm.masked.expandload.v16f32(float* undef, <16 x i1> undef, <16 x float> undef)
  %V8F32 = call <8 x float> @llvm.masked.expandload.v8f32(float* undef, <8 x i1> undef, <8 x float> undef)
  %V4F32 = call <4 x float> @llvm.masked.expandload.v4f32(float* undef, <4 x i1> undef, <4 x float> undef)
  %V2F32 = call <2 x float> @llvm.masked.expandload.v2f32(float* undef, <2 x i1> undef, <2 x float> undef)

  %V8I64 = call <8 x i64> @llvm.masked.expandload.v8i64(i64* undef, <8 x i1> undef, <8 x i64> undef)
  %V4I64 = call <4 x i64> @llvm.masked.expandload.v4i64(i64* undef, <4 x i1> undef, <4 x i64> undef)
  %V2I64 = call <2 x i64> @llvm.masked.expandload.v2i64(i64* undef, <2 x i1> undef, <2 x i64> undef)
  %V1I64 = call <1 x i64> @llvm.masked.expandload.v1i64(i64* undef, <1 x i1> undef, <1 x i64> undef)

  %V16I32 = call <16 x i32> @llvm.masked.expandload.v16i32(i32* undef, <16 x i1> undef, <16 x i32> undef)
  %V8I32 = call <8 x i32> @llvm.masked.expandload.v8i32(i32* undef, <8 x i1> undef, <8 x i32> undef)
  %V4I32 = call <4 x i32> @llvm.masked.expandload.v4i32(i32* undef, <4 x i1> undef, <4 x i32> undef)
  %V2I32 = call <2 x i32> @llvm.masked.expandload.v2i32(i32* undef, <2 x i1> undef, <2 x i32> undef)

  %V32I16 = call <32 x i16> @llvm.masked.expandload.v32i16(i16* undef, <32 x i1> undef, <32 x i16> undef)
  %V16I16 = call <16 x i16> @llvm.masked.expandload.v16i16(i16* undef, <16 x i1> undef, <16 x i16> undef)
  %V8I16 = call <8 x i16> @llvm.masked.expandload.v8i16(i16* undef, <8 x i1> undef, <8 x i16> undef)
  %V4I16 = call <4 x i16> @llvm.masked.expandload.v4i16(i16* undef, <4 x i1> undef, <4 x i16> undef)

  %V64I8 = call <64 x i8> @llvm.masked.expandload.v64i8(i8* undef, <64 x i1> undef, <64 x i8> undef)
  %V32I8 = call <32 x i8> @llvm.masked.expandload.v32i8(i8* undef, <32 x i1> undef, <32 x i8> undef)
  %V16I8 = call <16 x i8> @llvm.masked.expandload.v16i8(i8* undef, <16 x i1> undef, <16 x i8> undef)
  %V8I8 = call <8 x i8> @llvm.masked.expandload.v8i8(i8* undef, <8 x i1> undef, <8 x i8> undef)

  ret i32 0
}

define i32 @masked_compressstore() {
; SSE2-LABEL: 'masked_compressstore'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.compressstore.v8f64(<8 x double> undef, double* undef, <8 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: call void @llvm.masked.compressstore.v4f64(<4 x double> undef, double* undef, <4 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.compressstore.v2f64(<2 x double> undef, double* undef, <2 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1f64(<1 x double> undef, double* undef, <1 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: call void @llvm.masked.compressstore.v16f32(<16 x float> undef, float* undef, <16 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.compressstore.v8f32(<8 x float> undef, float* undef, <8 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.compressstore.v4f32(<4 x float> undef, float* undef, <4 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.compressstore.v2f32(<2 x float> undef, float* undef, <2 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.compressstore.v8i64(<8 x i64> undef, i64* undef, <8 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.compressstore.v4i64(<4 x i64> undef, i64* undef, <4 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.compressstore.v2i64(<2 x i64> undef, i64* undef, <2 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1i64(<1 x i64> undef, i64* undef, <1 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 75 for instruction: call void @llvm.masked.compressstore.v16i32(<16 x i32> undef, i32* undef, <16 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.compressstore.v8i32(<8 x i32> undef, i32* undef, <8 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.compressstore.v4i32(<4 x i32> undef, i32* undef, <4 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.compressstore.v2i32(<2 x i32> undef, i32* undef, <2 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 126 for instruction: call void @llvm.masked.compressstore.v32i16(<32 x i16> undef, i16* undef, <32 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 63 for instruction: call void @llvm.masked.compressstore.v16i16(<16 x i16> undef, i16* undef, <16 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.compressstore.v8i16(<8 x i16> undef, i16* undef, <8 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: call void @llvm.masked.compressstore.v4i16(<4 x i16> undef, i16* undef, <4 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 312 for instruction: call void @llvm.masked.compressstore.v64i8(<64 x i8> undef, i8* undef, <64 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 156 for instruction: call void @llvm.masked.compressstore.v32i8(<32 x i8> undef, i8* undef, <32 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: call void @llvm.masked.compressstore.v16i8(<16 x i8> undef, i8* undef, <16 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: call void @llvm.masked.compressstore.v8i8(<8 x i8> undef, i8* undef, <8 x i1> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
;
; SSE42-LABEL: 'masked_compressstore'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.compressstore.v8f64(<8 x double> undef, double* undef, <8 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.compressstore.v4f64(<4 x double> undef, double* undef, <4 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2f64(<2 x double> undef, double* undef, <2 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1f64(<1 x double> undef, double* undef, <1 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: call void @llvm.masked.compressstore.v16f32(<16 x float> undef, float* undef, <16 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.compressstore.v8f32(<8 x float> undef, float* undef, <8 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.compressstore.v4f32(<4 x float> undef, float* undef, <4 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2f32(<2 x float> undef, float* undef, <2 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.compressstore.v8i64(<8 x i64> undef, i64* undef, <8 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v4i64(<4 x i64> undef, i64* undef, <4 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.compressstore.v2i64(<2 x i64> undef, i64* undef, <2 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1i64(<1 x i64> undef, i64* undef, <1 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.compressstore.v16i32(<16 x i32> undef, i32* undef, <16 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.compressstore.v8i32(<8 x i32> undef, i32* undef, <8 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v4i32(<4 x i32> undef, i32* undef, <4 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.compressstore.v2i32(<2 x i32> undef, i32* undef, <2 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.compressstore.v32i16(<32 x i16> undef, i16* undef, <32 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.compressstore.v16i16(<16 x i16> undef, i16* undef, <16 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.compressstore.v8i16(<8 x i16> undef, i16* undef, <8 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v4i16(<4 x i16> undef, i16* undef, <4 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: call void @llvm.masked.compressstore.v64i8(<64 x i8> undef, i8* undef, <64 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.compressstore.v32i8(<32 x i8> undef, i8* undef, <32 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.compressstore.v16i8(<16 x i8> undef, i8* undef, <16 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.compressstore.v8i8(<8 x i8> undef, i8* undef, <8 x i1> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
;
; AVX-LABEL: 'masked_compressstore'
; AVX-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.compressstore.v8f64(<8 x double> undef, double* undef, <8 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v4f64(<4 x double> undef, double* undef, <4 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2f64(<2 x double> undef, double* undef, <2 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1f64(<1 x double> undef, double* undef, <1 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: call void @llvm.masked.compressstore.v16f32(<16 x float> undef, float* undef, <16 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.masked.compressstore.v8f32(<8 x float> undef, float* undef, <8 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.compressstore.v4f32(<4 x float> undef, float* undef, <4 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2f32(<2 x float> undef, float* undef, <2 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.compressstore.v8i64(<8 x i64> undef, i64* undef, <8 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.compressstore.v4i64(<4 x i64> undef, i64* undef, <4 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.compressstore.v2i64(<2 x i64> undef, i64* undef, <2 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1i64(<1 x i64> undef, i64* undef, <1 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: call void @llvm.masked.compressstore.v16i32(<16 x i32> undef, i32* undef, <16 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.compressstore.v8i32(<8 x i32> undef, i32* undef, <8 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v4i32(<4 x i32> undef, i32* undef, <4 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.compressstore.v2i32(<2 x i32> undef, i32* undef, <2 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.compressstore.v32i16(<32 x i16> undef, i16* undef, <32 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: call void @llvm.masked.compressstore.v16i16(<16 x i16> undef, i16* undef, <16 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.compressstore.v8i16(<8 x i16> undef, i16* undef, <8 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v4i16(<4 x i16> undef, i16* undef, <4 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: call void @llvm.masked.compressstore.v64i8(<64 x i8> undef, i8* undef, <64 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.compressstore.v32i8(<32 x i8> undef, i8* undef, <32 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.compressstore.v16i8(<16 x i8> undef, i8* undef, <16 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.compressstore.v8i8(<8 x i8> undef, i8* undef, <8 x i1> undef)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
;
; AVX512-LABEL: 'masked_compressstore'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.masked.compressstore.v8f64(<8 x double> undef, double* undef, <8 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v4f64(<4 x double> undef, double* undef, <4 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2f64(<2 x double> undef, double* undef, <2 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1f64(<1 x double> undef, double* undef, <1 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: call void @llvm.masked.compressstore.v16f32(<16 x float> undef, float* undef, <16 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.masked.compressstore.v8f32(<8 x float> undef, float* undef, <8 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.compressstore.v4f32(<4 x float> undef, float* undef, <4 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2f32(<2 x float> undef, float* undef, <2 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.compressstore.v8i64(<8 x i64> undef, i64* undef, <8 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.compressstore.v4i64(<4 x i64> undef, i64* undef, <4 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.compressstore.v2i64(<2 x i64> undef, i64* undef, <2 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1i64(<1 x i64> undef, i64* undef, <1 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.compressstore.v16i32(<16 x i32> undef, i32* undef, <16 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.compressstore.v8i32(<8 x i32> undef, i32* undef, <8 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v4i32(<4 x i32> undef, i32* undef, <4 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.compressstore.v2i32(<2 x i32> undef, i32* undef, <2 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 120 for instruction: call void @llvm.masked.compressstore.v32i16(<32 x i16> undef, i16* undef, <32 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: call void @llvm.masked.compressstore.v16i16(<16 x i16> undef, i16* undef, <16 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.compressstore.v8i16(<8 x i16> undef, i16* undef, <8 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v4i16(<4 x i16> undef, i16* undef, <4 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 240 for instruction: call void @llvm.masked.compressstore.v64i8(<64 x i8> undef, i8* undef, <64 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: call void @llvm.masked.compressstore.v32i8(<32 x i8> undef, i8* undef, <32 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: call void @llvm.masked.compressstore.v16i8(<16 x i8> undef, i8* undef, <16 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.compressstore.v8i8(<8 x i8> undef, i8* undef, <8 x i1> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
;
  call void @llvm.masked.compressstore.v8f64(<8 x double> undef, double* undef, <8 x i1> undef)
  call void @llvm.masked.compressstore.v4f64(<4 x double> undef, double* undef, <4 x i1> undef)
  call void @llvm.masked.compressstore.v2f64(<2 x double> undef, double* undef, <2 x i1> undef)
  call void @llvm.masked.compressstore.v1f64(<1 x double> undef, double* undef, <1 x i1> undef)

  call void @llvm.masked.compressstore.v16f32(<16 x float> undef, float* undef, <16 x i1> undef)
  call void @llvm.masked.compressstore.v8f32(<8 x float> undef, float* undef, <8 x i1> undef)
  call void @llvm.masked.compressstore.v4f32(<4 x float> undef, float* undef, <4 x i1> undef)
  call void @llvm.masked.compressstore.v2f32(<2 x float> undef, float* undef, <2 x i1> undef)

  call void @llvm.masked.compressstore.v8i64(<8 x i64> undef, i64* undef, <8 x i1> undef)
  call void @llvm.masked.compressstore.v4i64(<4 x i64> undef, i64* undef, <4 x i1> undef)
  call void @llvm.masked.compressstore.v2i64(<2 x i64> undef, i64* undef, <2 x i1> undef)
  call void @llvm.masked.compressstore.v1i64(<1 x i64> undef, i64* undef, <1 x i1> undef)

  call void @llvm.masked.compressstore.v16i32(<16 x i32> undef, i32* undef, <16 x i1> undef)
  call void @llvm.masked.compressstore.v8i32(<8 x i32> undef, i32* undef, <8 x i1> undef)
  call void @llvm.masked.compressstore.v4i32(<4 x i32> undef, i32* undef, <4 x i1> undef)
  call void @llvm.masked.compressstore.v2i32(<2 x i32> undef, i32* undef, <2 x i1> undef)

  call void @llvm.masked.compressstore.v32i16(<32 x i16> undef, i16* undef, <32 x i1> undef)
  call void @llvm.masked.compressstore.v16i16(<16 x i16> undef, i16* undef, <16 x i1> undef)
  call void @llvm.masked.compressstore.v8i16(<8 x i16> undef, i16* undef, <8 x i1> undef)
  call void @llvm.masked.compressstore.v4i16(<4 x i16> undef, i16* undef, <4 x i1> undef)

  call void @llvm.masked.compressstore.v64i8(<64 x i8> undef, i8* undef, <64 x i1> undef)
  call void @llvm.masked.compressstore.v32i8(<32 x i8> undef, i8* undef, <32 x i1> undef)
  call void @llvm.masked.compressstore.v16i8(<16 x i8> undef, i8* undef, <16 x i1> undef)
  call void @llvm.masked.compressstore.v8i8(<8 x i8> undef, i8* undef, <8 x i1> undef)

  ret i32 0
}

define <2 x double> @test1(<2 x i64> %trigger, <2 x double>* %addr, <2 x double> %dst) {
; SSE2-LABEL: 'test1'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %mask = icmp eq <2 x i64> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1> %mask, <2 x double> %dst)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;
; SSE42-LABEL: 'test1'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i64> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1> %mask, <2 x double> %dst)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;
; AVX-LABEL: 'test1'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i64> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1> %mask, <2 x double> %dst)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;
; AVX512-LABEL: 'test1'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i64> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1> %mask, <2 x double> %dst)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;
  %mask = icmp eq <2 x i64> %trigger, zeroinitializer
  %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1>%mask, <2 x double>%dst)
  ret <2 x double> %res
}

define <4 x i32> @test2(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %dst) {
; SSE2-LABEL: 'test2'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> %mask, <4 x i32> %dst)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; SSE42-LABEL: 'test2'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> %mask, <4 x i32> %dst)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; AVX-LABEL: 'test2'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> %mask, <4 x i32> %dst)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; AVX512-LABEL: 'test2'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> %mask, <4 x i32> %dst)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
  %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1>%mask, <4 x i32>%dst)
  ret <4 x i32> %res
}

define void @test3(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
; SSE2-LABEL: 'test3'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1> %mask)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSE42-LABEL: 'test3'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1> %mask)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX-LABEL: 'test3'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1> %mask)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'test3'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1> %mask)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1>%mask)
  ret void
}

define <8 x float> @test4(<8 x i32> %trigger, <8 x float>* %addr, <8 x float> %dst) {
; SSE2-LABEL: 'test4'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
;
; SSE42-LABEL: 'test4'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
;
; AVX1-LABEL: 'test4'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
;
; AVX2-LABEL: 'test4'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
;
; SKL-LABEL: 'test4'
; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
; SKL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
;
; AVX512-LABEL: 'test4'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
;
  %mask = icmp eq <8 x i32> %trigger, zeroinitializer
  %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1>%mask, <8 x float>%dst)
  ret <8 x float> %res
}

define void @test5(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %val) {
; SSE2-LABEL: 'test5'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> %val, <2 x float>* %addr, i32 4, <2 x i1> %mask)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSE42-LABEL: 'test5'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> %val, <2 x float>* %addr, i32 4, <2 x i1> %mask)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX-LABEL: 'test5'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> %val, <2 x float>* %addr, i32 4, <2 x i1> %mask)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'test5'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> %val, <2 x float>* %addr, i32 4, <2 x i1> %mask)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
  call void @llvm.masked.store.v2f32.p0v2f32(<2 x float>%val, <2 x float>* %addr, i32 4, <2 x i1>%mask)
  ret void
}

define void @test6(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %val) {
; SSE2-LABEL: 'test6'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> %val, <2 x i32>* %addr, i32 4, <2 x i1> %mask)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSE42-LABEL: 'test6'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> %val, <2 x i32>* %addr, i32 4, <2 x i1> %mask)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX-LABEL: 'test6'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> %val, <2 x i32>* %addr, i32 4, <2 x i1> %mask)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'test6'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> %val, <2 x i32>* %addr, i32 4, <2 x i1> %mask)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
  call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>%val, <2 x i32>* %addr, i32 4, <2 x i1>%mask)
  ret void
}

define <2 x float> @test7(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %dst) {
; SSE2-LABEL: 'test7'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1> %mask, <2 x float> %dst)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %res
;
; SSE42-LABEL: 'test7'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1> %mask, <2 x float> %dst)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %res
;
; AVX-LABEL: 'test7'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1> %mask, <2 x float> %dst)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %res
;
; AVX512-LABEL: 'test7'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1> %mask, <2 x float> %dst)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %res
;
  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
  %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>%dst)
  ret <2 x float> %res
}

define <2 x i32> @test8(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %dst) {
; SSE2-LABEL: 'test8'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1> %mask, <2 x i32> %dst)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %res
;
; SSE42-LABEL: 'test8'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1> %mask, <2 x i32> %dst)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %res
;
; AVX-LABEL: 'test8'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1> %mask, <2 x i32> %dst)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %res
;
; AVX512-LABEL: 'test8'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1> %mask, <2 x i32> %dst)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %res
;
  %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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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
;
; AVX512-LABEL: 'test_gather_16f32_const_mask'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; AVX512-NEXT:  Cost Model: Found an estimated cost of 18 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)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind

  %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 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 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 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 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
;
; AVX512-LABEL: 'test_gather_16f32_var_mask'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; AVX512-NEXT:  Cost Model: Found an estimated cost of 18 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)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind

  %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 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 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 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 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
;
; AVX512-LABEL: 'test_gather_16f32_ra_var_mask'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
; AVX512-NEXT:  Cost Model: Found an estimated cost of 20 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)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind

  %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_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 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 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 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 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)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX512-LABEL: 'test_gather_16f32_const_mask2'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
; AVX512-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
; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX512-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
; AVX512-NEXT:  Cost Model: Found an estimated cost of 18 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)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
  %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
  %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer

  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind

  %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)
  ret <16 x float>%res
}

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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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
;
  %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> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
  ret <4 x float>%res
}

declare <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>*, i32, <8 x i1>, <8 x double>)
declare <7 x double> @llvm.masked.load.v7f64.p0v7f64(<7 x double>*, i32, <7 x i1>, <7 x double>)
declare <6 x double> @llvm.masked.load.v6f64.p0v6f64(<6 x double>*, i32, <6 x i1>, <6 x double>)
declare <5 x double> @llvm.masked.load.v5f64.p0v5f64(<5 x double>*, i32, <5 x i1>, <5 x double>)
declare <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>*, i32, <4 x i1>, <4 x double>)
declare <3 x double> @llvm.masked.load.v3f64.p0v3f64(<3 x double>*, i32, <3 x i1>, <3 x double>)
declare <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>*, i32, <2 x i1>, <2 x double>)
declare <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>*, i32, <1 x i1>, <1 x double>)

declare <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>*, i32, <16 x i1>, <16 x float>)
declare <15 x float> @llvm.masked.load.v15f32.p0v15f32(<15 x float>*, i32, <15 x i1>, <15 x float>)
declare <14 x float> @llvm.masked.load.v14f32.p0v14f32(<14 x float>*, i32, <14 x i1>, <14 x float>)
declare <13 x float> @llvm.masked.load.v13f32.p0v13f32(<13 x float>*, i32, <13 x i1>, <13 x float>)
declare <12 x float> @llvm.masked.load.v12f32.p0v12f32(<12 x float>*, i32, <12 x i1>, <12 x float>)
declare <11 x float> @llvm.masked.load.v11f32.p0v11f32(<11 x float>*, i32, <11 x i1>, <11 x float>)
declare <10 x float> @llvm.masked.load.v10f32.p0v10f32(<10 x float>*, i32, <10 x i1>, <10 x float>)
declare <9 x float> @llvm.masked.load.v9f32.p0v9f32(<9 x float>*, i32, <9 x i1>, <9 x float>)
declare <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>*, i32, <8 x i1>, <8 x float>)
declare <7 x float> @llvm.masked.load.v7f32.p0v7f32(<7 x float>*, i32, <7 x i1>, <7 x float>)
declare <6 x float> @llvm.masked.load.v6f32.p0v6f32(<6 x float>*, i32, <6 x i1>, <6 x float>)
declare <5 x float> @llvm.masked.load.v5f32.p0v5f32(<5 x float>*, i32, <5 x i1>, <5 x float>)
declare <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>*, i32, <4 x i1>, <4 x float>)
declare <3 x float> @llvm.masked.load.v3f32.p0v3f32(<3 x float>*, i32, <3 x i1>, <3 x float>)
declare <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>*, i32, <2 x i1>, <2 x float>)
declare <1 x float> @llvm.masked.load.v1f32.p0v1f32(<1 x float>*, i32, <1 x i1>, <1 x float>)

declare <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>*, i32, <8 x i1>, <8 x i64>)
declare <7 x i64> @llvm.masked.load.v7i64.p0v7i64(<7 x i64>*, i32, <7 x i1>, <7 x i64>)
declare <6 x i64> @llvm.masked.load.v6i64.p0v6i64(<6 x i64>*, i32, <6 x i1>, <6 x i64>)
declare <5 x i64> @llvm.masked.load.v5i64.p0v5i64(<5 x i64>*, i32, <5 x i1>, <5 x i64>)
declare <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>*, i32, <4 x i1>, <4 x i64>)
declare <3 x i64> @llvm.masked.load.v3i64.p0v3i64(<3 x i64>*, i32, <3 x i1>, <3 x i64>)
declare <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>*, i32, <2 x i1>, <2 x i64>)
declare <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>*, i32, <1 x i1>, <1 x i64>)

declare <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>*, i32, <16 x i1>, <16 x i32>)
declare <15 x i32> @llvm.masked.load.v15i32.p0v15i32(<15 x i32>*, i32, <15 x i1>, <15 x i32>)
declare <14 x i32> @llvm.masked.load.v14i32.p0v14i32(<14 x i32>*, i32, <14 x i1>, <14 x i32>)
declare <13 x i32> @llvm.masked.load.v13i32.p0v13i32(<13 x i32>*, i32, <13 x i1>, <13 x i32>)
declare <12 x i32> @llvm.masked.load.v12i32.p0v12i32(<12 x i32>*, i32, <12 x i1>, <12 x i32>)
declare <11 x i32> @llvm.masked.load.v11i32.p0v11i32(<11 x i32>*, i32, <11 x i1>, <11 x i32>)
declare <10 x i32> @llvm.masked.load.v10i32.p0v10i32(<10 x i32>*, i32, <10 x i1>, <10 x i32>)
declare <9 x i32> @llvm.masked.load.v9i32.p0v9i32(<9 x i32>*, i32, <9 x i1>, <9 x i32>)
declare <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>*, i32, <8 x i1>, <8 x i32>)
declare <7 x i32> @llvm.masked.load.v7i32.p0v7i32(<7 x i32>*, i32, <7 x i1>, <7 x i32>)
declare <6 x i32> @llvm.masked.load.v6i32.p0v6i32(<6 x i32>*, i32, <6 x i1>, <6 x i32>)
declare <5 x i32> @llvm.masked.load.v5i32.p0v5i32(<5 x i32>*, i32, <5 x i1>, <5 x i32>)
declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
declare <3 x i32> @llvm.masked.load.v3i32.p0v3i32(<3 x i32>*, i32, <3 x i1>, <3 x i32>)
declare <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
declare <1 x i32> @llvm.masked.load.v1i32.p0v1i32(<1 x i32>*, i32, <1 x i1>, <1 x i32>)

declare <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>*, i32, <32 x i1>, <32 x i16>)
declare <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>*, i32, <16 x i1>, <16 x i16>)
declare <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>*, i32, <8 x i1>, <8 x i16>)
declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32, <4 x i1>, <4 x i16>)

declare <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>*, i32, <64 x i1>, <64 x i8>)
declare <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>*, i32, <32 x i1>, <32 x i8>)
declare <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>*, i32, <16 x i1>, <16 x i8>)
declare <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>*, i32, <8 x i1>, <8 x i8>)

declare void @llvm.masked.store.v8f64.p0v8f64(<8 x double>, <8 x double>*, i32, <8 x i1>)
declare void @llvm.masked.store.v7f64.p0v7f64(<7 x double>, <7 x double>*, i32, <7 x i1>)
declare void @llvm.masked.store.v6f64.p0v6f64(<6 x double>, <6 x double>*, i32, <6 x i1>)
declare void @llvm.masked.store.v5f64.p0v5f64(<5 x double>, <5 x double>*, i32, <5 x i1>)
declare void @llvm.masked.store.v4f64.p0v4f64(<4 x double>, <4 x double>*, i32, <4 x i1>)
declare void @llvm.masked.store.v3f64.p0v3f64(<3 x double>, <3 x double>*, i32, <3 x i1>)
declare void @llvm.masked.store.v2f64.p0v2f64(<2 x double>, <2 x double>*, i32, <2 x i1>)
declare void @llvm.masked.store.v1f64.p0v1f64(<1 x double>, <1 x double>*, i32, <1 x i1>)

declare void @llvm.masked.store.v16f32.p0v16f32(<16 x float>, <16 x float>*, i32, <16 x i1>)
declare void @llvm.masked.store.v15f32.p0v15f32(<15 x float>, <15 x float>*, i32, <15 x i1>)
declare void @llvm.masked.store.v14f32.p0v14f32(<14 x float>, <14 x float>*, i32, <14 x i1>)
declare void @llvm.masked.store.v13f32.p0v13f32(<13 x float>, <13 x float>*, i32, <13 x i1>)
declare void @llvm.masked.store.v12f32.p0v12f32(<12 x float>, <12 x float>*, i32, <12 x i1>)
declare void @llvm.masked.store.v11f32.p0v11f32(<11 x float>, <11 x float>*, i32, <11 x i1>)
declare void @llvm.masked.store.v10f32.p0v10f32(<10 x float>, <10 x float>*, i32, <10 x i1>)
declare void @llvm.masked.store.v9f32.p0v9f32(<9 x float>, <9 x float>*, i32, <9 x i1>)
declare void @llvm.masked.store.v8f32.p0v8f32(<8 x float>, <8 x float>*, i32, <8 x i1>)
declare void @llvm.masked.store.v7f32.p0v7f32(<7 x float>, <7 x float>*, i32, <7 x i1>)
declare void @llvm.masked.store.v6f32.p0v6f32(<6 x float>, <6 x float>*, i32, <6 x i1>)
declare void @llvm.masked.store.v5f32.p0v5f32(<5 x float>, <5 x float>*, i32, <5 x i1>)
declare void @llvm.masked.store.v4f32.p0v4f32(<4 x float>, <4 x float>*, i32, <4 x i1>)
declare void @llvm.masked.store.v3f32.p0v3f32(<3 x float>, <3 x float>*, i32, <3 x i1>)
declare void @llvm.masked.store.v2f32.p0v2f32(<2 x float>, <2 x float>*, i32, <2 x i1>)
declare void @llvm.masked.store.v1f32.p0v1f32(<1 x float>, <1 x float>*, i32, <1 x i1>)

declare void @llvm.masked.store.v8i64.p0v8i64(<8 x i64>, <8 x i64>*, i32, <8 x i1>)
declare void @llvm.masked.store.v7i64.p0v7i64(<7 x i64>, <7 x i64>*, i32, <7 x i1>)
declare void @llvm.masked.store.v6i64.p0v6i64(<6 x i64>, <6 x i64>*, i32, <6 x i1>)
declare void @llvm.masked.store.v5i64.p0v5i64(<5 x i64>, <5 x i64>*, i32, <5 x i1>)
declare void @llvm.masked.store.v4i64.p0v4i64(<4 x i64>, <4 x i64>*, i32, <4 x i1>)
declare void @llvm.masked.store.v3i64.p0v3i64(<3 x i64>, <3 x i64>*, i32, <3 x i1>)
declare void @llvm.masked.store.v2i64.p0v2i64(<2 x i64>, <2 x i64>*, i32, <2 x i1>)
declare void @llvm.masked.store.v1i64.p0v1i64(<1 x i64>, <1 x i64>*, i32, <1 x i1>)

declare void @llvm.masked.store.v16i32.p0v16i32(<16 x i32>, <16 x i32>*, i32, <16 x i1>)
declare void @llvm.masked.store.v15i32.p0v15i32(<15 x i32>, <15 x i32>*, i32, <15 x i1>)
declare void @llvm.masked.store.v14i32.p0v14i32(<14 x i32>, <14 x i32>*, i32, <14 x i1>)
declare void @llvm.masked.store.v13i32.p0v13i32(<13 x i32>, <13 x i32>*, i32, <13 x i1>)
declare void @llvm.masked.store.v12i32.p0v12i32(<12 x i32>, <12 x i32>*, i32, <12 x i1>)
declare void @llvm.masked.store.v11i32.p0v11i32(<11 x i32>, <11 x i32>*, i32, <11 x i1>)
declare void @llvm.masked.store.v10i32.p0v10i32(<10 x i32>, <10 x i32>*, i32, <10 x i1>)
declare void @llvm.masked.store.v9i32.p0v9i32(<9 x i32>, <9 x i32>*, i32, <9 x i1>)
declare void @llvm.masked.store.v8i32.p0v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
declare void @llvm.masked.store.v7i32.p0v7i32(<7 x i32>, <7 x i32>*, i32, <7 x i1>)
declare void @llvm.masked.store.v6i32.p0v6i32(<6 x i32>, <6 x i32>*, i32, <6 x i1>)
declare void @llvm.masked.store.v5i32.p0v5i32(<5 x i32>, <5 x i32>*, i32, <5 x i1>)
declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
declare void @llvm.masked.store.v3i32.p0v3i32(<3 x i32>, <3 x i32>*, i32, <3 x i1>)
declare void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>, <2 x i32>*, i32, <2 x i1>)
declare void @llvm.masked.store.v1i32.p0v1i32(<1 x i32>, <1 x i32>*, i32, <1 x i1>)

declare void @llvm.masked.store.v32i16.p0v32i16(<32 x i16>, <32 x i16>*, i32, <32 x i1>)
declare void @llvm.masked.store.v16i16.p0v16i16(<16 x i16>, <16 x i16>*, i32, <16 x i1>)
declare void @llvm.masked.store.v8i16.p0v8i16(<8 x i16>, <8 x i16>*, i32, <8 x i1>)
declare void @llvm.masked.store.v4i16.p0v4i16(<4 x i16>, <4 x i16>*, i32, <4 x i1>)

declare void @llvm.masked.store.v64i8.p0v64i8(<64 x i8>, <64 x i8>*, i32, <64 x i1>)
declare void @llvm.masked.store.v32i8.p0v32i8(<32 x i8>, <32 x i8>*, i32, <32 x i1>)
declare void @llvm.masked.store.v16i8.p0v16i8(<16 x i8>, <16 x i8>*, i32, <16 x i1>)
declare void @llvm.masked.store.v8i8.p0v8i8(<8 x i8>, <8 x i8>*, i32, <8 x i1>)

declare <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*>, i32, <8 x i1>, <8 x double>)
declare <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*>, i32, <4 x i1>, <4 x double>)
declare <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*>, i32, <2 x i1>, <2 x double>)
declare <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*>, i32, <1 x i1>, <1 x double>)

declare <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*>, i32, <16 x i1>, <16 x float>)
declare <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*>, i32, <8 x i1>, <8 x float>)
declare <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*>, i32, <4 x i1>, <4 x float>)
declare <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*>, i32, <2 x i1>, <2 x float>)

declare <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*>, i32, <8 x i1>, <8 x i64>)
declare <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*>, i32, <4 x i1>, <4 x i64>)
declare <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*>, i32, <2 x i1>, <2 x i64>)
declare <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*>, i32, <1 x i1>, <1 x i64>)

declare <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*>, i32, <16 x i1>, <16 x i32>)
declare <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*>, i32, <8 x i1>, <8 x i32>)
declare <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*>, i32, <4 x i1>, <4 x i32>)
declare <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*>, i32, <2 x i1>, <2 x i32>)

declare <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*>, i32, <32 x i1>, <32 x i16>)
declare <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*>, i32, <16 x i1>, <16 x i16>)
declare <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*>, i32, <8 x i1>, <8 x i16>)
declare <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*>, i32, <4 x i1>, <4 x i16>)

declare <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*>, i32, <64 x i1>, <64 x i8>)
declare <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*>, i32, <32 x i1>, <32 x i8>)
declare <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*>, i32, <16 x i1>, <16 x i8>)
declare <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*>, i32, <8 x i1>, <8 x i8>)

declare void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double>, <8 x double*>, i32, <8 x i1>)
declare void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double>, <4 x double*>, i32, <4 x i1>)
declare void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double>, <2 x double*>, i32, <2 x i1>)
declare void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double>, <1 x double*>, i32, <1 x i1>)

declare void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float>, <16 x float*>, i32, <16 x i1>)
declare void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float>, <8 x float*>, i32, <8 x i1>)
declare void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float>, <4 x float*>, i32, <4 x i1>)
declare void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float>, <2 x float*>, i32, <2 x i1>)

declare void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64>, <8 x i64*>, i32, <8 x i1>)
declare void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64>, <4 x i64*>, i32, <4 x i1>)
declare void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64>, <2 x i64*>, i32, <2 x i1>)
declare void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64>, <1 x i64*>, i32, <1 x i1>)

declare void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32>, <16 x i32*>, i32, <16 x i1>)
declare void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32>, <8 x i32*>, i32, <8 x i1>)
declare void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32>, <4 x i32*>, i32, <4 x i1>)
declare void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32>, <2 x i32*>, i32, <2 x i1>)

declare void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16>, <32 x i16*>, i32, <32 x i1>)
declare void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16>, <16 x i16*>, i32, <16 x i1>)
declare void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16>, <8 x i16*>, i32, <8 x i1>)
declare void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16>, <4 x i16*>, i32, <4 x i1>)

declare void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8>, <64 x i8*>, i32, <64 x i1>)
declare void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8>, <32 x i8*>, i32, <32 x i1>)
declare void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8>, <16 x i8*>, i32, <16 x i1>)
declare void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8>, <8 x i8*>, i32, <8 x i1>)

declare <8 x double> @llvm.masked.expandload.v8f64(double*, <8 x i1>, <8 x double>)
declare <4 x double> @llvm.masked.expandload.v4f64(double*, <4 x i1>, <4 x double>)
declare <2 x double> @llvm.masked.expandload.v2f64(double*, <2 x i1>, <2 x double>)
declare <1 x double> @llvm.masked.expandload.v1f64(double*, <1 x i1>, <1 x double>)

declare <16 x float> @llvm.masked.expandload.v16f32(float*, <16 x i1>, <16 x float>)
declare <8 x float> @llvm.masked.expandload.v8f32(float*, <8 x i1>, <8 x float>)
declare <4 x float> @llvm.masked.expandload.v4f32(float*, <4 x i1>, <4 x float>)
declare <2 x float> @llvm.masked.expandload.v2f32(float*, <2 x i1>, <2 x float>)

declare <8 x i64> @llvm.masked.expandload.v8i64(i64*, <8 x i1>, <8 x i64>)
declare <4 x i64> @llvm.masked.expandload.v4i64(i64*, <4 x i1>, <4 x i64>)
declare <2 x i64> @llvm.masked.expandload.v2i64(i64*, <2 x i1>, <2 x i64>)
declare <1 x i64> @llvm.masked.expandload.v1i64(i64*, <1 x i1>, <1 x i64>)

declare <16 x i32> @llvm.masked.expandload.v16i32(i32*, <16 x i1>, <16 x i32>)
declare <8 x i32> @llvm.masked.expandload.v8i32(i32*, <8 x i1>, <8 x i32>)
declare <4 x i32> @llvm.masked.expandload.v4i32(i32*, <4 x i1>, <4 x i32>)
declare <2 x i32> @llvm.masked.expandload.v2i32(i32*, <2 x i1>, <2 x i32>)

declare <32 x i16> @llvm.masked.expandload.v32i16(i16*, <32 x i1>, <32 x i16>)
declare <16 x i16> @llvm.masked.expandload.v16i16(i16*, <16 x i1>, <16 x i16>)
declare <8 x i16> @llvm.masked.expandload.v8i16(i16*, <8 x i1>, <8 x i16>)
declare <4 x i16> @llvm.masked.expandload.v4i16(i16*, <4 x i1>, <4 x i16>)

declare <64 x i8> @llvm.masked.expandload.v64i8(i8*, <64 x i1>, <64 x i8>)
declare <32 x i8> @llvm.masked.expandload.v32i8(i8*, <32 x i1>, <32 x i8>)
declare <16 x i8> @llvm.masked.expandload.v16i8(i8*, <16 x i1>, <16 x i8>)
declare <8 x i8> @llvm.masked.expandload.v8i8(i8*, <8 x i1>, <8 x i8>)

declare void @llvm.masked.compressstore.v8f64(<8 x double>, double*, <8 x i1>)
declare void @llvm.masked.compressstore.v4f64(<4 x double>, double*, <4 x i1>)
declare void @llvm.masked.compressstore.v2f64(<2 x double>, double*, <2 x i1>)
declare void @llvm.masked.compressstore.v1f64(<1 x double>, double*, <1 x i1>)

declare void @llvm.masked.compressstore.v16f32(<16 x float>, float*, <16 x i1>)
declare void @llvm.masked.compressstore.v8f32(<8 x float>, float*, <8 x i1>)
declare void @llvm.masked.compressstore.v4f32(<4 x float>, float*, <4 x i1>)
declare void @llvm.masked.compressstore.v2f32(<2 x float>, float*, <2 x i1>)

declare void @llvm.masked.compressstore.v8i64(<8 x i64>, i64*, <8 x i1>)
declare void @llvm.masked.compressstore.v4i64(<4 x i64>, i64*, <4 x i1>)
declare void @llvm.masked.compressstore.v2i64(<2 x i64>, i64*, <2 x i1>)
declare void @llvm.masked.compressstore.v1i64(<1 x i64>, i64*, <1 x i1>)

declare void @llvm.masked.compressstore.v16i32(<16 x i32>, i32*, <16 x i1>)
declare void @llvm.masked.compressstore.v8i32(<8 x i32>, i32*, <8 x i1>)
declare void @llvm.masked.compressstore.v4i32(<4 x i32>, i32*, <4 x i1>)
declare void @llvm.masked.compressstore.v2i32(<2 x i32>, i32*, <2 x i1>)

declare void @llvm.masked.compressstore.v32i16(<32 x i16>, i16*, <32 x i1>)
declare void @llvm.masked.compressstore.v16i16(<16 x i16>, i16*, <16 x i1>)
declare void @llvm.masked.compressstore.v8i16(<8 x i16>, i16*, <8 x i1>)
declare void @llvm.masked.compressstore.v4i16(<4 x i16>, i16*, <4 x i1>)

declare void @llvm.masked.compressstore.v64i8(<64 x i8>, i8*, <64 x i1>)
declare void @llvm.masked.compressstore.v32i8(<32 x i8>, i8*, <32 x i1>)
declare void @llvm.masked.compressstore.v16i8(<16 x i8>, i8*, <16 x i1>)
declare void @llvm.masked.compressstore.v8i8(<8 x i8>, i8*, <8 x i1>)