325 lines · plain
1; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py2; RUN: opt < %s -mtriple=aarch64--linux-gnu -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output | FileCheck %s3 4target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"5 6define void @vst2(ptr %p) {7; CHECK-LABEL: 'vst2'8; CHECK-NEXT: Cost Model: Found costs of 1 for: %v4i8 = shufflevector <2 x i8> undef, <2 x i8> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>9; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <4 x i8> %v4i8, ptr %p, align 410; CHECK-NEXT: Cost Model: Found costs of 1 for: %v8i8 = shufflevector <4 x i8> undef, <4 x i8> undef, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>11; CHECK-NEXT: Cost Model: Found costs of 1 for: store <8 x i8> %v8i8, ptr %p, align 812; CHECK-NEXT: Cost Model: Found costs of 1 for: %v16i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>13; CHECK-NEXT: Cost Model: Found costs of 1 for: store <16 x i8> %v16i8, ptr %p, align 1614; CHECK-NEXT: Cost Model: Found costs of 2 for: %v32i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <32 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>15; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <32 x i8> %v32i8, ptr %p, align 3216; CHECK-NEXT: Cost Model: Found costs of 1 for: %v4i16 = shufflevector <2 x i16> undef, <2 x i16> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>17; CHECK-NEXT: Cost Model: Found costs of 1 for: store <4 x i16> %v4i16, ptr %p, align 818; CHECK-NEXT: Cost Model: Found costs of 1 for: %v8i16 = shufflevector <4 x i16> undef, <4 x i16> undef, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>19; CHECK-NEXT: Cost Model: Found costs of 1 for: store <8 x i16> %v8i16, ptr %p, align 1620; CHECK-NEXT: Cost Model: Found costs of 2 for: %v16i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>21; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <16 x i16> %v16i16, ptr %p, align 3222; CHECK-NEXT: Cost Model: Found costs of 4 for: %v32i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <32 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>23; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <32 x i16> %v32i16, ptr %p, align 6424; CHECK-NEXT: Cost Model: Found costs of 1 for: %v4i32 = shufflevector <2 x i32> undef, <2 x i32> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>25; CHECK-NEXT: Cost Model: Found costs of 1 for: store <4 x i32> %v4i32, ptr %p, align 1626; CHECK-NEXT: Cost Model: Found costs of 2 for: %v8i32 = shufflevector <4 x i32> undef, <4 x i32> undef, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>27; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <8 x i32> %v8i32, ptr %p, align 3228; CHECK-NEXT: Cost Model: Found costs of 4 for: %v16i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>29; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <16 x i32> %v16i32, ptr %p, align 6430; CHECK-NEXT: Cost Model: Found costs of 8 for: %v32i32 = shufflevector <16 x i32> undef, <16 x i32> undef, <32 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>31; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:1 SizeLat:8 for: store <32 x i32> %v32i32, ptr %p, align 12832; CHECK-NEXT: Cost Model: Found costs of 2 for: %v4i64 = shufflevector <2 x i64> undef, <2 x i64> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>33; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <4 x i64> %v4i64, ptr %p, align 3234; CHECK-NEXT: Cost Model: Found costs of 4 for: %v8i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>35; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <8 x i64> %v8i64, ptr %p, align 6436; CHECK-NEXT: Cost Model: Found costs of 8 for: %v16i64 = shufflevector <8 x i64> undef, <8 x i64> undef, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>37; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:1 SizeLat:8 for: store <16 x i64> %v16i64, ptr %p, align 12838; CHECK-NEXT: Cost Model: Found costs of 16 for: %v32i64 = shufflevector <16 x i64> undef, <16 x i64> undef, <32 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>39; CHECK-NEXT: Cost Model: Found costs of RThru:16 CodeSize:16 Lat:1 SizeLat:16 for: store <32 x i64> %v32i64, ptr %p, align 25640; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void41;42 %v4i8 = shufflevector <2 x i8> undef, <2 x i8> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>43 store <4 x i8> %v4i8, ptr %p44 %v8i8 = shufflevector <4 x i8> undef, <4 x i8> undef, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>45 store <8 x i8> %v8i8, ptr %p46 %v16i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>47 store <16 x i8> %v16i8, ptr %p48 %v32i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <32 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>49 store <32 x i8> %v32i8, ptr %p50 51 %v4i16 = shufflevector <2 x i16> undef, <2 x i16> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>52 store <4 x i16> %v4i16, ptr %p53 %v8i16 = shufflevector <4 x i16> undef, <4 x i16> undef, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>54 store <8 x i16> %v8i16, ptr %p55 %v16i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>56 store <16 x i16> %v16i16, ptr %p57 %v32i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <32 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>58 store <32 x i16> %v32i16, ptr %p59 60 %v4i32 = shufflevector <2 x i32> undef, <2 x i32> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>61 store <4 x i32> %v4i32, ptr %p62 %v8i32 = shufflevector <4 x i32> undef, <4 x i32> undef, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>63 store <8 x i32> %v8i32, ptr %p64 %v16i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>65 store <16 x i32> %v16i32, ptr %p66 %v32i32 = shufflevector <16 x i32> undef, <16 x i32> undef, <32 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>67 store <32 x i32> %v32i32, ptr %p68 69 %v4i64 = shufflevector <2 x i64> undef, <2 x i64> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>70 store <4 x i64> %v4i64, ptr %p71 %v8i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>72 store <8 x i64> %v8i64, ptr %p73 %v16i64 = shufflevector <8 x i64> undef, <8 x i64> undef, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>74 store <16 x i64> %v16i64, ptr %p75 %v32i64 = shufflevector <16 x i64> undef, <16 x i64> undef, <32 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>76 store <32 x i64> %v32i64, ptr %p77 78 ret void79}80 81 82define void @vst3(ptr %p) {83; CHECK-LABEL: 'vst3'84; CHECK-NEXT: Cost Model: Found costs of 8 for: %v8i8 = shufflevector <4 x i8> undef, <4 x i8> undef, <6 x i32> <i32 0, i32 2, i32 4, i32 1, i32 3, i32 5>85; CHECK-NEXT: Cost Model: Found costs of 1 for: store <6 x i8> %v8i8, ptr %p, align 886; CHECK-NEXT: Cost Model: Found costs of 8 for: %v16i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>87; CHECK-NEXT: Cost Model: Found costs of 1 for: store <12 x i8> %v16i8, ptr %p, align 1688; CHECK-NEXT: Cost Model: Found costs of 2 for: %v32i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <24 x i32> <i32 0, i32 8, i32 16, i32 1, i32 9, i32 17, i32 2, i32 10, i32 18, i32 3, i32 11, i32 19, i32 4, i32 12, i32 20, i32 5, i32 13, i32 21, i32 6, i32 14, i32 22, i32 7, i32 15, i32 23>89; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <24 x i8> %v32i8, ptr %p, align 3290; CHECK-NEXT: Cost Model: Found costs of 4 for: %v64i8 = shufflevector <32 x i8> undef, <32 x i8> undef, <48 x i32> <i32 0, i32 16, i32 32, i32 1, i32 17, i32 33, i32 2, i32 18, i32 34, i32 3, i32 19, i32 35, i32 4, i32 20, i32 36, i32 5, i32 21, i32 37, i32 6, i32 22, i32 38, i32 7, i32 23, i32 39, i32 8, i32 24, i32 40, i32 9, i32 25, i32 41, i32 10, i32 26, i32 42, i32 11, i32 27, i32 43, i32 12, i32 28, i32 44, i32 13, i32 29, i32 45, i32 14, i32 30, i32 46, i32 15, i32 31, i32 47>91; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <48 x i8> %v64i8, ptr %p, align 6492; CHECK-NEXT: Cost Model: Found costs of 8 for: %v8i16 = shufflevector <4 x i16> undef, <4 x i16> undef, <6 x i32> <i32 0, i32 2, i32 4, i32 1, i32 3, i32 5>93; CHECK-NEXT: Cost Model: Found costs of 1 for: store <6 x i16> %v8i16, ptr %p, align 1694; CHECK-NEXT: Cost Model: Found costs of 2 for: %v16i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>95; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <12 x i16> %v16i16, ptr %p, align 3296; CHECK-NEXT: Cost Model: Found costs of 4 for: %v32i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <24 x i32> <i32 0, i32 8, i32 16, i32 1, i32 9, i32 17, i32 2, i32 10, i32 18, i32 3, i32 11, i32 19, i32 4, i32 12, i32 20, i32 5, i32 13, i32 21, i32 6, i32 14, i32 22, i32 7, i32 15, i32 23>97; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <24 x i16> %v32i16, ptr %p, align 6498; CHECK-NEXT: Cost Model: Found costs of 8 for: %v64i16 = shufflevector <32 x i16> undef, <32 x i16> undef, <48 x i32> <i32 0, i32 16, i32 32, i32 1, i32 17, i32 33, i32 2, i32 18, i32 34, i32 3, i32 19, i32 35, i32 4, i32 20, i32 36, i32 5, i32 21, i32 37, i32 6, i32 22, i32 38, i32 7, i32 23, i32 39, i32 8, i32 24, i32 40, i32 9, i32 25, i32 41, i32 10, i32 26, i32 42, i32 11, i32 27, i32 43, i32 12, i32 28, i32 44, i32 13, i32 29, i32 45, i32 14, i32 30, i32 46, i32 15, i32 31, i32 47>99; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:1 SizeLat:8 for: store <48 x i16> %v64i16, ptr %p, align 128100; CHECK-NEXT: Cost Model: Found costs of 2 for: %v8i32 = shufflevector <4 x i32> undef, <4 x i32> undef, <6 x i32> <i32 0, i32 2, i32 4, i32 1, i32 3, i32 5>101; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <6 x i32> %v8i32, ptr %p, align 32102; CHECK-NEXT: Cost Model: Found costs of 4 for: %v16i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>103; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <12 x i32> %v16i32, ptr %p, align 64104; CHECK-NEXT: Cost Model: Found costs of 8 for: %v32i32 = shufflevector <16 x i32> undef, <16 x i32> undef, <24 x i32> <i32 0, i32 8, i32 16, i32 1, i32 9, i32 17, i32 2, i32 10, i32 18, i32 3, i32 11, i32 19, i32 4, i32 12, i32 20, i32 5, i32 13, i32 21, i32 6, i32 14, i32 22, i32 7, i32 15, i32 23>105; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:1 SizeLat:8 for: store <24 x i32> %v32i32, ptr %p, align 128106; CHECK-NEXT: Cost Model: Found costs of 16 for: %v64i32 = shufflevector <32 x i32> undef, <32 x i32> undef, <48 x i32> <i32 0, i32 16, i32 32, i32 1, i32 17, i32 33, i32 2, i32 18, i32 34, i32 3, i32 19, i32 35, i32 4, i32 20, i32 36, i32 5, i32 21, i32 37, i32 6, i32 22, i32 38, i32 7, i32 23, i32 39, i32 8, i32 24, i32 40, i32 9, i32 25, i32 41, i32 10, i32 26, i32 42, i32 11, i32 27, i32 43, i32 12, i32 28, i32 44, i32 13, i32 29, i32 45, i32 14, i32 30, i32 46, i32 15, i32 31, i32 47>107; CHECK-NEXT: Cost Model: Found costs of RThru:16 CodeSize:16 Lat:1 SizeLat:16 for: store <48 x i32> %v64i32, ptr %p, align 256108; CHECK-NEXT: Cost Model: Found costs of 4 for: %v8i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <6 x i32> <i32 0, i32 2, i32 4, i32 1, i32 3, i32 5>109; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <6 x i64> %v8i64, ptr %p, align 64110; CHECK-NEXT: Cost Model: Found costs of 8 for: %v16i64 = shufflevector <8 x i64> undef, <8 x i64> undef, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>111; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:1 SizeLat:8 for: store <12 x i64> %v16i64, ptr %p, align 128112; CHECK-NEXT: Cost Model: Found costs of 16 for: %v32i64 = shufflevector <16 x i64> undef, <16 x i64> undef, <24 x i32> <i32 0, i32 8, i32 16, i32 1, i32 9, i32 17, i32 2, i32 10, i32 18, i32 3, i32 11, i32 19, i32 4, i32 12, i32 20, i32 5, i32 13, i32 21, i32 6, i32 14, i32 22, i32 7, i32 15, i32 23>113; CHECK-NEXT: Cost Model: Found costs of RThru:16 CodeSize:16 Lat:1 SizeLat:16 for: store <24 x i64> %v32i64, ptr %p, align 256114; CHECK-NEXT: Cost Model: Found costs of 32 for: %v64i64 = shufflevector <32 x i64> undef, <32 x i64> undef, <48 x i32> <i32 0, i32 16, i32 32, i32 1, i32 17, i32 33, i32 2, i32 18, i32 34, i32 3, i32 19, i32 35, i32 4, i32 20, i32 36, i32 5, i32 21, i32 37, i32 6, i32 22, i32 38, i32 7, i32 23, i32 39, i32 8, i32 24, i32 40, i32 9, i32 25, i32 41, i32 10, i32 26, i32 42, i32 11, i32 27, i32 43, i32 12, i32 28, i32 44, i32 13, i32 29, i32 45, i32 14, i32 30, i32 46, i32 15, i32 31, i32 47>115; CHECK-NEXT: Cost Model: Found costs of RThru:32 CodeSize:32 Lat:1 SizeLat:32 for: store <48 x i64> %v64i64, ptr %p, align 512116; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void117;118 %v8i8 = shufflevector <4 x i8> undef, <4 x i8> undef, <6 x i32> <i32 0, i32 2, i32 4, i32 1, i32 3, i32 5>119 store <6 x i8> %v8i8, ptr %p120 %v16i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>121 store <12 x i8> %v16i8, ptr %p122 %v32i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <24 x i32> <i32 0, i32 8, i32 16, i32 1, i32 9, i32 17, i32 2, i32 10, i32 18, i32 3, i32 11, i32 19, i32 4, i32 12, i32 20, i32 5, i32 13, i32 21, i32 6, i32 14, i32 22, i32 7, i32 15, i32 23>123 store <24 x i8> %v32i8, ptr %p124 %v64i8 = shufflevector <32 x i8> undef, <32 x i8> undef, <48 x i32> <i32 0, i32 16, i32 32, i32 1, i32 17, i32 33, i32 2, i32 18, i32 34, i32 3, i32 19, i32 35, i32 4, i32 20, i32 36, i32 5, i32 21, i32 37, i32 6, i32 22, i32 38, i32 7, i32 23, i32 39, i32 8, i32 24, i32 40, i32 9, i32 25, i32 41, i32 10, i32 26, i32 42, i32 11, i32 27, i32 43, i32 12, i32 28, i32 44, i32 13, i32 29, i32 45, i32 14, i32 30, i32 46, i32 15, i32 31, i32 47>125 store <48 x i8> %v64i8, ptr %p126 127 %v8i16 = shufflevector <4 x i16> undef, <4 x i16> undef, <6 x i32> <i32 0, i32 2, i32 4, i32 1, i32 3, i32 5>128 store <6 x i16> %v8i16, ptr %p129 %v16i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>130 store <12 x i16> %v16i16, ptr %p131 %v32i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <24 x i32> <i32 0, i32 8, i32 16, i32 1, i32 9, i32 17, i32 2, i32 10, i32 18, i32 3, i32 11, i32 19, i32 4, i32 12, i32 20, i32 5, i32 13, i32 21, i32 6, i32 14, i32 22, i32 7, i32 15, i32 23>132 store <24 x i16> %v32i16, ptr %p133 %v64i16 = shufflevector <32 x i16> undef, <32 x i16> undef, <48 x i32> <i32 0, i32 16, i32 32, i32 1, i32 17, i32 33, i32 2, i32 18, i32 34, i32 3, i32 19, i32 35, i32 4, i32 20, i32 36, i32 5, i32 21, i32 37, i32 6, i32 22, i32 38, i32 7, i32 23, i32 39, i32 8, i32 24, i32 40, i32 9, i32 25, i32 41, i32 10, i32 26, i32 42, i32 11, i32 27, i32 43, i32 12, i32 28, i32 44, i32 13, i32 29, i32 45, i32 14, i32 30, i32 46, i32 15, i32 31, i32 47>134 store <48 x i16> %v64i16, ptr %p135 136 %v8i32 = shufflevector <4 x i32> undef, <4 x i32> undef, <6 x i32> <i32 0, i32 2, i32 4, i32 1, i32 3, i32 5>137 store <6 x i32> %v8i32, ptr %p138 %v16i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>139 store <12 x i32> %v16i32, ptr %p140 %v32i32 = shufflevector <16 x i32> undef, <16 x i32> undef, <24 x i32> <i32 0, i32 8, i32 16, i32 1, i32 9, i32 17, i32 2, i32 10, i32 18, i32 3, i32 11, i32 19, i32 4, i32 12, i32 20, i32 5, i32 13, i32 21, i32 6, i32 14, i32 22, i32 7, i32 15, i32 23>141 store <24 x i32> %v32i32, ptr %p142 %v64i32 = shufflevector <32 x i32> undef, <32 x i32> undef, <48 x i32> <i32 0, i32 16, i32 32, i32 1, i32 17, i32 33, i32 2, i32 18, i32 34, i32 3, i32 19, i32 35, i32 4, i32 20, i32 36, i32 5, i32 21, i32 37, i32 6, i32 22, i32 38, i32 7, i32 23, i32 39, i32 8, i32 24, i32 40, i32 9, i32 25, i32 41, i32 10, i32 26, i32 42, i32 11, i32 27, i32 43, i32 12, i32 28, i32 44, i32 13, i32 29, i32 45, i32 14, i32 30, i32 46, i32 15, i32 31, i32 47>143 store <48 x i32> %v64i32, ptr %p144 145 %v8i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <6 x i32> <i32 0, i32 2, i32 4, i32 1, i32 3, i32 5>146 store <6 x i64> %v8i64, ptr %p147 %v16i64 = shufflevector <8 x i64> undef, <8 x i64> undef, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>148 store <12 x i64> %v16i64, ptr %p149 %v32i64 = shufflevector <16 x i64> undef, <16 x i64> undef, <24 x i32> <i32 0, i32 8, i32 16, i32 1, i32 9, i32 17, i32 2, i32 10, i32 18, i32 3, i32 11, i32 19, i32 4, i32 12, i32 20, i32 5, i32 13, i32 21, i32 6, i32 14, i32 22, i32 7, i32 15, i32 23>150 store <24 x i64> %v32i64, ptr %p151 %v64i64 = shufflevector <32 x i64> undef, <32 x i64> undef, <48 x i32> <i32 0, i32 16, i32 32, i32 1, i32 17, i32 33, i32 2, i32 18, i32 34, i32 3, i32 19, i32 35, i32 4, i32 20, i32 36, i32 5, i32 21, i32 37, i32 6, i32 22, i32 38, i32 7, i32 23, i32 39, i32 8, i32 24, i32 40, i32 9, i32 25, i32 41, i32 10, i32 26, i32 42, i32 11, i32 27, i32 43, i32 12, i32 28, i32 44, i32 13, i32 29, i32 45, i32 14, i32 30, i32 46, i32 15, i32 31, i32 47>152 store <48 x i64> %v64i64, ptr %p153 154 ret void155}156 157 158define void @vst4(ptr %p) {159; CHECK-LABEL: 'vst4'160; CHECK-NEXT: Cost Model: Found costs of 8 for: %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>161; CHECK-NEXT: Cost Model: Found costs of 1 for: store <8 x i8> %v8i8, ptr %p, align 8162; CHECK-NEXT: Cost Model: Found costs of 8 for: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 1, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>163; CHECK-NEXT: Cost Model: Found costs of 1 for: store <16 x i8> %v16i8, ptr %p, align 16164; CHECK-NEXT: Cost Model: Found costs of 2 for: %v32i8 = shufflevector <32 x i8> undef, <32 x i8> undef, <32 x i32> <i32 0, i32 8, i32 16, i32 24, i32 1, i32 9, i32 17, i32 25, i32 2, i32 10, i32 18, i32 26, i32 3, i32 11, i32 19, i32 27, i32 4, i32 12, i32 20, i32 28, i32 5, i32 13, i32 21, i32 29, i32 6, i32 14, i32 22, i32 30, i32 7, i32 15, i32 23, i32 31>165; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <32 x i8> %v32i8, ptr %p, align 32166; CHECK-NEXT: Cost Model: Found costs of 4 for: %v64i8 = shufflevector <64 x i8> undef, <64 x i8> undef, <64 x i32> <i32 0, i32 16, i32 32, i32 48, i32 1, i32 17, i32 33, i32 49, i32 2, i32 18, i32 34, i32 50, i32 3, i32 19, i32 35, i32 51, i32 4, i32 20, i32 36, i32 52, i32 5, i32 21, i32 37, i32 53, i32 6, i32 22, i32 38, i32 54, i32 7, i32 23, i32 39, i32 55, i32 8, i32 24, i32 40, i32 56, i32 9, i32 25, i32 41, i32 57, i32 10, i32 26, i32 42, i32 58, i32 11, i32 27, i32 43, i32 59, i32 12, i32 28, i32 44, i32 60, i32 13, i32 29, i32 45, i32 61, i32 14, i32 30, i32 46, i32 62, i32 15, i32 31, i32 47, i32 63>167; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <64 x i8> %v64i8, ptr %p, align 64168; CHECK-NEXT: Cost Model: Found costs of 8 for: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>169; CHECK-NEXT: Cost Model: Found costs of 1 for: store <8 x i16> %v8i16, ptr %p, align 16170; CHECK-NEXT: Cost Model: Found costs of 2 for: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 1, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>171; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <16 x i16> %v16i16, ptr %p, align 32172; CHECK-NEXT: Cost Model: Found costs of 4 for: %v32i16 = shufflevector <32 x i16> undef, <32 x i16> undef, <32 x i32> <i32 0, i32 8, i32 16, i32 24, i32 1, i32 9, i32 17, i32 25, i32 2, i32 10, i32 18, i32 26, i32 3, i32 11, i32 19, i32 27, i32 4, i32 12, i32 20, i32 28, i32 5, i32 13, i32 21, i32 29, i32 6, i32 14, i32 22, i32 30, i32 7, i32 15, i32 23, i32 31>173; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <32 x i16> %v32i16, ptr %p, align 64174; CHECK-NEXT: Cost Model: Found costs of 8 for: %v64i16 = shufflevector <64 x i16> undef, <64 x i16> undef, <64 x i32> <i32 0, i32 16, i32 32, i32 48, i32 1, i32 17, i32 33, i32 49, i32 2, i32 18, i32 34, i32 50, i32 3, i32 19, i32 35, i32 51, i32 4, i32 20, i32 36, i32 52, i32 5, i32 21, i32 37, i32 53, i32 6, i32 22, i32 38, i32 54, i32 7, i32 23, i32 39, i32 55, i32 8, i32 24, i32 40, i32 56, i32 9, i32 25, i32 41, i32 57, i32 10, i32 26, i32 42, i32 58, i32 11, i32 27, i32 43, i32 59, i32 12, i32 28, i32 44, i32 60, i32 13, i32 29, i32 45, i32 61, i32 14, i32 30, i32 46, i32 62, i32 15, i32 31, i32 47, i32 63>175; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:1 SizeLat:8 for: store <64 x i16> %v64i16, ptr %p, align 128176; CHECK-NEXT: Cost Model: Found costs of 2 for: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>177; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <8 x i32> %v8i32, ptr %p, align 32178; CHECK-NEXT: Cost Model: Found costs of 4 for: %v16i32 = shufflevector <16 x i32> undef, <16 x i32> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 1, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>179; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <16 x i32> %v16i32, ptr %p, align 64180; CHECK-NEXT: Cost Model: Found costs of 8 for: %v32i32 = shufflevector <32 x i32> undef, <32 x i32> undef, <32 x i32> <i32 0, i32 8, i32 16, i32 24, i32 1, i32 9, i32 17, i32 25, i32 2, i32 10, i32 18, i32 26, i32 3, i32 11, i32 19, i32 27, i32 4, i32 12, i32 20, i32 28, i32 5, i32 13, i32 21, i32 29, i32 6, i32 14, i32 22, i32 30, i32 7, i32 15, i32 23, i32 31>181; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:1 SizeLat:8 for: store <32 x i32> %v32i32, ptr %p, align 128182; CHECK-NEXT: Cost Model: Found costs of 16 for: %v64i32 = shufflevector <64 x i32> undef, <64 x i32> undef, <64 x i32> <i32 0, i32 16, i32 32, i32 48, i32 1, i32 17, i32 33, i32 49, i32 2, i32 18, i32 34, i32 50, i32 3, i32 19, i32 35, i32 51, i32 4, i32 20, i32 36, i32 52, i32 5, i32 21, i32 37, i32 53, i32 6, i32 22, i32 38, i32 54, i32 7, i32 23, i32 39, i32 55, i32 8, i32 24, i32 40, i32 56, i32 9, i32 25, i32 41, i32 57, i32 10, i32 26, i32 42, i32 58, i32 11, i32 27, i32 43, i32 59, i32 12, i32 28, i32 44, i32 60, i32 13, i32 29, i32 45, i32 61, i32 14, i32 30, i32 46, i32 62, i32 15, i32 31, i32 47, i32 63>183; CHECK-NEXT: Cost Model: Found costs of RThru:16 CodeSize:16 Lat:1 SizeLat:16 for: store <64 x i32> %v64i32, ptr %p, align 256184; CHECK-NEXT: Cost Model: Found costs of 4 for: %v8i64 = shufflevector <8 x i64> undef, <8 x i64> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>185; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <8 x i64> %v8i64, ptr %p, align 64186; CHECK-NEXT: Cost Model: Found costs of 8 for: %v16i64 = shufflevector <16 x i64> undef, <16 x i64> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 1, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>187; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:1 SizeLat:8 for: store <16 x i64> %v16i64, ptr %p, align 128188; CHECK-NEXT: Cost Model: Found costs of 16 for: %v32i64 = shufflevector <32 x i64> undef, <32 x i64> undef, <32 x i32> <i32 0, i32 8, i32 16, i32 24, i32 1, i32 9, i32 17, i32 25, i32 2, i32 10, i32 18, i32 26, i32 3, i32 11, i32 19, i32 27, i32 4, i32 12, i32 20, i32 28, i32 5, i32 13, i32 21, i32 29, i32 6, i32 14, i32 22, i32 30, i32 7, i32 15, i32 23, i32 31>189; CHECK-NEXT: Cost Model: Found costs of RThru:16 CodeSize:16 Lat:1 SizeLat:16 for: store <32 x i64> %v32i64, ptr %p, align 256190; CHECK-NEXT: Cost Model: Found costs of 32 for: %v64i64 = shufflevector <64 x i64> undef, <64 x i64> undef, <64 x i32> <i32 0, i32 16, i32 32, i32 48, i32 1, i32 17, i32 33, i32 49, i32 2, i32 18, i32 34, i32 50, i32 3, i32 19, i32 35, i32 51, i32 4, i32 20, i32 36, i32 52, i32 5, i32 21, i32 37, i32 53, i32 6, i32 22, i32 38, i32 54, i32 7, i32 23, i32 39, i32 55, i32 8, i32 24, i32 40, i32 56, i32 9, i32 25, i32 41, i32 57, i32 10, i32 26, i32 42, i32 58, i32 11, i32 27, i32 43, i32 59, i32 12, i32 28, i32 44, i32 60, i32 13, i32 29, i32 45, i32 61, i32 14, i32 30, i32 46, i32 62, i32 15, i32 31, i32 47, i32 63>191; CHECK-NEXT: Cost Model: Found costs of RThru:32 CodeSize:32 Lat:1 SizeLat:32 for: store <64 x i64> %v64i64, ptr %p, align 512192; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void193;194 %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>195 store <8 x i8> %v8i8, ptr %p196 %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 1, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>197 store <16 x i8> %v16i8, ptr %p198 %v32i8 = shufflevector <32 x i8> undef, <32 x i8> undef, <32 x i32> <i32 0, i32 8, i32 16, i32 24, i32 1, i32 9, i32 17, i32 25, i32 2, i32 10, i32 18, i32 26, i32 3, i32 11, i32 19, i32 27, i32 4, i32 12, i32 20, i32 28, i32 5, i32 13, i32 21, i32 29, i32 6, i32 14, i32 22, i32 30, i32 7, i32 15, i32 23, i32 31>199 store <32 x i8> %v32i8, ptr %p200 %v64i8 = shufflevector <64 x i8> undef, <64 x i8> undef, <64 x i32> <i32 0, i32 16, i32 32, i32 48, i32 1, i32 17, i32 33, i32 49, i32 2, i32 18, i32 34, i32 50, i32 3, i32 19, i32 35, i32 51, i32 4, i32 20, i32 36, i32 52, i32 5, i32 21, i32 37, i32 53, i32 6, i32 22, i32 38, i32 54, i32 7, i32 23, i32 39, i32 55, i32 8, i32 24, i32 40, i32 56, i32 9, i32 25, i32 41, i32 57, i32 10, i32 26, i32 42, i32 58, i32 11, i32 27, i32 43, i32 59, i32 12, i32 28, i32 44, i32 60, i32 13, i32 29, i32 45, i32 61, i32 14, i32 30, i32 46, i32 62, i32 15, i32 31, i32 47, i32 63>201 store <64 x i8> %v64i8, ptr %p202 203 %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>204 store <8 x i16> %v8i16, ptr %p205 %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 1, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>206 store <16 x i16> %v16i16, ptr %p207 %v32i16 = shufflevector <32 x i16> undef, <32 x i16> undef, <32 x i32> <i32 0, i32 8, i32 16, i32 24, i32 1, i32 9, i32 17, i32 25, i32 2, i32 10, i32 18, i32 26, i32 3, i32 11, i32 19, i32 27, i32 4, i32 12, i32 20, i32 28, i32 5, i32 13, i32 21, i32 29, i32 6, i32 14, i32 22, i32 30, i32 7, i32 15, i32 23, i32 31>208 store <32 x i16> %v32i16, ptr %p209 %v64i16 = shufflevector <64 x i16> undef, <64 x i16> undef, <64 x i32> <i32 0, i32 16, i32 32, i32 48, i32 1, i32 17, i32 33, i32 49, i32 2, i32 18, i32 34, i32 50, i32 3, i32 19, i32 35, i32 51, i32 4, i32 20, i32 36, i32 52, i32 5, i32 21, i32 37, i32 53, i32 6, i32 22, i32 38, i32 54, i32 7, i32 23, i32 39, i32 55, i32 8, i32 24, i32 40, i32 56, i32 9, i32 25, i32 41, i32 57, i32 10, i32 26, i32 42, i32 58, i32 11, i32 27, i32 43, i32 59, i32 12, i32 28, i32 44, i32 60, i32 13, i32 29, i32 45, i32 61, i32 14, i32 30, i32 46, i32 62, i32 15, i32 31, i32 47, i32 63>210 store <64 x i16> %v64i16, ptr %p211 212 %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>213 store <8 x i32> %v8i32, ptr %p214 %v16i32 = shufflevector <16 x i32> undef, <16 x i32> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 1, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>215 store <16 x i32> %v16i32, ptr %p216 %v32i32 = shufflevector <32 x i32> undef, <32 x i32> undef, <32 x i32> <i32 0, i32 8, i32 16, i32 24, i32 1, i32 9, i32 17, i32 25, i32 2, i32 10, i32 18, i32 26, i32 3, i32 11, i32 19, i32 27, i32 4, i32 12, i32 20, i32 28, i32 5, i32 13, i32 21, i32 29, i32 6, i32 14, i32 22, i32 30, i32 7, i32 15, i32 23, i32 31>217 store <32 x i32> %v32i32, ptr %p218 %v64i32 = shufflevector <64 x i32> undef, <64 x i32> undef, <64 x i32> <i32 0, i32 16, i32 32, i32 48, i32 1, i32 17, i32 33, i32 49, i32 2, i32 18, i32 34, i32 50, i32 3, i32 19, i32 35, i32 51, i32 4, i32 20, i32 36, i32 52, i32 5, i32 21, i32 37, i32 53, i32 6, i32 22, i32 38, i32 54, i32 7, i32 23, i32 39, i32 55, i32 8, i32 24, i32 40, i32 56, i32 9, i32 25, i32 41, i32 57, i32 10, i32 26, i32 42, i32 58, i32 11, i32 27, i32 43, i32 59, i32 12, i32 28, i32 44, i32 60, i32 13, i32 29, i32 45, i32 61, i32 14, i32 30, i32 46, i32 62, i32 15, i32 31, i32 47, i32 63>219 store <64 x i32> %v64i32, ptr %p220 221 %v8i64 = shufflevector <8 x i64> undef, <8 x i64> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>222 store <8 x i64> %v8i64, ptr %p223 %v16i64 = shufflevector <16 x i64> undef, <16 x i64> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 1, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>224 store <16 x i64> %v16i64, ptr %p225 %v32i64 = shufflevector <32 x i64> undef, <32 x i64> undef, <32 x i32> <i32 0, i32 8, i32 16, i32 24, i32 1, i32 9, i32 17, i32 25, i32 2, i32 10, i32 18, i32 26, i32 3, i32 11, i32 19, i32 27, i32 4, i32 12, i32 20, i32 28, i32 5, i32 13, i32 21, i32 29, i32 6, i32 14, i32 22, i32 30, i32 7, i32 15, i32 23, i32 31>226 store <32 x i64> %v32i64, ptr %p227 %v64i64 = shufflevector <64 x i64> undef, <64 x i64> undef, <64 x i32> <i32 0, i32 16, i32 32, i32 48, i32 1, i32 17, i32 33, i32 49, i32 2, i32 18, i32 34, i32 50, i32 3, i32 19, i32 35, i32 51, i32 4, i32 20, i32 36, i32 52, i32 5, i32 21, i32 37, i32 53, i32 6, i32 22, i32 38, i32 54, i32 7, i32 23, i32 39, i32 55, i32 8, i32 24, i32 40, i32 56, i32 9, i32 25, i32 41, i32 57, i32 10, i32 26, i32 42, i32 58, i32 11, i32 27, i32 43, i32 59, i32 12, i32 28, i32 44, i32 60, i32 13, i32 29, i32 45, i32 61, i32 14, i32 30, i32 46, i32 62, i32 15, i32 31, i32 47, i32 63>228 store <64 x i64> %v64i64, ptr %p229 230 ret void231}232 233 234define void @splatstore(ptr %p) {235; CHECK-LABEL: 'splatstore'236; CHECK-NEXT: Cost Model: Found costs of 1 for: %v4i8 = shufflevector <4 x i8> undef, <4 x i8> undef, <4 x i32> zeroinitializer237; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <4 x i8> %v4i8, ptr %p, align 4238; CHECK-NEXT: Cost Model: Found costs of 1 for: %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> zeroinitializer239; CHECK-NEXT: Cost Model: Found costs of 1 for: store <8 x i8> %v8i8, ptr %p, align 8240; CHECK-NEXT: Cost Model: Found costs of 1 for: %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> zeroinitializer241; CHECK-NEXT: Cost Model: Found costs of 1 for: store <16 x i8> %v16i8, ptr %p, align 16242; CHECK-NEXT: Cost Model: Found costs of 1 for: %v32i8 = shufflevector <32 x i8> undef, <32 x i8> undef, <32 x i32> zeroinitializer243; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <32 x i8> %v32i8, ptr %p, align 32244; CHECK-NEXT: Cost Model: Found costs of 1 for: %v64i8 = shufflevector <64 x i8> undef, <64 x i8> undef, <64 x i32> zeroinitializer245; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <64 x i8> %v64i8, ptr %p, align 64246; CHECK-NEXT: Cost Model: Found costs of 1 for: %v4i16 = shufflevector <4 x i16> undef, <4 x i16> undef, <4 x i32> zeroinitializer247; CHECK-NEXT: Cost Model: Found costs of 1 for: store <4 x i16> %v4i16, ptr %p, align 8248; CHECK-NEXT: Cost Model: Found costs of 1 for: %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> zeroinitializer249; CHECK-NEXT: Cost Model: Found costs of 1 for: store <8 x i16> %v8i16, ptr %p, align 16250; CHECK-NEXT: Cost Model: Found costs of 1 for: %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> zeroinitializer251; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <16 x i16> %v16i16, ptr %p, align 32252; CHECK-NEXT: Cost Model: Found costs of 1 for: %v32i16 = shufflevector <32 x i16> undef, <32 x i16> undef, <32 x i32> zeroinitializer253; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <32 x i16> %v32i16, ptr %p, align 64254; CHECK-NEXT: Cost Model: Found costs of 1 for: %v64i16 = shufflevector <64 x i16> undef, <64 x i16> undef, <64 x i32> zeroinitializer255; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:1 SizeLat:8 for: store <64 x i16> %v64i16, ptr %p, align 128256; CHECK-NEXT: Cost Model: Found costs of 1 for: %v4i32 = shufflevector <4 x i32> undef, <4 x i32> undef, <4 x i32> zeroinitializer257; CHECK-NEXT: Cost Model: Found costs of 1 for: store <4 x i32> %v4i32, ptr %p, align 16258; CHECK-NEXT: Cost Model: Found costs of 1 for: %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> zeroinitializer259; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <8 x i32> %v8i32, ptr %p, align 32260; CHECK-NEXT: Cost Model: Found costs of 1 for: %v16i32 = shufflevector <16 x i32> undef, <16 x i32> undef, <16 x i32> zeroinitializer261; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <16 x i32> %v16i32, ptr %p, align 64262; CHECK-NEXT: Cost Model: Found costs of 1 for: %v32i32 = shufflevector <32 x i32> undef, <32 x i32> undef, <32 x i32> zeroinitializer263; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:1 SizeLat:8 for: store <32 x i32> %v32i32, ptr %p, align 128264; CHECK-NEXT: Cost Model: Found costs of 1 for: %v64i32 = shufflevector <64 x i32> undef, <64 x i32> undef, <64 x i32> zeroinitializer265; CHECK-NEXT: Cost Model: Found costs of RThru:16 CodeSize:16 Lat:1 SizeLat:16 for: store <64 x i32> %v64i32, ptr %p, align 256266; CHECK-NEXT: Cost Model: Found costs of 2 for: %v4i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <4 x i32> zeroinitializer267; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:2 Lat:1 SizeLat:2 for: store <4 x i64> %v4i64, ptr %p, align 32268; CHECK-NEXT: Cost Model: Found costs of 1 for: %v8i64 = shufflevector <8 x i64> undef, <8 x i64> undef, <8 x i32> zeroinitializer269; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:4 Lat:1 SizeLat:4 for: store <8 x i64> %v8i64, ptr %p, align 64270; CHECK-NEXT: Cost Model: Found costs of 1 for: %v16i64 = shufflevector <16 x i64> undef, <16 x i64> undef, <16 x i32> zeroinitializer271; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:8 Lat:1 SizeLat:8 for: store <16 x i64> %v16i64, ptr %p, align 128272; CHECK-NEXT: Cost Model: Found costs of 1 for: %v32i64 = shufflevector <32 x i64> undef, <32 x i64> undef, <32 x i32> zeroinitializer273; CHECK-NEXT: Cost Model: Found costs of RThru:16 CodeSize:16 Lat:1 SizeLat:16 for: store <32 x i64> %v32i64, ptr %p, align 256274; CHECK-NEXT: Cost Model: Found costs of 1 for: %v64i64 = shufflevector <64 x i64> undef, <64 x i64> undef, <64 x i32> zeroinitializer275; CHECK-NEXT: Cost Model: Found costs of RThru:32 CodeSize:32 Lat:1 SizeLat:32 for: store <64 x i64> %v64i64, ptr %p, align 512276; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void277;278 %v4i8 = shufflevector <4 x i8> undef, <4 x i8> undef, <4 x i32> zeroinitializer279 store <4 x i8> %v4i8, ptr %p280 %v8i8 = shufflevector <8 x i8> undef, <8 x i8> undef, <8 x i32> zeroinitializer281 store <8 x i8> %v8i8, ptr %p282 %v16i8 = shufflevector <16 x i8> undef, <16 x i8> undef, <16 x i32> zeroinitializer283 store <16 x i8> %v16i8, ptr %p284 %v32i8 = shufflevector <32 x i8> undef, <32 x i8> undef, <32 x i32> zeroinitializer285 store <32 x i8> %v32i8, ptr %p286 %v64i8 = shufflevector <64 x i8> undef, <64 x i8> undef, <64 x i32> zeroinitializer287 store <64 x i8> %v64i8, ptr %p288 289 %v4i16 = shufflevector <4 x i16> undef, <4 x i16> undef, <4 x i32> zeroinitializer290 store <4 x i16> %v4i16, ptr %p291 %v8i16 = shufflevector <8 x i16> undef, <8 x i16> undef, <8 x i32> zeroinitializer292 store <8 x i16> %v8i16, ptr %p293 %v16i16 = shufflevector <16 x i16> undef, <16 x i16> undef, <16 x i32> zeroinitializer294 store <16 x i16> %v16i16, ptr %p295 %v32i16 = shufflevector <32 x i16> undef, <32 x i16> undef, <32 x i32> zeroinitializer296 store <32 x i16> %v32i16, ptr %p297 %v64i16 = shufflevector <64 x i16> undef, <64 x i16> undef, <64 x i32> zeroinitializer298 store <64 x i16> %v64i16, ptr %p299 300 %v4i32 = shufflevector <4 x i32> undef, <4 x i32> undef, <4 x i32> zeroinitializer301 store <4 x i32> %v4i32, ptr %p302 %v8i32 = shufflevector <8 x i32> undef, <8 x i32> undef, <8 x i32> zeroinitializer303 store <8 x i32> %v8i32, ptr %p304 %v16i32 = shufflevector <16 x i32> undef, <16 x i32> undef, <16 x i32> zeroinitializer305 store <16 x i32> %v16i32, ptr %p306 %v32i32 = shufflevector <32 x i32> undef, <32 x i32> undef, <32 x i32> zeroinitializer307 store <32 x i32> %v32i32, ptr %p308 %v64i32 = shufflevector <64 x i32> undef, <64 x i32> undef, <64 x i32> zeroinitializer309 store <64 x i32> %v64i32, ptr %p310 311 %v4i64 = shufflevector <4 x i64> undef, <4 x i64> undef, <4 x i32> zeroinitializer312 store <4 x i64> %v4i64, ptr %p313 %v8i64 = shufflevector <8 x i64> undef, <8 x i64> undef, <8 x i32> zeroinitializer314 store <8 x i64> %v8i64, ptr %p315 %v16i64 = shufflevector <16 x i64> undef, <16 x i64> undef, <16 x i32> zeroinitializer316 store <16 x i64> %v16i64, ptr %p317 %v32i64 = shufflevector <32 x i64> undef, <32 x i64> undef, <32 x i32> zeroinitializer318 store <32 x i64> %v32i64, ptr %p319 %v64i64 = shufflevector <64 x i64> undef, <64 x i64> undef, <64 x i32> zeroinitializer320 store <64 x i64> %v64i64, ptr %p321 322 ret void323}324 325