; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve < %s | FileCheck %s --check-prefixes=CHECK,CHECK-UF2
; RUN: opt -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve.fp < %s | FileCheck %s --check-prefixes=CHECK,CHECK-UF2
; RUN: opt -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve -mve-max-interleave-factor=4 < %s | FileCheck %s --check-prefixes=CHECK,CHECK-UF4
; RUN: opt -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve.fp -mve-max-interleave-factor=4 < %s | FileCheck %s --check-prefixes=CHECK,CHECK-UF4

define void @vld2(ptr %p) {
; CHECK-LABEL: 'vld2'
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %v4i8 = load <4 x i8>, ptr %p, align 4
; CHECK-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v4i8_0 = shufflevector <4 x i8> %v4i8, <4 x i8> undef, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v4i8_1 = shufflevector <4 x i8> %v4i8, <4 x i8> undef, <2 x i32> <i32 1, i32 3>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %v8i8 = load <8 x i8>, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v8i8_0 = shufflevector <8 x i8> %v8i8, <8 x i8> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
; CHECK-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v8i8_1 = shufflevector <8 x i8> %v8i8, <8 x i8> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %v16i8 = load <16 x i8>, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v16i8_0 = shufflevector <16 x i8> %v16i8, <16 x i8> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
; CHECK-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v16i8_1 = shufflevector <16 x i8> %v16i8, <16 x i8> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v32i8 = load <32 x i8>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:258 CodeSize:129 Lat:258 SizeLat:258 for: %v32i8_0 = shufflevector <32 x i8> %v32i8, <32 x i8> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
; CHECK-NEXT:  Cost Model: Found costs of RThru:258 CodeSize:129 Lat:258 SizeLat:258 for: %v32i8_1 = shufflevector <32 x i8> %v32i8, <32 x i8> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %v4i16 = load <4 x i16>, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v4i16_0 = shufflevector <4 x i16> %v4i16, <4 x i16> undef, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v4i16_1 = shufflevector <4 x i16> %v4i16, <4 x i16> undef, <2 x i32> <i32 1, i32 3>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %v8i16 = load <8 x i16>, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v8i16_0 = shufflevector <8 x i16> %v8i16, <8 x i16> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
; CHECK-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v8i16_1 = shufflevector <8 x i16> %v8i16, <8 x i16> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v16i16 = load <16 x i16>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v16i16_0 = shufflevector <16 x i16> %v16i16, <16 x i16> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
; CHECK-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v16i16_1 = shufflevector <16 x i16> %v16i16, <16 x i16> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v32i16 = load <32 x i16>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:258 CodeSize:129 Lat:258 SizeLat:258 for: %v32i16_0 = shufflevector <32 x i16> %v32i16, <32 x i16> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
; CHECK-NEXT:  Cost Model: Found costs of RThru:258 CodeSize:129 Lat:258 SizeLat:258 for: %v32i16_1 = shufflevector <32 x i16> %v32i16, <32 x i16> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %v4i32 = load <4 x i32>, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v4i32_0 = shufflevector <4 x i32> %v4i32, <4 x i32> undef, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v4i32_1 = shufflevector <4 x i32> %v4i32, <4 x i32> undef, <2 x i32> <i32 1, i32 3>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v8i32 = load <8 x i32>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v8i32_0 = shufflevector <8 x i32> %v8i32, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
; CHECK-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v8i32_1 = shufflevector <8 x i32> %v8i32, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v16i32 = load <16 x i32>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v16i32_0 = shufflevector <16 x i32> %v16i32, <16 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
; CHECK-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v16i32_1 = shufflevector <16 x i32> %v16i32, <16 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
; CHECK-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:4 SizeLat:1 for: %v32i32 = load <32 x i32>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of RThru:260 CodeSize:130 Lat:260 SizeLat:260 for: %v32i32_0 = shufflevector <32 x i32> %v32i32, <32 x i32> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
; CHECK-NEXT:  Cost Model: Found costs of RThru:260 CodeSize:130 Lat:260 SizeLat:260 for: %v32i32_1 = shufflevector <32 x i32> %v32i32, <32 x i32> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v2i64 = load <4 x i64>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:192 CodeSize:96 Lat:192 SizeLat:192 for: %v2i64_0 = shufflevector <4 x i64> %v2i64, <4 x i64> undef, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT:  Cost Model: Found costs of RThru:192 CodeSize:96 Lat:192 SizeLat:192 for: %v2i64_1 = shufflevector <4 x i64> %v2i64, <4 x i64> undef, <2 x i32> <i32 1, i32 3>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v4i64 = load <8 x i64>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:384 CodeSize:192 Lat:384 SizeLat:384 for: %v4i64_0 = shufflevector <8 x i64> %v4i64, <8 x i64> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
; CHECK-NEXT:  Cost Model: Found costs of RThru:384 CodeSize:192 Lat:384 SizeLat:384 for: %v4i64_1 = shufflevector <8 x i64> %v4i64, <8 x i64> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
; CHECK-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:4 SizeLat:1 for: %v8i64 = load <16 x i64>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of RThru:768 CodeSize:384 Lat:768 SizeLat:768 for: %v8i64_0 = shufflevector <16 x i64> %v8i64, <16 x i64> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
; CHECK-NEXT:  Cost Model: Found costs of RThru:768 CodeSize:384 Lat:768 SizeLat:768 for: %v8i64_1 = shufflevector <16 x i64> %v8i64, <16 x i64> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
; CHECK-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:4 SizeLat:1 for: %v16i64 = load <32 x i64>, ptr %p, align 256
; CHECK-NEXT:  Cost Model: Found costs of RThru:1536 CodeSize:768 Lat:1536 SizeLat:1536 for: %v16i64_0 = shufflevector <32 x i64> %v16i64, <32 x i64> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
; CHECK-NEXT:  Cost Model: Found costs of RThru:1536 CodeSize:768 Lat:1536 SizeLat:1536 for: %v16i64_1 = shufflevector <32 x i64> %v16i64, <32 x i64> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %v4i8 = load <4 x i8>, ptr %p
  %v4i8_0 = shufflevector <4 x i8> %v4i8, <4 x i8> undef, <2 x i32> <i32 0, i32 2>
  %v4i8_1 = shufflevector <4 x i8> %v4i8, <4 x i8> undef, <2 x i32> <i32 1, i32 3>
  %v8i8 = load <8 x i8>, ptr %p
  %v8i8_0 = shufflevector <8 x i8> %v8i8, <8 x i8> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
  %v8i8_1 = shufflevector <8 x i8> %v8i8, <8 x i8> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
  %v16i8 = load <16 x i8>, ptr %p
  %v16i8_0 = shufflevector <16 x i8> %v16i8, <16 x i8> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
  %v16i8_1 = shufflevector <16 x i8> %v16i8, <16 x i8> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
  %v32i8 = load <32 x i8>, ptr %p
  %v32i8_0 = shufflevector <32 x i8> %v32i8, <32 x i8> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
  %v32i8_1 = shufflevector <32 x i8> %v32i8, <32 x i8> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>

  %v4i16 = load <4 x i16>, ptr %p
  %v4i16_0 = shufflevector <4 x i16> %v4i16, <4 x i16> undef, <2 x i32> <i32 0, i32 2>
  %v4i16_1 = shufflevector <4 x i16> %v4i16, <4 x i16> undef, <2 x i32> <i32 1, i32 3>
  %v8i16 = load <8 x i16>, ptr %p
  %v8i16_0 = shufflevector <8 x i16> %v8i16, <8 x i16> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
  %v8i16_1 = shufflevector <8 x i16> %v8i16, <8 x i16> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
  %v16i16 = load <16 x i16>, ptr %p
  %v16i16_0 = shufflevector <16 x i16> %v16i16, <16 x i16> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
  %v16i16_1 = shufflevector <16 x i16> %v16i16, <16 x i16> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
  %v32i16 = load <32 x i16>, ptr %p
  %v32i16_0 = shufflevector <32 x i16> %v32i16, <32 x i16> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
  %v32i16_1 = shufflevector <32 x i16> %v32i16, <32 x i16> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>

  %v4i32 = load <4 x i32>, ptr %p
  %v4i32_0 = shufflevector <4 x i32> %v4i32, <4 x i32> undef, <2 x i32> <i32 0, i32 2>
  %v4i32_1 = shufflevector <4 x i32> %v4i32, <4 x i32> undef, <2 x i32> <i32 1, i32 3>
  %v8i32 = load <8 x i32>, ptr %p
  %v8i32_0 = shufflevector <8 x i32> %v8i32, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
  %v8i32_1 = shufflevector <8 x i32> %v8i32, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
  %v16i32 = load <16 x i32>, ptr %p
  %v16i32_0 = shufflevector <16 x i32> %v16i32, <16 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
  %v16i32_1 = shufflevector <16 x i32> %v16i32, <16 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
  %v32i32 = load <32 x i32>, ptr %p
  %v32i32_0 = shufflevector <32 x i32> %v32i32, <32 x i32> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
  %v32i32_1 = shufflevector <32 x i32> %v32i32, <32 x i32> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>

  %v2i64 = load <4 x i64>, ptr %p
  %v2i64_0 = shufflevector <4 x i64> %v2i64, <4 x i64> undef, <2 x i32> <i32 0, i32 2>
  %v2i64_1 = shufflevector <4 x i64> %v2i64, <4 x i64> undef, <2 x i32> <i32 1, i32 3>
  %v4i64 = load <8 x i64>, ptr %p
  %v4i64_0 = shufflevector <8 x i64> %v4i64, <8 x i64> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
  %v4i64_1 = shufflevector <8 x i64> %v4i64, <8 x i64> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
  %v8i64 = load <16 x i64>, ptr %p
  %v8i64_0 = shufflevector <16 x i64> %v8i64, <16 x i64> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
  %v8i64_1 = shufflevector <16 x i64> %v8i64, <16 x i64> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
  %v16i64 = load <32 x i64>, ptr %p
  %v16i64_0 = shufflevector <32 x i64> %v16i64, <32 x i64> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
  %v16i64_1 = shufflevector <32 x i64> %v16i64, <32 x i64> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>

  ret void
}


define void @vld3(ptr %p) {
; CHECK-LABEL: 'vld3'
; CHECK-NEXT:  Cost Model: Found costs of RThru:50 CodeSize:1 Lat:4 SizeLat:1 for: %v2i8 = load <6 x i8>, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 for: %v2i8_0 = shufflevector <6 x i8> %v2i8, <6 x i8> undef, <2 x i32> <i32 0, i32 3>
; CHECK-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 for: %v2i8_1 = shufflevector <6 x i8> %v2i8, <6 x i8> undef, <2 x i32> <i32 1, i32 4>
; CHECK-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 for: %v2i8_2 = shufflevector <6 x i8> %v2i8, <6 x i8> undef, <2 x i32> <i32 2, i32 5>
; CHECK-NEXT:  Cost Model: Found costs of RThru:98 CodeSize:1 Lat:4 SizeLat:1 for: %v4i8 = load <12 x i8>, ptr %p, align 16
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 for: %v4i8_0 = shufflevector <12 x i8> %v4i8, <12 x i8> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 for: %v4i8_1 = shufflevector <12 x i8> %v4i8, <12 x i8> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 for: %v4i8_2 = shufflevector <12 x i8> %v4i8, <12 x i8> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v8i8 = load <24 x i8>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 for: %v8i8_0 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 for: %v8i8_1 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 for: %v8i8_2 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v16i8 = load <48 x i8>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 for: %v16i8_0 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 for: %v16i8_1 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 for: %v16i8_2 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
; CHECK-NEXT:  Cost Model: Found costs of RThru:50 CodeSize:1 Lat:4 SizeLat:1 for: %v2i16 = load <6 x i16>, ptr %p, align 16
; CHECK-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 for: %v2i16_0 = shufflevector <6 x i16> %v2i16, <6 x i16> undef, <2 x i32> <i32 0, i32 3>
; CHECK-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 for: %v2i16_1 = shufflevector <6 x i16> %v2i16, <6 x i16> undef, <2 x i32> <i32 1, i32 4>
; CHECK-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 for: %v2i16_2 = shufflevector <6 x i16> %v2i16, <6 x i16> undef, <2 x i32> <i32 2, i32 5>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v4i16 = load <12 x i16>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 for: %v4i16_0 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 for: %v4i16_1 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 for: %v4i16_2 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v8i16 = load <24 x i16>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 for: %v8i16_0 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 for: %v8i16_1 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 for: %v8i16_2 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
; CHECK-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:4 SizeLat:1 for: %v16i16 = load <48 x i16>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 for: %v16i16_0 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 for: %v16i16_1 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 for: %v16i16_2 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v2i32 = load <6 x i32>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 for: %v2i32_0 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 0, i32 3>
; CHECK-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 for: %v2i32_1 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 1, i32 4>
; CHECK-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 for: %v2i32_2 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 2, i32 5>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v4i32 = load <12 x i32>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 for: %v4i32_0 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 for: %v4i32_1 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 for: %v4i32_2 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
; CHECK-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:4 SizeLat:1 for: %v8i32 = load <24 x i32>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 for: %v8i32_0 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 for: %v8i32_1 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 for: %v8i32_2 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
; CHECK-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:4 SizeLat:1 for: %v16i32 = load <48 x i32>, ptr %p, align 256
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 for: %v16i32_0 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 for: %v16i32_1 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 for: %v16i32_2 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v2i64 = load <6 x i64>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 for: %v2i64_0 = shufflevector <6 x i64> %v2i64, <6 x i64> undef, <2 x i32> <i32 0, i32 3>
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 for: %v2i64_1 = shufflevector <6 x i64> %v2i64, <6 x i64> undef, <2 x i32> <i32 1, i32 4>
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 for: %v2i64_2 = shufflevector <6 x i64> %v2i64, <6 x i64> undef, <2 x i32> <i32 2, i32 5>
; CHECK-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:4 SizeLat:1 for: %v4i64 = load <12 x i64>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 for: %v4i64_0 = shufflevector <12 x i64> %v4i64, <12 x i64> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 for: %v4i64_1 = shufflevector <12 x i64> %v4i64, <12 x i64> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 for: %v4i64_2 = shufflevector <12 x i64> %v4i64, <12 x i64> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
; CHECK-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:4 SizeLat:1 for: %v8i64 = load <24 x i64>, ptr %p, align 256
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 for: %v8i64_0 = shufflevector <24 x i64> %v8i64, <24 x i64> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 for: %v8i64_1 = shufflevector <24 x i64> %v8i64, <24 x i64> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 for: %v8i64_2 = shufflevector <24 x i64> %v8i64, <24 x i64> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
; CHECK-NEXT:  Cost Model: Found costs of RThru:64 CodeSize:1 Lat:4 SizeLat:1 for: %v16i64 = load <48 x i64>, ptr %p, align 512
; CHECK-NEXT:  Cost Model: Found costs of RThru:2048 CodeSize:1024 Lat:2048 SizeLat:2048 for: %v16i64_0 = shufflevector <48 x i64> %v16i64, <48 x i64> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2048 CodeSize:1024 Lat:2048 SizeLat:2048 for: %v16i64_1 = shufflevector <48 x i64> %v16i64, <48 x i64> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2048 CodeSize:1024 Lat:2048 SizeLat:2048 for: %v16i64_2 = shufflevector <48 x i64> %v16i64, <48 x i64> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %v2i8 = load <6 x i8>, ptr %p
  %v2i8_0 = shufflevector <6 x i8> %v2i8, <6 x i8> undef, <2 x i32> <i32 0, i32 3>
  %v2i8_1 = shufflevector <6 x i8> %v2i8, <6 x i8> undef, <2 x i32> <i32 1, i32 4>
  %v2i8_2 = shufflevector <6 x i8> %v2i8, <6 x i8> undef, <2 x i32> <i32 2, i32 5>
  %v4i8 = load <12 x i8>, ptr %p
  %v4i8_0 = shufflevector <12 x i8> %v4i8, <12 x i8> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
  %v4i8_1 = shufflevector <12 x i8> %v4i8, <12 x i8> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
  %v4i8_2 = shufflevector <12 x i8> %v4i8, <12 x i8> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
  %v8i8 = load <24 x i8>, ptr %p
  %v8i8_0 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
  %v8i8_1 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
  %v8i8_2 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
  %v16i8 = load <48 x i8>, ptr %p
  %v16i8_0 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
  %v16i8_1 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
  %v16i8_2 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>

  %v2i16 = load <6 x i16>, ptr %p
  %v2i16_0 = shufflevector <6 x i16> %v2i16, <6 x i16> undef, <2 x i32> <i32 0, i32 3>
  %v2i16_1 = shufflevector <6 x i16> %v2i16, <6 x i16> undef, <2 x i32> <i32 1, i32 4>
  %v2i16_2 = shufflevector <6 x i16> %v2i16, <6 x i16> undef, <2 x i32> <i32 2, i32 5>
  %v4i16 = load <12 x i16>, ptr %p
  %v4i16_0 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
  %v4i16_1 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
  %v4i16_2 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
  %v8i16 = load <24 x i16>, ptr %p
  %v8i16_0 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
  %v8i16_1 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
  %v8i16_2 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
  %v16i16 = load <48 x i16>, ptr %p
  %v16i16_0 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
  %v16i16_1 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
  %v16i16_2 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>

  %v2i32 = load <6 x i32>, ptr %p
  %v2i32_0 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 0, i32 3>
  %v2i32_1 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 1, i32 4>
  %v2i32_2 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 2, i32 5>
  %v4i32 = load <12 x i32>, ptr %p
  %v4i32_0 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
  %v4i32_1 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
  %v4i32_2 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
  %v8i32 = load <24 x i32>, ptr %p
  %v8i32_0 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
  %v8i32_1 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
  %v8i32_2 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
  %v16i32 = load <48 x i32>, ptr %p
  %v16i32_0 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
  %v16i32_1 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
  %v16i32_2 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>

  %v2i64 = load <6 x i64>, ptr %p
  %v2i64_0 = shufflevector <6 x i64> %v2i64, <6 x i64> undef, <2 x i32> <i32 0, i32 3>
  %v2i64_1 = shufflevector <6 x i64> %v2i64, <6 x i64> undef, <2 x i32> <i32 1, i32 4>
  %v2i64_2 = shufflevector <6 x i64> %v2i64, <6 x i64> undef, <2 x i32> <i32 2, i32 5>
  %v4i64 = load <12 x i64>, ptr %p
  %v4i64_0 = shufflevector <12 x i64> %v4i64, <12 x i64> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
  %v4i64_1 = shufflevector <12 x i64> %v4i64, <12 x i64> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
  %v4i64_2 = shufflevector <12 x i64> %v4i64, <12 x i64> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
  %v8i64 = load <24 x i64>, ptr %p
  %v8i64_0 = shufflevector <24 x i64> %v8i64, <24 x i64> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
  %v8i64_1 = shufflevector <24 x i64> %v8i64, <24 x i64> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
  %v8i64_2 = shufflevector <24 x i64> %v8i64, <24 x i64> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
  %v16i64 = load <48 x i64>, ptr %p
  %v16i64_0 = shufflevector <48 x i64> %v16i64, <48 x i64> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
  %v16i64_1 = shufflevector <48 x i64> %v16i64, <48 x i64> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
  %v16i64_2 = shufflevector <48 x i64> %v16i64, <48 x i64> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>

  ret void
}

define void @vld4(ptr %p) {
; CHECK-UF2-LABEL: 'vld4'
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %v2i8 = load <8 x i8>, ptr %p, align 8
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:80 Lat:160 SizeLat:160 for: %v2i8_0 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 0, i32 4>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:80 Lat:160 SizeLat:160 for: %v2i8_1 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 1, i32 5>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:80 Lat:160 SizeLat:160 for: %v2i8_2 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 2, i32 6>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:80 Lat:160 SizeLat:160 for: %v2i8_3 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 3, i32 7>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %v4i8 = load <16 x i8>, ptr %p, align 8
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v4i8_0 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v4i8_1 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v4i8_2 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v4i8_3 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v8i8 = load <32 x i8>, ptr %p, align 32
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v8i8_0 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v8i8_1 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v8i8_2 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v8i8_3 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v16i8 = load <64 x i8>, ptr %p, align 64
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v16i8_0 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v16i8_1 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v16i8_2 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v16i8_3 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %v2i16 = load <8 x i16>, ptr %p, align 8
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:80 Lat:160 SizeLat:160 for: %v2i16_0 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 0, i32 4>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:80 Lat:160 SizeLat:160 for: %v2i16_1 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 1, i32 5>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:80 Lat:160 SizeLat:160 for: %v2i16_2 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 2, i32 6>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:80 Lat:160 SizeLat:160 for: %v2i16_3 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 3, i32 7>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v4i16 = load <16 x i16>, ptr %p, align 32
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v4i16_0 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v4i16_1 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v4i16_2 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v4i16_3 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v8i16 = load <32 x i16>, ptr %p, align 64
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v8i16_0 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v8i16_1 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v8i16_2 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v8i16_3 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:4 SizeLat:1 for: %v16i16 = load <64 x i16>, ptr %p, align 128
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v16i16_0 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v16i16_1 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v16i16_2 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v16i16_3 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v2i32 = load <8 x i32>, ptr %p, align 32
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:80 Lat:160 SizeLat:160 for: %v2i32_0 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 0, i32 4>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:80 Lat:160 SizeLat:160 for: %v2i32_1 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 1, i32 5>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:80 Lat:160 SizeLat:160 for: %v2i32_2 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 2, i32 6>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:80 Lat:160 SizeLat:160 for: %v2i32_3 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 3, i32 7>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v4i32 = load <16 x i32>, ptr %p, align 64
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v4i32_0 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v4i32_1 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v4i32_2 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v4i32_3 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:4 SizeLat:1 for: %v8i32 = load <32 x i32>, ptr %p, align 128
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v8i32_0 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v8i32_1 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v8i32_2 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v8i32_3 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:4 SizeLat:1 for: %v16i32 = load <64 x i32>, ptr %p, align 256
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v16i32_0 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v16i32_1 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v16i32_2 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v16i32_3 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v2i64 = load <8 x i64>, ptr %p, align 64
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v2i64_0 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 0, i32 4>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v2i64_1 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 1, i32 5>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v2i64_2 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 2, i32 6>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v2i64_3 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 3, i32 7>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:4 SizeLat:1 for: %v4i64 = load <16 x i64>, ptr %p, align 128
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v4i64_0 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v4i64_1 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v4i64_2 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v4i64_3 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:4 SizeLat:1 for: %v8i64 = load <32 x i64>, ptr %p, align 256
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v8i64_0 = shufflevector <32 x i64> %v8i64, <32 x i64> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v8i64_1 = shufflevector <32 x i64> %v8i64, <32 x i64> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v8i64_2 = shufflevector <32 x i64> %v8i64, <32 x i64> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v8i64_3 = shufflevector <32 x i64> %v8i64, <32 x i64> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:64 CodeSize:1 Lat:4 SizeLat:1 for: %v16i64 = load <64 x i64>, ptr %p, align 512
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:2560 CodeSize:1280 Lat:2560 SizeLat:2560 for: %v16i64_0 = shufflevector <64 x i64> %v16i64, <64 x i64> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:2560 CodeSize:1280 Lat:2560 SizeLat:2560 for: %v16i64_1 = shufflevector <64 x i64> %v16i64, <64 x i64> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:2560 CodeSize:1280 Lat:2560 SizeLat:2560 for: %v16i64_2 = shufflevector <64 x i64> %v16i64, <64 x i64> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:2560 CodeSize:1280 Lat:2560 SizeLat:2560 for: %v16i64_3 = shufflevector <64 x i64> %v16i64, <64 x i64> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-UF4-LABEL: 'vld4'
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %v2i8 = load <8 x i8>, ptr %p, align 8
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v2i8_0 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 0, i32 4>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v2i8_1 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 1, i32 5>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v2i8_2 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 2, i32 6>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v2i8_3 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 3, i32 7>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %v4i8 = load <16 x i8>, ptr %p, align 8
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v4i8_0 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v4i8_1 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v4i8_2 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v4i8_3 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v8i8 = load <32 x i8>, ptr %p, align 32
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v8i8_0 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v8i8_1 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v8i8_2 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v8i8_3 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v16i8 = load <64 x i8>, ptr %p, align 64
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:258 CodeSize:129 Lat:258 SizeLat:258 for: %v16i8_0 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:258 CodeSize:129 Lat:258 SizeLat:258 for: %v16i8_1 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:258 CodeSize:129 Lat:258 SizeLat:258 for: %v16i8_2 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:258 CodeSize:129 Lat:258 SizeLat:258 for: %v16i8_3 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %v2i16 = load <8 x i16>, ptr %p, align 8
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v2i16_0 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 0, i32 4>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v2i16_1 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 1, i32 5>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v2i16_2 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 2, i32 6>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v2i16_3 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 3, i32 7>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v4i16 = load <16 x i16>, ptr %p, align 32
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v4i16_0 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v4i16_1 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v4i16_2 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v4i16_3 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v8i16 = load <32 x i16>, ptr %p, align 64
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v8i16_0 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v8i16_1 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v8i16_2 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:130 CodeSize:65 Lat:130 SizeLat:130 for: %v8i16_3 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:4 SizeLat:1 for: %v16i16 = load <64 x i16>, ptr %p, align 128
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:260 CodeSize:130 Lat:260 SizeLat:260 for: %v16i16_0 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:260 CodeSize:130 Lat:260 SizeLat:260 for: %v16i16_1 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:260 CodeSize:130 Lat:260 SizeLat:260 for: %v16i16_2 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:260 CodeSize:130 Lat:260 SizeLat:260 for: %v16i16_3 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %v2i32 = load <8 x i32>, ptr %p, align 32
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v2i32_0 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 0, i32 4>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v2i32_1 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 1, i32 5>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v2i32_2 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 2, i32 6>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:34 CodeSize:17 Lat:34 SizeLat:34 for: %v2i32_3 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 3, i32 7>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v4i32 = load <16 x i32>, ptr %p, align 64
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v4i32_0 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v4i32_1 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v4i32_2 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:66 CodeSize:33 Lat:66 SizeLat:66 for: %v4i32_3 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:4 SizeLat:1 for: %v8i32 = load <32 x i32>, ptr %p, align 128
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:132 CodeSize:66 Lat:132 SizeLat:132 for: %v8i32_0 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:132 CodeSize:66 Lat:132 SizeLat:132 for: %v8i32_1 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:132 CodeSize:66 Lat:132 SizeLat:132 for: %v8i32_2 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:132 CodeSize:66 Lat:132 SizeLat:132 for: %v8i32_3 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:4 SizeLat:1 for: %v16i32 = load <64 x i32>, ptr %p, align 256
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:264 CodeSize:132 Lat:264 SizeLat:264 for: %v16i32_0 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:264 CodeSize:132 Lat:264 SizeLat:264 for: %v16i32_1 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:264 CodeSize:132 Lat:264 SizeLat:264 for: %v16i32_2 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:264 CodeSize:132 Lat:264 SizeLat:264 for: %v16i32_3 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:4 SizeLat:1 for: %v2i64 = load <8 x i64>, ptr %p, align 64
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v2i64_0 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 0, i32 4>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v2i64_1 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 1, i32 5>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v2i64_2 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 2, i32 6>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:320 CodeSize:160 Lat:320 SizeLat:320 for: %v2i64_3 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 3, i32 7>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:4 SizeLat:1 for: %v4i64 = load <16 x i64>, ptr %p, align 128
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v4i64_0 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v4i64_1 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v4i64_2 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:640 CodeSize:320 Lat:640 SizeLat:640 for: %v4i64_3 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:4 SizeLat:1 for: %v8i64 = load <32 x i64>, ptr %p, align 256
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v8i64_0 = shufflevector <32 x i64> %v8i64, <32 x i64> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v8i64_1 = shufflevector <32 x i64> %v8i64, <32 x i64> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v8i64_2 = shufflevector <32 x i64> %v8i64, <32 x i64> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:1280 CodeSize:640 Lat:1280 SizeLat:1280 for: %v8i64_3 = shufflevector <32 x i64> %v8i64, <32 x i64> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:64 CodeSize:1 Lat:4 SizeLat:1 for: %v16i64 = load <64 x i64>, ptr %p, align 512
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2560 CodeSize:1280 Lat:2560 SizeLat:2560 for: %v16i64_0 = shufflevector <64 x i64> %v16i64, <64 x i64> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2560 CodeSize:1280 Lat:2560 SizeLat:2560 for: %v16i64_1 = shufflevector <64 x i64> %v16i64, <64 x i64> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2560 CodeSize:1280 Lat:2560 SizeLat:2560 for: %v16i64_2 = shufflevector <64 x i64> %v16i64, <64 x i64> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2560 CodeSize:1280 Lat:2560 SizeLat:2560 for: %v16i64_3 = shufflevector <64 x i64> %v16i64, <64 x i64> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %v2i8 = load <8 x i8>, ptr %p
  %v2i8_0 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 0, i32 4>
  %v2i8_1 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 1, i32 5>
  %v2i8_2 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 2, i32 6>
  %v2i8_3 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 3, i32 7>
  %v4i8 = load <16 x i8>, ptr %p
  %v4i8_0 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
  %v4i8_1 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
  %v4i8_2 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
  %v4i8_3 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
  %v8i8 = load <32 x i8>, ptr %p
  %v8i8_0 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
  %v8i8_1 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
  %v8i8_2 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
  %v8i8_3 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
  %v16i8 = load <64 x i8>, ptr %p
  %v16i8_0 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
  %v16i8_1 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
  %v16i8_2 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
  %v16i8_3 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>

  %v2i16 = load <8 x i16>, ptr %p
  %v2i16_0 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 0, i32 4>
  %v2i16_1 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 1, i32 5>
  %v2i16_2 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 2, i32 6>
  %v2i16_3 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 3, i32 7>
  %v4i16 = load <16 x i16>, ptr %p
  %v4i16_0 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
  %v4i16_1 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
  %v4i16_2 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
  %v4i16_3 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
  %v8i16 = load <32 x i16>, ptr %p
  %v8i16_0 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
  %v8i16_1 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
  %v8i16_2 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
  %v8i16_3 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
  %v16i16 = load <64 x i16>, ptr %p
  %v16i16_0 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
  %v16i16_1 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
  %v16i16_2 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
  %v16i16_3 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>

  %v2i32 = load <8 x i32>, ptr %p
  %v2i32_0 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 0, i32 4>
  %v2i32_1 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 1, i32 5>
  %v2i32_2 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 2, i32 6>
  %v2i32_3 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 3, i32 7>
  %v4i32 = load <16 x i32>, ptr %p
  %v4i32_0 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
  %v4i32_1 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
  %v4i32_2 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
  %v4i32_3 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
  %v8i32 = load <32 x i32>, ptr %p
  %v8i32_0 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
  %v8i32_1 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
  %v8i32_2 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
  %v8i32_3 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
  %v16i32 = load <64 x i32>, ptr %p
  %v16i32_0 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
  %v16i32_1 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
  %v16i32_2 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
  %v16i32_3 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>

  %v2i64 = load <8 x i64>, ptr %p
  %v2i64_0 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 0, i32 4>
  %v2i64_1 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 1, i32 5>
  %v2i64_2 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 2, i32 6>
  %v2i64_3 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 3, i32 7>
  %v4i64 = load <16 x i64>, ptr %p
  %v4i64_0 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
  %v4i64_1 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
  %v4i64_2 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
  %v4i64_3 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
  %v8i64 = load <32 x i64>, ptr %p
  %v8i64_0 = shufflevector <32 x i64> %v8i64, <32 x i64> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
  %v8i64_1 = shufflevector <32 x i64> %v8i64, <32 x i64> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
  %v8i64_2 = shufflevector <32 x i64> %v8i64, <32 x i64> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
  %v8i64_3 = shufflevector <32 x i64> %v8i64, <32 x i64> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
  %v16i64 = load <64 x i64>, ptr %p
  %v16i64_0 = shufflevector <64 x i64> %v16i64, <64 x i64> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
  %v16i64_1 = shufflevector <64 x i64> %v16i64, <64 x i64> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
  %v16i64_2 = shufflevector <64 x i64> %v16i64, <64 x i64> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
  %v16i64_3 = shufflevector <64 x i64> %v16i64, <64 x i64> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>

  ret void
}

define void @vst2(ptr %p) {
; CHECK-LABEL: 'vst2'
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %v4i8 = shufflevector <2 x i8> undef, <2 x i8> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <4 x i8> %v4i8, ptr %p, align 4
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <8 x i8> %v8i8, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <16 x i8> %v16i8, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <32 x i8> %v32i8, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %v4i16 = shufflevector <2 x i16> undef, <2 x i16> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <4 x i16> %v4i16, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <8 x i16> %v8i16, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <16 x i16> %v16i16, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:4 Lat:8 SizeLat:8 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <32 x i16> %v32i16, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 for: %v4i32 = shufflevector <2 x i32> undef, <2 x i32> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <4 x i32> %v4i32, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <8 x i32> %v8i32, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:4 Lat:8 SizeLat:8 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <16 x i32> %v16i32, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:8 Lat:16 SizeLat:16 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: store <32 x i32> %v32i32, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 for: %v4i64 = shufflevector <2 x i64> undef, <2 x i64> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <4 x i64> %v4i64, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <8 x i64> %v8i64, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: store <16 x i64> %v16i64, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:1 SizeLat:1 for: store <32 x i64> %v32i64, ptr %p, align 256
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %v4i8 = shufflevector <2 x i8> undef, <2 x i8> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
  store <4 x i8> %v4i8, ptr %p
  %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>
  store <8 x i8> %v8i8, ptr %p
  %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>
  store <16 x i8> %v16i8, ptr %p
  %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>
  store <32 x i8> %v32i8, ptr %p

  %v4i16 = shufflevector <2 x i16> undef, <2 x i16> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
  store <4 x i16> %v4i16, ptr %p
  %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>
  store <8 x i16> %v8i16, ptr %p
  %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>
  store <16 x i16> %v16i16, ptr %p
  %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>
  store <32 x i16> %v32i16, ptr %p

  %v4i32 = shufflevector <2 x i32> undef, <2 x i32> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
  store <4 x i32> %v4i32, ptr %p
  %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>
  store <8 x i32> %v8i32, ptr %p
  %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>
  store <16 x i32> %v16i32, ptr %p
  %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>
  store <32 x i32> %v32i32, ptr %p

  %v4i64 = shufflevector <2 x i64> undef, <2 x i64> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
  store <4 x i64> %v4i64, ptr %p
  %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>
  store <8 x i64> %v8i64, ptr %p
  %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>
  store <16 x i64> %v16i64, ptr %p
  %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>
  store <32 x i64> %v32i64, ptr %p

  ret void
}


define void @vst3(ptr %p) {
; CHECK-LABEL: 'vst3'
; CHECK-NEXT:  Cost Model: Found costs of RThru:96 CodeSize:48 Lat:96 SizeLat:96 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:50 CodeSize:1 Lat:1 SizeLat:1 for: store <6 x i8> %v8i8, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:192 CodeSize:96 Lat:192 SizeLat:192 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:98 CodeSize:1 Lat:1 SizeLat:1 for: store <12 x i8> %v16i8, ptr %p, align 16
; CHECK-NEXT:  Cost Model: Found costs of RThru:384 CodeSize:192 Lat:384 SizeLat:384 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <24 x i8> %v32i8, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:768 CodeSize:384 Lat:768 SizeLat:768 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <48 x i8> %v64i8, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:96 CodeSize:48 Lat:96 SizeLat:96 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:50 CodeSize:1 Lat:1 SizeLat:1 for: store <6 x i16> %v8i16, ptr %p, align 16
; CHECK-NEXT:  Cost Model: Found costs of RThru:192 CodeSize:96 Lat:192 SizeLat:192 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <12 x i16> %v16i16, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:384 CodeSize:192 Lat:384 SizeLat:384 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <24 x i16> %v32i16, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:768 CodeSize:384 Lat:768 SizeLat:768 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: store <48 x i16> %v64i16, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of RThru:96 CodeSize:48 Lat:96 SizeLat:96 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <6 x i32> %v8i32, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:192 CodeSize:96 Lat:192 SizeLat:192 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <12 x i32> %v16i32, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:384 CodeSize:192 Lat:384 SizeLat:384 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: store <24 x i32> %v32i32, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of RThru:768 CodeSize:384 Lat:768 SizeLat:768 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:1 SizeLat:1 for: store <48 x i32> %v64i32, ptr %p, align 256
; CHECK-NEXT:  Cost Model: Found costs of RThru:192 CodeSize:96 Lat:192 SizeLat:192 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <6 x i64> %v8i64, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of RThru:384 CodeSize:192 Lat:384 SizeLat:384 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: store <12 x i64> %v16i64, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of RThru:768 CodeSize:384 Lat:768 SizeLat:768 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:1 SizeLat:1 for: store <24 x i64> %v32i64, ptr %p, align 256
; CHECK-NEXT:  Cost Model: Found costs of RThru:1536 CodeSize:768 Lat:1536 SizeLat:1536 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>
; CHECK-NEXT:  Cost Model: Found costs of RThru:64 CodeSize:1 Lat:1 SizeLat:1 for: store <48 x i64> %v64i64, ptr %p, align 512
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %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>
  store <6 x i8> %v8i8, ptr %p
  %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>
  store <12 x i8> %v16i8, ptr %p
  %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>
  store <24 x i8> %v32i8, ptr %p
  %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>
  store <48 x i8> %v64i8, ptr %p

  %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>
  store <6 x i16> %v8i16, ptr %p
  %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>
  store <12 x i16> %v16i16, ptr %p
  %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>
  store <24 x i16> %v32i16, ptr %p
  %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>
  store <48 x i16> %v64i16, ptr %p

  %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>
  store <6 x i32> %v8i32, ptr %p
  %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>
  store <12 x i32> %v16i32, ptr %p
  %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>
  store <24 x i32> %v32i32, ptr %p
  %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>
  store <48 x i32> %v64i32, ptr %p

  %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>
  store <6 x i64> %v8i64, ptr %p
  %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>
  store <12 x i64> %v16i64, ptr %p
  %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>
  store <24 x i64> %v32i64, ptr %p
  %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>
  store <48 x i64> %v64i64, ptr %p

  ret void
}


define void @vst4(ptr %p) {
; CHECK-UF2-LABEL: 'vst4'
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <8 x i8> %v8i8, ptr %p, align 8
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <16 x i8> %v16i8, ptr %p, align 8
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <32 x i8> %v32i8, ptr %p, align 32
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <64 x i8> %v64i8, ptr %p, align 64
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <8 x i16> %v8i16, ptr %p, align 8
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <16 x i16> %v16i16, ptr %p, align 32
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <32 x i16> %v32i16, ptr %p, align 64
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: store <64 x i16> %v64i16, ptr %p, align 128
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:128 CodeSize:64 Lat:128 SizeLat:128 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <8 x i32> %v8i32, ptr %p, align 32
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <16 x i32> %v16i32, ptr %p, align 64
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: store <32 x i32> %v32i32, ptr %p, align 128
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:1 SizeLat:1 for: store <64 x i32> %v64i32, ptr %p, align 256
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <8 x i64> %v8i64, ptr %p, align 64
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: store <16 x i64> %v16i64, ptr %p, align 128
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:1 SizeLat:1 for: store <32 x i64> %v32i64, ptr %p, align 256
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:2048 CodeSize:1024 Lat:2048 SizeLat:2048 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>
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:64 CodeSize:1 Lat:1 SizeLat:1 for: store <64 x i64> %v64i64, ptr %p, align 512
; CHECK-UF2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-UF4-LABEL: 'vst4'
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <8 x i8> %v8i8, ptr %p, align 8
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <16 x i8> %v16i8, ptr %p, align 8
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <32 x i8> %v32i8, ptr %p, align 32
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:4 Lat:8 SizeLat:8 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <64 x i8> %v64i8, ptr %p, align 64
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:2 SizeLat:2 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: store <8 x i16> %v8i16, ptr %p, align 8
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <16 x i16> %v16i16, ptr %p, align 32
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:4 Lat:8 SizeLat:8 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <32 x i16> %v32i16, ptr %p, align 64
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:8 Lat:16 SizeLat:16 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: store <64 x i16> %v64i16, ptr %p, align 128
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:1 SizeLat:1 for: store <8 x i32> %v8i32, ptr %p, align 32
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:4 Lat:8 SizeLat:8 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <16 x i32> %v16i32, ptr %p, align 64
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:8 Lat:16 SizeLat:16 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: store <32 x i32> %v32i32, ptr %p, align 128
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:16 Lat:32 SizeLat:32 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:1 SizeLat:1 for: store <64 x i32> %v64i32, ptr %p, align 256
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:256 CodeSize:128 Lat:256 SizeLat:256 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:1 Lat:1 SizeLat:1 for: store <8 x i64> %v8i64, ptr %p, align 64
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:512 CodeSize:256 Lat:512 SizeLat:512 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:1 Lat:1 SizeLat:1 for: store <16 x i64> %v16i64, ptr %p, align 128
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:1024 CodeSize:512 Lat:1024 SizeLat:1024 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:1 Lat:1 SizeLat:1 for: store <32 x i64> %v32i64, ptr %p, align 256
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:2048 CodeSize:1024 Lat:2048 SizeLat:2048 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>
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:64 CodeSize:1 Lat:1 SizeLat:1 for: store <64 x i64> %v64i64, ptr %p, align 512
; CHECK-UF4-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %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>
  store <8 x i8> %v8i8, ptr %p
  %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>
  store <16 x i8> %v16i8, ptr %p
  %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>
  store <32 x i8> %v32i8, ptr %p
  %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>
  store <64 x i8> %v64i8, ptr %p

  %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>
  store <8 x i16> %v8i16, ptr %p
  %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>
  store <16 x i16> %v16i16, ptr %p
  %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>
  store <32 x i16> %v32i16, ptr %p
  %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>
  store <64 x i16> %v64i16, ptr %p

  %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>
  store <8 x i32> %v8i32, ptr %p
  %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>
  store <16 x i32> %v16i32, ptr %p
  %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>
  store <32 x i32> %v32i32, ptr %p
  %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>
  store <64 x i32> %v64i32, ptr %p

  %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>
  store <8 x i64> %v8i64, ptr %p
  %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>
  store <16 x i64> %v16i64, ptr %p
  %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>
  store <32 x i64> %v32i64, ptr %p
  %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>
  store <64 x i64> %v64i64, ptr %p

  ret void
}