; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -mtriple=aarch64-linux-gnu -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output | FileCheck %s

; These tests check the costs of ld1r instructions, through the
; isLegalBroadcastLoad method.

target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"

; The tests use vector loads and splats, as opposed to scalar loads, inserts
; and splats as that is how getShuffleCost currently recognizes them.
define void @shuffle() {
; CHECK-LABEL: 'shuffle'
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %lv2i8 = load <2 x i8>, ptr undef, align 2
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %sv2i8 = shufflevector <2 x i8> %lv2i8, <2 x i8> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:4 SizeLat:1 for: %lv4i8 = load <4 x i8>, ptr undef, align 4
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %sv4i8 = shufflevector <4 x i8> %lv4i8, <4 x i8> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv8i8 = load <8 x i8>, ptr undef, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv8i8 = shufflevector <8 x i8> %lv8i8, <8 x i8> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv16i8 = load <16 x i8>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv16i8 = shufflevector <16 x i8> %lv16i8, <16 x i8> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:1 Lat:4 SizeLat:1 for: %lv2i16 = load <2 x i16>, ptr undef, align 4
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %sv2i16 = shufflevector <2 x i16> %lv2i16, <2 x i16> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv4i16 = load <4 x i16>, ptr undef, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv4i16 = shufflevector <4 x i16> %lv4i16, <4 x i16> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv8i16 = load <8 x i16>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv8i16 = shufflevector <8 x i16> %lv8i16, <8 x i16> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:4 SizeLat:2 for: %lv16i16 = load <16 x i16>, ptr undef, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv16i16 = shufflevector <16 x i16> %lv16i16, <16 x i16> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv2i32 = load <2 x i32>, ptr undef, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv2i32 = shufflevector <2 x i32> %lv2i32, <2 x i32> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv4i32 = load <4 x i32>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv4i32 = shufflevector <4 x i32> %lv4i32, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:4 SizeLat:2 for: %lv8i32 = load <8 x i32>, ptr undef, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv8i32 = shufflevector <8 x i32> %lv8i32, <8 x i32> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv2i64 = load <2 x i64>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv2i64 = shufflevector <2 x i64> %lv2i64, <2 x i64> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:4 SizeLat:2 for: %lv4i64 = load <4 x i64>, ptr undef, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv4i64 = shufflevector <4 x i64> %lv4i64, <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv2f16 = load <2 x half>, ptr undef, align 4
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv2f16 = shufflevector <2 x half> %lv2f16, <2 x half> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv4f16 = load <4 x half>, ptr undef, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv4f16 = shufflevector <4 x half> %lv4f16, <4 x half> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv8f16 = load <8 x half>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv8f16 = shufflevector <8 x half> %lv8f16, <8 x half> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:4 SizeLat:2 for: %lv16f16 = load <16 x half>, ptr undef, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv16f16 = shufflevector <16 x half> %lv16f16, <16 x half> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv2f32 = load <2 x float>, ptr undef, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv2f32 = shufflevector <2 x float> %lv2f32, <2 x float> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv4f32 = load <4 x float>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv4f32 = shufflevector <4 x float> %lv4f32, <4 x float> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:4 SizeLat:2 for: %lv8f32 = load <8 x float>, ptr undef, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv8f32 = shufflevector <8 x float> %lv8f32, <8 x float> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %lv2f64 = load <2 x double>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv2f64 = shufflevector <2 x double> %lv2f64, <2 x double> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:4 SizeLat:2 for: %lv4f64 = load <4 x double>, ptr undef, align 32
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:0 Lat:1 SizeLat:1 for: %sv4f64 = shufflevector <4 x double> %lv4f64, <4 x double> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %lv2i8 = load <2 x i8>, ptr undef
  %sv2i8 = shufflevector <2 x i8> %lv2i8, <2 x i8> undef, <2 x i32> zeroinitializer
  %lv4i8 = load <4 x i8>, ptr undef
  %sv4i8 = shufflevector <4 x i8> %lv4i8, <4 x i8> undef, <4 x i32> zeroinitializer
  %lv8i8 = load <8 x i8>, ptr undef
  %sv8i8 = shufflevector <8 x i8> %lv8i8, <8 x i8> undef, <8 x i32> zeroinitializer
  %lv16i8 = load <16 x i8>, ptr undef
  %sv16i8 = shufflevector <16 x i8> %lv16i8, <16 x i8> undef, <16 x i32> zeroinitializer

  %lv2i16 = load <2 x i16>, ptr undef
  %sv2i16 = shufflevector <2 x i16> %lv2i16, <2 x i16> undef, <2 x i32> zeroinitializer
  %lv4i16 = load <4 x i16>, ptr undef
  %sv4i16 = shufflevector <4 x i16> %lv4i16, <4 x i16> undef, <4 x i32> zeroinitializer
  %lv8i16 = load <8 x i16>, ptr undef
  %sv8i16 = shufflevector <8 x i16> %lv8i16, <8 x i16> undef, <8 x i32> zeroinitializer
  %lv16i16 = load <16 x i16>, ptr undef
  %sv16i16 = shufflevector <16 x i16> %lv16i16, <16 x i16> undef, <16 x i32> zeroinitializer

  %lv2i32 = load <2 x i32>, ptr undef
  %sv2i32 = shufflevector <2 x i32> %lv2i32, <2 x i32> undef, <2 x i32> zeroinitializer
  %lv4i32 = load <4 x i32>, ptr undef
  %sv4i32 = shufflevector <4 x i32> %lv4i32, <4 x i32> undef, <4 x i32> zeroinitializer
  %lv8i32 = load <8 x i32>, ptr undef
  %sv8i32 = shufflevector <8 x i32> %lv8i32, <8 x i32> undef, <8 x i32> zeroinitializer

  %lv2i64 = load <2 x i64>, ptr undef
  %sv2i64 = shufflevector <2 x i64> %lv2i64, <2 x i64> undef, <2 x i32> zeroinitializer
  %lv4i64 = load <4 x i64>, ptr undef
  %sv4i64 = shufflevector <4 x i64> %lv4i64, <4 x i64> undef, <4 x i32> zeroinitializer

  %lv2f16 = load <2 x half>, ptr undef
  %sv2f16 = shufflevector <2 x half> %lv2f16, <2 x half> undef, <2 x i32> zeroinitializer
  %lv4f16 = load <4 x half>, ptr undef
  %sv4f16 = shufflevector <4 x half> %lv4f16, <4 x half> undef, <4 x i32> zeroinitializer
  %lv8f16 = load <8 x half>, ptr undef
  %sv8f16 = shufflevector <8 x half> %lv8f16, <8 x half> undef, <8 x i32> zeroinitializer
  %lv16f16 = load <16 x half>, ptr undef
  %sv16f16 = shufflevector <16 x half> %lv16f16, <16 x half> undef, <16 x i32> zeroinitializer

  %lv2f32 = load <2 x float>, ptr undef
  %sv2f32 = shufflevector <2 x float> %lv2f32, <2 x float> undef, <2 x i32> zeroinitializer
  %lv4f32 = load <4 x float>, ptr undef
  %sv4f32 = shufflevector <4 x float> %lv4f32, <4 x float> undef, <4 x i32> zeroinitializer
  %lv8f32 = load <8 x float>, ptr undef
  %sv8f32 = shufflevector <8 x float> %lv8f32, <8 x float> undef, <8 x i32> zeroinitializer

  %lv2f64 = load <2 x double>, ptr undef
  %sv2f64 = shufflevector <2 x double> %lv2f64, <2 x double> undef, <2 x i32> zeroinitializer
  %lv4f64 = load <4 x double>, ptr undef
  %sv4f64 = shufflevector <4 x double> %lv4f64, <4 x double> undef, <4 x i32> zeroinitializer

  ret void
}

; Check ld1r generated from scalar FP loads

define <4 x half> @ld1r_4h_float_shuff(ptr nocapture %x) {
; CHECK-LABEL: 'ld1r_4h_float_shuff'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %tmp = load half, ptr %x, align 2
; CHECK-NEXT:  Cost Model: Found costs of 0 for: %tmp1 = insertelement <4 x half> undef, half %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %lane = shufflevector <4 x half> %tmp1, <4 x half> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x half> %lane
;
entry:
  %tmp = load half, ptr %x, align 2
  %tmp1 = insertelement <4 x half> undef, half %tmp, i32 0
  %lane = shufflevector <4 x half> %tmp1, <4 x half> undef, <4 x i32> zeroinitializer
  ret <4 x half> %lane
}

define <8 x half> @ld1r_8h_float_shuff(ptr nocapture %x) {
; CHECK-LABEL: 'ld1r_8h_float_shuff'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %tmp = load half, ptr %x, align 2
; CHECK-NEXT:  Cost Model: Found costs of 0 for: %tmp1 = insertelement <8 x half> undef, half %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %lane = shufflevector <8 x half> %tmp1, <8 x half> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x half> %lane
;
entry:
  %tmp = load half, ptr %x, align 2
  %tmp1 = insertelement <8 x half> undef, half %tmp, i32 0
  %lane = shufflevector <8 x half> %tmp1, <8 x half> undef, <8 x i32> zeroinitializer
  ret <8 x half> %lane
}

define <2 x float> @ld1r_2s_float_shuff(ptr nocapture %x) {
; CHECK-LABEL: 'ld1r_2s_float_shuff'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %tmp = load float, ptr %x, align 4
; CHECK-NEXT:  Cost Model: Found costs of 0 for: %tmp1 = insertelement <2 x float> undef, float %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %lane = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <2 x float> %lane
;
entry:
  %tmp = load float, ptr %x, align 4
  %tmp1 = insertelement <2 x float> undef, float %tmp, i32 0
  %lane = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> zeroinitializer
  ret <2 x float> %lane
}

define <4 x float> @ld1r_4s_float_shuff(ptr nocapture %x) {
; CHECK-LABEL: 'ld1r_4s_float_shuff'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %tmp = load float, ptr %x, align 4
; CHECK-NEXT:  Cost Model: Found costs of 0 for: %tmp1 = insertelement <4 x float> undef, float %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %lane = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x float> %lane
;
entry:
  %tmp = load float, ptr %x, align 4
  %tmp1 = insertelement <4 x float> undef, float %tmp, i32 0
  %lane = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> zeroinitializer
  ret <4 x float> %lane
}

define <2 x double> @ld1r_2d_double_shuff(ptr nocapture %x) {
; CHECK-LABEL: 'ld1r_2d_double_shuff'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %tmp = load double, ptr %x, align 4
; CHECK-NEXT:  Cost Model: Found costs of 0 for: %tmp1 = insertelement <2 x double> undef, double %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %lane = shufflevector <2 x double> %tmp1, <2 x double> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <2 x double> %lane
;
entry:
  %tmp = load double, ptr %x, align 4
  %tmp1 = insertelement <2 x double> undef, double %tmp, i32 0
  %lane = shufflevector <2 x double> %tmp1, <2 x double> undef, <2 x i32> zeroinitializer
  ret <2 x double> %lane
}

; Check ld1r generated from scalar integer loads

define <8 x i8> @ld1r_8b_int_shuff(ptr nocapture %x) {
; CHECK-LABEL: 'ld1r_8b_int_shuff'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %tmp = load i8, ptr %x, align 2
; CHECK-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:0 Lat:3 SizeLat:3 for: %tmp1 = insertelement <8 x i8> undef, i8 %tmp, i8 0
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %lane = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x i8> %lane
;
entry:
  %tmp = load i8, ptr %x, align 2
  %tmp1 = insertelement <8 x i8> undef, i8 %tmp, i8 0
  %lane = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> zeroinitializer
  ret <8 x i8> %lane
}

define <16 x i8> @ld1r_16b_int_shuff(ptr nocapture %x) {
; CHECK-LABEL: 'ld1r_16b_int_shuff'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %tmp = load i8, ptr %x, align 2
; CHECK-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:0 Lat:3 SizeLat:3 for: %tmp1 = insertelement <16 x i8> undef, i8 %tmp, i8 0
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %lane = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <16 x i8> %lane
;
entry:
  %tmp = load i8, ptr %x, align 2
  %tmp1 = insertelement <16 x i8> undef, i8 %tmp, i8 0
  %lane = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> zeroinitializer
  ret <16 x i8> %lane
}

define <4 x i16> @ld1r_4h_int_shuff(ptr nocapture %x) {
; CHECK-LABEL: 'ld1r_4h_int_shuff'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %tmp = load i16, ptr %x, align 2
; CHECK-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:0 Lat:3 SizeLat:3 for: %tmp1 = insertelement <4 x i16> undef, i16 %tmp, i16 0
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %lane = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x i16> %lane
;
entry:
  %tmp = load i16, ptr %x, align 2
  %tmp1 = insertelement <4 x i16> undef, i16 %tmp, i16 0
  %lane = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> zeroinitializer
  ret <4 x i16> %lane
}

define <8 x i16> @ld1r_8h_int_shuff(ptr nocapture %x) {
; CHECK-LABEL: 'ld1r_8h_int_shuff'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %tmp = load i16, ptr %x, align 2
; CHECK-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:0 Lat:3 SizeLat:3 for: %tmp1 = insertelement <8 x i16> undef, i16 %tmp, i16 0
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %lane = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <8 x i16> %lane
;
entry:
  %tmp = load i16, ptr %x, align 2
  %tmp1 = insertelement <8 x i16> undef, i16 %tmp, i16 0
  %lane = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> zeroinitializer
  ret <8 x i16> %lane
}

define <2 x i32> @ld1r_2s_int_shuff(ptr nocapture %x) {
; CHECK-LABEL: 'ld1r_2s_int_shuff'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %tmp = load i32, ptr %x, align 4
; CHECK-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:0 Lat:3 SizeLat:3 for: %tmp1 = insertelement <2 x i32> undef, i32 %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %lane = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <2 x i32> %lane
;
entry:
  %tmp = load i32, ptr %x, align 4
  %tmp1 = insertelement <2 x i32> undef, i32 %tmp, i32 0
  %lane = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> zeroinitializer
  ret <2 x i32> %lane
}

define <4 x i32> @ld1r_4s_int_shuff(ptr nocapture %x) {
; CHECK-LABEL: 'ld1r_4s_int_shuff'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %tmp = load i32, ptr %x, align 4
; CHECK-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:0 Lat:3 SizeLat:3 for: %tmp1 = insertelement <4 x i32> undef, i32 %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %lane = shufflevector <4 x i32> %tmp1, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x i32> %lane
;
entry:
  %tmp = load i32, ptr %x, align 4
  %tmp1 = insertelement <4 x i32> undef, i32 %tmp, i32 0
  %lane = shufflevector <4 x i32> %tmp1, <4 x i32> undef, <4 x i32> zeroinitializer
  ret <4 x i32> %lane
}

define <2 x i64> @ld1r_2d_int_shuff(ptr nocapture %x) {
; CHECK-LABEL: 'ld1r_2d_int_shuff'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %tmp = load i64, ptr %x, align 8
; CHECK-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:0 Lat:3 SizeLat:3 for: %tmp1 = insertelement <2 x i64> undef, i64 %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %lane = shufflevector <2 x i64> %tmp1, <2 x i64> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <2 x i64> %lane
;
entry:
  %tmp = load i64, ptr %x, align 8
  %tmp1 = insertelement <2 x i64> undef, i64 %tmp, i32 0
  %lane = shufflevector <2 x i64> %tmp1, <2 x i64> undef, <2 x i32> zeroinitializer
  ret <2 x i64> %lane
}

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 1 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 1 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:1 CodeSize:1 Lat:4 SizeLat:1 for: %v8i8 = load <8 x i8>, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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:1 CodeSize:1 Lat:4 SizeLat:1 for: %v16i8 = load <16 x i8>, ptr %p, align 16
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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:2 CodeSize:2 Lat:4 SizeLat:2 for: %v32i8 = load <32 x i8>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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:1 CodeSize:1 Lat:4 SizeLat:1 for: %v4i16 = load <4 x i16>, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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:1 CodeSize:1 Lat:4 SizeLat:1 for: %v8i16 = load <8 x i16>, ptr %p, align 16
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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:2 CodeSize:2 Lat:4 SizeLat:2 for: %v16i16 = load <16 x i16>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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 4 for: %v32i16 = load <32 x i16>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of 2 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 2 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:1 CodeSize:1 Lat:4 SizeLat:1 for: %v4i32 = load <4 x i32>, ptr %p, align 16
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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:2 CodeSize:2 Lat:4 SizeLat:2 for: %v8i32 = load <8 x i32>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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 4 for: %v16i32 = load <16 x i32>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of 2 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 2 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:8 CodeSize:8 Lat:4 SizeLat:8 for: %v32i32 = load <32 x i32>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of 4 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 4 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:2 CodeSize:2 Lat:4 SizeLat:2 for: %v2i64 = load <4 x i64>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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 4 for: %v4i64 = load <8 x i64>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of 2 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 2 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:8 CodeSize:8 Lat:4 SizeLat:8 for: %v8i64 = load <16 x i64>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of 4 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 4 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:16 CodeSize:16 Lat:4 SizeLat:16 for: %v16i64 = load <32 x i64>, ptr %p, align 256
; CHECK-NEXT:  Cost Model: Found costs of 8 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 8 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:1 CodeSize:1 Lat:4 SizeLat:1 for: %v2i8 = load <6 x i8>, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of 8 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 8 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 8 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:1 CodeSize:1 Lat:4 SizeLat:1 for: %v4i8 = load <12 x i8>, ptr %p, align 16
; CHECK-NEXT:  Cost Model: Found costs of 8 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 8 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 8 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:2 CodeSize:2 Lat:4 SizeLat:2 for: %v8i8 = load <24 x i8>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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 1 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 4 for: %v16i8 = load <48 x i8>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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 1 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:1 CodeSize:1 Lat:4 SizeLat:1 for: %v2i16 = load <6 x i16>, ptr %p, align 16
; CHECK-NEXT:  Cost Model: Found costs of 8 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 8 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 8 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:2 CodeSize:2 Lat:4 SizeLat:2 for: %v4i16 = load <12 x i16>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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 1 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 4 for: %v8i16 = load <24 x i16>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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 1 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:8 CodeSize:8 Lat:4 SizeLat:8 for: %v16i16 = load <48 x i16>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of 2 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 2 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 2 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:2 CodeSize:2 Lat:4 SizeLat:2 for: %v2i32 = load <6 x i32>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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 1 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 4 for: %v4i32 = load <12 x i32>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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 1 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:8 CodeSize:8 Lat:4 SizeLat:8 for: %v8i32 = load <24 x i32>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of 2 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 2 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 2 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:16 CodeSize:16 Lat:4 SizeLat:16 for: %v16i32 = load <48 x i32>, ptr %p, align 256
; CHECK-NEXT:  Cost Model: Found costs of 4 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 4 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 4 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 4 for: %v2i64 = load <6 x i64>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of 1 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 1 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 1 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:8 CodeSize:8 Lat:4 SizeLat:8 for: %v4i64 = load <12 x i64>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of 2 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 2 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 2 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:16 CodeSize:16 Lat:4 SizeLat:16 for: %v8i64 = load <24 x i64>, ptr %p, align 256
; CHECK-NEXT:  Cost Model: Found costs of 4 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 4 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 4 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:32 CodeSize:32 Lat:4 SizeLat:32 for: %v16i64 = load <48 x i64>, ptr %p, align 512
; CHECK-NEXT:  Cost Model: Found costs of 8 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 8 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 8 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-LABEL: 'vld4'
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %v2i8 = load <8 x i8>, ptr %p, align 8
; CHECK-NEXT:  Cost Model: Found costs of 8 for: %v2i8_0 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 0, i32 4>
; CHECK-NEXT:  Cost Model: Found costs of 8 for: %v2i8_1 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 1, i32 5>
; CHECK-NEXT:  Cost Model: Found costs of 8 for: %v2i8_2 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 2, i32 6>
; CHECK-NEXT:  Cost Model: Found costs of 8 for: %v2i8_3 = shufflevector <8 x i8> %v2i8, <8 x i8> undef, <2 x i32> <i32 3, i32 7>
; CHECK-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %v4i8 = load <16 x i8>, ptr %p, align 16
; CHECK-NEXT:  Cost Model: Found costs of 8 for: %v4i8_0 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
; CHECK-NEXT:  Cost Model: Found costs of 8 for: %v4i8_1 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
; CHECK-NEXT:  Cost Model: Found costs of 8 for: %v4i8_2 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
; CHECK-NEXT:  Cost Model: Found costs of 8 for: %v4i8_3 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:4 SizeLat:2 for: %v8i8 = load <32 x i8>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of 1 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-NEXT:  Cost Model: Found costs of 1 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-NEXT:  Cost Model: Found costs of 1 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-NEXT:  Cost Model: Found costs of 1 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-NEXT:  Cost Model: Found costs of 4 for: %v16i8 = load <64 x i8>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of 1 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-NEXT:  Cost Model: Found costs of 1 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-NEXT:  Cost Model: Found costs of 1 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-NEXT:  Cost Model: Found costs of 1 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-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:4 SizeLat:1 for: %v2i16 = load <8 x i16>, ptr %p, align 16
; CHECK-NEXT:  Cost Model: Found costs of 8 for: %v2i16_0 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 0, i32 4>
; CHECK-NEXT:  Cost Model: Found costs of 8 for: %v2i16_1 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 1, i32 5>
; CHECK-NEXT:  Cost Model: Found costs of 8 for: %v2i16_2 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 2, i32 6>
; CHECK-NEXT:  Cost Model: Found costs of 8 for: %v2i16_3 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 3, i32 7>
; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:4 SizeLat:2 for: %v4i16 = load <16 x i16>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v4i16_0 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v4i16_1 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v4i16_2 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v4i16_3 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
; CHECK-NEXT:  Cost Model: Found costs of 4 for: %v8i16 = load <32 x i16>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of 1 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-NEXT:  Cost Model: Found costs of 1 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-NEXT:  Cost Model: Found costs of 1 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-NEXT:  Cost Model: Found costs of 1 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-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:8 Lat:4 SizeLat:8 for: %v16i16 = load <64 x i16>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of 2 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-NEXT:  Cost Model: Found costs of 2 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-NEXT:  Cost Model: Found costs of 2 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-NEXT:  Cost Model: Found costs of 2 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-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:4 SizeLat:2 for: %v2i32 = load <8 x i32>, ptr %p, align 32
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v2i32_0 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 0, i32 4>
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v2i32_1 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 1, i32 5>
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v2i32_2 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 2, i32 6>
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v2i32_3 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 3, i32 7>
; CHECK-NEXT:  Cost Model: Found costs of 4 for: %v4i32 = load <16 x i32>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v4i32_0 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v4i32_1 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v4i32_2 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v4i32_3 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:8 Lat:4 SizeLat:8 for: %v8i32 = load <32 x i32>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of 2 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-NEXT:  Cost Model: Found costs of 2 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-NEXT:  Cost Model: Found costs of 2 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-NEXT:  Cost Model: Found costs of 2 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-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:16 Lat:4 SizeLat:16 for: %v16i32 = load <64 x i32>, ptr %p, align 256
; CHECK-NEXT:  Cost Model: Found costs of 4 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-NEXT:  Cost Model: Found costs of 4 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-NEXT:  Cost Model: Found costs of 4 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-NEXT:  Cost Model: Found costs of 4 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-NEXT:  Cost Model: Found costs of 4 for: %v2i64 = load <8 x i64>, ptr %p, align 64
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v2i64_0 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 0, i32 4>
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v2i64_1 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 1, i32 5>
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v2i64_2 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 2, i32 6>
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %v2i64_3 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 3, i32 7>
; CHECK-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:8 Lat:4 SizeLat:8 for: %v4i64 = load <16 x i64>, ptr %p, align 128
; CHECK-NEXT:  Cost Model: Found costs of 2 for: %v4i64_0 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
; CHECK-NEXT:  Cost Model: Found costs of 2 for: %v4i64_1 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
; CHECK-NEXT:  Cost Model: Found costs of 2 for: %v4i64_2 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
; CHECK-NEXT:  Cost Model: Found costs of 2 for: %v4i64_3 = shufflevector <16 x i64> %v4i64, <16 x i64> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
; CHECK-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:16 Lat:4 SizeLat:16 for: %v8i64 = load <32 x i64>, ptr %p, align 256
; CHECK-NEXT:  Cost Model: Found costs of 4 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-NEXT:  Cost Model: Found costs of 4 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-NEXT:  Cost Model: Found costs of 4 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-NEXT:  Cost Model: Found costs of 4 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-NEXT:  Cost Model: Found costs of RThru:32 CodeSize:32 Lat:4 SizeLat:32 for: %v16i64 = load <64 x i64>, ptr %p, align 512
; CHECK-NEXT:  Cost Model: Found costs of 8 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-NEXT:  Cost Model: Found costs of 8 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-NEXT:  Cost Model: Found costs of 8 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-NEXT:  Cost Model: Found costs of 8 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-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
}