llvm/test/Analysis/CostModel/AArch64/shuffle-load.ll

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

; 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 an estimated cost of 4 for instruction: %lv2i8 = load <2 x i8>, ptr undef, align 2
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv2i8 = shufflevector <2 x i8> %lv2i8, <2 x i8> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv4i8 = load <4 x i8>, ptr undef, align 4
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv4i8 = shufflevector <4 x i8> %lv4i8, <4 x i8> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv8i8 = load <8 x i8>, ptr undef, align 8
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv8i8 = shufflevector <8 x i8> %lv8i8, <8 x i8> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv16i8 = load <16 x i8>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv16i8 = shufflevector <16 x i8> %lv16i8, <16 x i8> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %lv2i16 = load <2 x i16>, ptr undef, align 4
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv2i16 = shufflevector <2 x i16> %lv2i16, <2 x i16> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv4i16 = load <4 x i16>, ptr undef, align 8
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv4i16 = shufflevector <4 x i16> %lv4i16, <4 x i16> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv8i16 = load <8 x i16>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv8i16 = shufflevector <8 x i16> %lv8i16, <8 x i16> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv16i16 = load <16 x i16>, ptr undef, align 32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sv16i16 = shufflevector <16 x i16> %lv16i16, <16 x i16> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv2i32 = load <2 x i32>, ptr undef, align 8
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv2i32 = shufflevector <2 x i32> %lv2i32, <2 x i32> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv4i32 = load <4 x i32>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv4i32 = shufflevector <4 x i32> %lv4i32, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv8i32 = load <8 x i32>, ptr undef, align 32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sv8i32 = shufflevector <8 x i32> %lv8i32, <8 x i32> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv2i64 = load <2 x i64>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv2i64 = shufflevector <2 x i64> %lv2i64, <2 x i64> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv4i64 = load <4 x i64>, ptr undef, align 32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sv4i64 = shufflevector <4 x i64> %lv4i64, <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv2f16 = load <2 x half>, ptr undef, align 4
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv2f16 = shufflevector <2 x half> %lv2f16, <2 x half> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv4f16 = load <4 x half>, ptr undef, align 8
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv4f16 = shufflevector <4 x half> %lv4f16, <4 x half> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv8f16 = load <8 x half>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv8f16 = shufflevector <8 x half> %lv8f16, <8 x half> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv16f16 = load <16 x half>, ptr undef, align 32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sv16f16 = shufflevector <16 x half> %lv16f16, <16 x half> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv2f32 = load <2 x float>, ptr undef, align 8
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv2f32 = shufflevector <2 x float> %lv2f32, <2 x float> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv4f32 = load <4 x float>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv4f32 = shufflevector <4 x float> %lv4f32, <4 x float> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv8f32 = load <8 x float>, ptr undef, align 32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sv8f32 = shufflevector <8 x float> %lv8f32, <8 x float> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv2f64 = load <2 x double>, ptr undef, align 16
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv2f64 = shufflevector <2 x double> %lv2f64, <2 x double> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv4f64 = load <4 x double>, ptr undef, align 32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sv4f64 = shufflevector <4 x double> %lv4f64, <4 x double> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CODESIZE-LABEL: 'shuffle'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv2i8 = load <2 x i8>, ptr undef, align 2
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv2i8 = shufflevector <2 x i8> %lv2i8, <2 x i8> undef, <2 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv4i8 = load <4 x i8>, ptr undef, align 4
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv4i8 = shufflevector <4 x i8> %lv4i8, <4 x i8> undef, <4 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv8i8 = load <8 x i8>, ptr undef, align 8
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv8i8 = shufflevector <8 x i8> %lv8i8, <8 x i8> undef, <8 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv16i8 = load <16 x i8>, ptr undef, align 16
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv16i8 = shufflevector <16 x i8> %lv16i8, <16 x i8> undef, <16 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv2i16 = load <2 x i16>, ptr undef, align 4
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sv2i16 = shufflevector <2 x i16> %lv2i16, <2 x i16> undef, <2 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv4i16 = load <4 x i16>, ptr undef, align 8
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv4i16 = shufflevector <4 x i16> %lv4i16, <4 x i16> undef, <4 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv8i16 = load <8 x i16>, ptr undef, align 16
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv8i16 = shufflevector <8 x i16> %lv8i16, <8 x i16> undef, <8 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv16i16 = load <16 x i16>, ptr undef, align 32
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv16i16 = shufflevector <16 x i16> %lv16i16, <16 x i16> undef, <16 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv2i32 = load <2 x i32>, ptr undef, align 8
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv2i32 = shufflevector <2 x i32> %lv2i32, <2 x i32> undef, <2 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv4i32 = load <4 x i32>, ptr undef, align 16
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv4i32 = shufflevector <4 x i32> %lv4i32, <4 x i32> undef, <4 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv8i32 = load <8 x i32>, ptr undef, align 32
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv8i32 = shufflevector <8 x i32> %lv8i32, <8 x i32> undef, <8 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv2i64 = load <2 x i64>, ptr undef, align 16
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv2i64 = shufflevector <2 x i64> %lv2i64, <2 x i64> undef, <2 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv4i64 = load <4 x i64>, ptr undef, align 32
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv4i64 = shufflevector <4 x i64> %lv4i64, <4 x i64> undef, <4 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv2f16 = load <2 x half>, ptr undef, align 4
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv2f16 = shufflevector <2 x half> %lv2f16, <2 x half> undef, <2 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv4f16 = load <4 x half>, ptr undef, align 8
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv4f16 = shufflevector <4 x half> %lv4f16, <4 x half> undef, <4 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv8f16 = load <8 x half>, ptr undef, align 16
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv8f16 = shufflevector <8 x half> %lv8f16, <8 x half> undef, <8 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv16f16 = load <16 x half>, ptr undef, align 32
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv16f16 = shufflevector <16 x half> %lv16f16, <16 x half> undef, <16 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv2f32 = load <2 x float>, ptr undef, align 8
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv2f32 = shufflevector <2 x float> %lv2f32, <2 x float> undef, <2 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv4f32 = load <4 x float>, ptr undef, align 16
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv4f32 = shufflevector <4 x float> %lv4f32, <4 x float> undef, <4 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv8f32 = load <8 x float>, ptr undef, align 32
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv8f32 = shufflevector <8 x float> %lv8f32, <8 x float> undef, <8 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lv2f64 = load <2 x double>, ptr undef, align 16
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv2f64 = shufflevector <2 x double> %lv2f64, <2 x double> undef, <2 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %lv4f64 = load <4 x double>, ptr undef, align 32
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %sv4f64 = shufflevector <4 x double> %lv4f64, <4 x double> undef, <4 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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 an estimated cost of 1 for instruction: %tmp = load half, ptr %x, align 2
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tmp1 = insertelement <4 x half> undef, half %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <4 x half> %tmp1, <4 x half> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x half> %lane
;
; CODESIZE-LABEL: 'ld1r_4h_float_shuff'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp = load half, ptr %x, align 2
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tmp1 = insertelement <4 x half> undef, half %tmp, i32 0
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <4 x half> %tmp1, <4 x half> undef, <4 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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 an estimated cost of 1 for instruction: %tmp = load half, ptr %x, align 2
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tmp1 = insertelement <8 x half> undef, half %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <8 x half> %tmp1, <8 x half> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x half> %lane
;
; CODESIZE-LABEL: 'ld1r_8h_float_shuff'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp = load half, ptr %x, align 2
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tmp1 = insertelement <8 x half> undef, half %tmp, i32 0
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <8 x half> %tmp1, <8 x half> undef, <8 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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 an estimated cost of 1 for instruction: %tmp = load float, ptr %x, align 4
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tmp1 = insertelement <2 x float> undef, float %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %lane
;
; CODESIZE-LABEL: 'ld1r_2s_float_shuff'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp = load float, ptr %x, align 4
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tmp1 = insertelement <2 x float> undef, float %tmp, i32 0
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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 an estimated cost of 1 for instruction: %tmp = load float, ptr %x, align 4
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tmp1 = insertelement <4 x float> undef, float %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %lane
;
; CODESIZE-LABEL: 'ld1r_4s_float_shuff'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp = load float, ptr %x, align 4
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tmp1 = insertelement <4 x float> undef, float %tmp, i32 0
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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 an estimated cost of 1 for instruction: %tmp = load double, ptr %x, align 4
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tmp1 = insertelement <2 x double> undef, double %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <2 x double> %tmp1, <2 x double> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %lane
;
; CODESIZE-LABEL: 'ld1r_2d_double_shuff'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp = load double, ptr %x, align 4
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tmp1 = insertelement <2 x double> undef, double %tmp, i32 0
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <2 x double> %tmp1, <2 x double> undef, <2 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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 an estimated cost of 1 for instruction: %tmp = load i8, ptr %x, align 2
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <8 x i8> undef, i8 %tmp, i8 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i8> %lane
;
; CODESIZE-LABEL: 'ld1r_8b_int_shuff'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp = load i8, ptr %x, align 2
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <8 x i8> undef, i8 %tmp, i8 0
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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 an estimated cost of 1 for instruction: %tmp = load i8, ptr %x, align 2
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <16 x i8> undef, i8 %tmp, i8 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %lane
;
; CODESIZE-LABEL: 'ld1r_16b_int_shuff'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp = load i8, ptr %x, align 2
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <16 x i8> undef, i8 %tmp, i8 0
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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 an estimated cost of 1 for instruction: %tmp = load i16, ptr %x, align 2
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <4 x i16> undef, i16 %tmp, i16 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i16> %lane
;
; CODESIZE-LABEL: 'ld1r_4h_int_shuff'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp = load i16, ptr %x, align 2
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <4 x i16> undef, i16 %tmp, i16 0
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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 an estimated cost of 1 for instruction: %tmp = load i16, ptr %x, align 2
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <8 x i16> undef, i16 %tmp, i16 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %lane
;
; CODESIZE-LABEL: 'ld1r_8h_int_shuff'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp = load i16, ptr %x, align 2
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <8 x i16> undef, i16 %tmp, i16 0
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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 an estimated cost of 1 for instruction: %tmp = load i32, ptr %x, align 4
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <2 x i32> undef, i32 %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %lane
;
; CODESIZE-LABEL: 'ld1r_2s_int_shuff'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp = load i32, ptr %x, align 4
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <2 x i32> undef, i32 %tmp, i32 0
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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 an estimated cost of 1 for instruction: %tmp = load i32, ptr %x, align 4
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <4 x i32> undef, i32 %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <4 x i32> %tmp1, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %lane
;
; CODESIZE-LABEL: 'ld1r_4s_int_shuff'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp = load i32, ptr %x, align 4
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <4 x i32> undef, i32 %tmp, i32 0
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <4 x i32> %tmp1, <4 x i32> undef, <4 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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 an estimated cost of 1 for instruction: %tmp = load i64, ptr %x, align 8
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <2 x i64> undef, i64 %tmp, i32 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <2 x i64> %tmp1, <2 x i64> undef, <2 x i32> zeroinitializer
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %lane
;
; CODESIZE-LABEL: 'ld1r_2d_int_shuff'
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp = load i64, ptr %x, align 8
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %tmp1 = insertelement <2 x i64> undef, i64 %tmp, i32 0
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %lane = shufflevector <2 x i64> %tmp1, <2 x i64> undef, <2 x i32> zeroinitializer
; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: 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
}