; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -slp-vectorizer -S -o - -mtriple=x86_64-unknown-linux -mcpu=bdver2 -instcombine | FileCheck %s

define <2 x i8> @g(<2 x i8> %x, <2 x i8> %y) {
; CHECK-LABEL: @g(
; CHECK-NEXT:    [[X0:%.*]] = extractelement <2 x i8> [[X:%.*]], i32 0
; CHECK-NEXT:    [[Y1:%.*]] = extractelement <2 x i8> [[Y:%.*]], i32 1
; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
; CHECK-NEXT:    [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
; CHECK-NEXT:    [[INS1:%.*]] = insertelement <2 x i8> undef, i8 [[X0X0]], i32 0
; CHECK-NEXT:    [[INS2:%.*]] = insertelement <2 x i8> [[INS1]], i8 [[Y1Y1]], i32 1
; CHECK-NEXT:    ret <2 x i8> [[INS2]]
;
  %x0 = extractelement <2 x i8> %x, i32 0
  %y1 = extractelement <2 x i8> %y, i32 1
  %x0x0 = mul i8 %x0, %x0
  %y1y1 = mul i8 %y1, %y1
  %ins1 = insertelement <2 x i8> undef, i8 %x0x0, i32 0
  %ins2 = insertelement <2 x i8> %ins1, i8 %y1y1, i32 1
  ret <2 x i8> %ins2
}

define <4 x i8> @h(<4 x i8> %x, <4 x i8> %y) {
; CHECK-LABEL: @h(
; CHECK-NEXT:    [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
; CHECK-NEXT:    [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
; CHECK-NEXT:    [[Y1:%.*]] = extractelement <4 x i8> [[Y:%.*]], i32 1
; CHECK-NEXT:    [[Y2:%.*]] = extractelement <4 x i8> [[Y]], i32 2
; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
; CHECK-NEXT:    [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
; CHECK-NEXT:    [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
; CHECK-NEXT:    [[Y2Y2:%.*]] = mul i8 [[Y2]], [[Y2]]
; CHECK-NEXT:    [[INS1:%.*]] = insertelement <4 x i8> undef, i8 [[X0X0]], i32 0
; CHECK-NEXT:    [[INS2:%.*]] = insertelement <4 x i8> [[INS1]], i8 [[X3X3]], i32 1
; CHECK-NEXT:    [[INS3:%.*]] = insertelement <4 x i8> [[INS2]], i8 [[Y1Y1]], i32 2
; CHECK-NEXT:    [[INS4:%.*]] = insertelement <4 x i8> [[INS3]], i8 [[Y2Y2]], i32 3
; CHECK-NEXT:    ret <4 x i8> [[INS4]]
;
  %x0 = extractelement <4 x i8> %x, i32 0
  %x3 = extractelement <4 x i8> %x, i32 3
  %y1 = extractelement <4 x i8> %y, i32 1
  %y2 = extractelement <4 x i8> %y, i32 2
  %x0x0 = mul i8 %x0, %x0
  %x3x3 = mul i8 %x3, %x3
  %y1y1 = mul i8 %y1, %y1
  %y2y2 = mul i8 %y2, %y2
  %ins1 = insertelement <4 x i8> undef, i8 %x0x0, i32 0
  %ins2 = insertelement <4 x i8> %ins1, i8 %x3x3, i32 1
  %ins3 = insertelement <4 x i8> %ins2, i8 %y1y1, i32 2
  %ins4 = insertelement <4 x i8> %ins3, i8 %y2y2, i32 3
  ret <4 x i8> %ins4
}

define <4 x i8> @h_undef(<4 x i8> %x, <4 x i8> %y) {
; CHECK-LABEL: @h_undef(
; CHECK-NEXT:    [[X3:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 3
; CHECK-NEXT:    [[Y1:%.*]] = extractelement <4 x i8> [[Y:%.*]], i32 1
; CHECK-NEXT:    [[Y2:%.*]] = extractelement <4 x i8> [[Y]], i32 2
; CHECK-NEXT:    [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
; CHECK-NEXT:    [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
; CHECK-NEXT:    [[Y2Y2:%.*]] = mul i8 [[Y2]], [[Y2]]
; CHECK-NEXT:    [[INS2:%.*]] = insertelement <4 x i8> undef, i8 [[X3X3]], i32 1
; CHECK-NEXT:    [[INS3:%.*]] = insertelement <4 x i8> [[INS2]], i8 [[Y1Y1]], i32 2
; CHECK-NEXT:    [[INS4:%.*]] = insertelement <4 x i8> [[INS3]], i8 [[Y2Y2]], i32 3
; CHECK-NEXT:    ret <4 x i8> [[INS4]]
;
  %x0 = extractelement <4 x i8> undef, i32 0
  %x3 = extractelement <4 x i8> %x, i32 3
  %y1 = extractelement <4 x i8> %y, i32 1
  %y2 = extractelement <4 x i8> %y, i32 2
  %x0x0 = mul i8 %x0, %x0
  %x3x3 = mul i8 %x3, %x3
  %y1y1 = mul i8 %y1, %y1
  %y2y2 = mul i8 %y2, %y2
  %ins1 = insertelement <4 x i8> undef, i8 %x0x0, i32 0
  %ins2 = insertelement <4 x i8> %ins1, i8 %x3x3, i32 1
  %ins3 = insertelement <4 x i8> %ins2, i8 %y1y1, i32 2
  %ins4 = insertelement <4 x i8> %ins3, i8 %y2y2, i32 3
  ret <4 x i8> %ins4
}

define i8 @i(<4 x i8> %x, <4 x i8> %y) {
; CHECK-LABEL: @i(
; CHECK-NEXT:    [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
; CHECK-NEXT:    [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
; CHECK-NEXT:    [[Y1:%.*]] = extractelement <4 x i8> [[Y:%.*]], i32 1
; CHECK-NEXT:    [[Y2:%.*]] = extractelement <4 x i8> [[Y]], i32 2
; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
; CHECK-NEXT:    [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
; CHECK-NEXT:    [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
; CHECK-NEXT:    [[Y2Y2:%.*]] = mul i8 [[Y2]], [[Y2]]
; CHECK-NEXT:    [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
; CHECK-NEXT:    [[TMP2:%.*]] = add i8 [[Y1Y1]], [[Y2Y2]]
; CHECK-NEXT:    [[TMP3:%.*]] = add i8 [[TMP1]], [[TMP2]]
; CHECK-NEXT:    ret i8 [[TMP3]]
;
  %x0 = extractelement <4 x i8> %x, i32 0
  %x3 = extractelement <4 x i8> %x, i32 3
  %y1 = extractelement <4 x i8> %y, i32 1
  %y2 = extractelement <4 x i8> %y, i32 2
  %x0x0 = mul i8 %x0, %x0
  %x3x3 = mul i8 %x3, %x3
  %y1y1 = mul i8 %y1, %y1
  %y2y2 = mul i8 %y2, %y2
  %1 = add i8 %x0x0, %x3x3
  %2 = add i8 %y1y1, %y2y2
  %3 = add i8 %1, %2
  ret i8 %3
}

define i8 @j(<4 x i8> %x, <4 x i8> %y) {
; CHECK-LABEL: @j(
; CHECK-NEXT:    [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
; CHECK-NEXT:    [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
; CHECK-NEXT:    [[Y1:%.*]] = extractelement <4 x i8> [[Y:%.*]], i32 1
; CHECK-NEXT:    [[Y2:%.*]] = extractelement <4 x i8> [[Y]], i32 2
; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
; CHECK-NEXT:    [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
; CHECK-NEXT:    [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
; CHECK-NEXT:    [[Y2Y2:%.*]] = mul i8 [[Y2]], [[Y2]]
; CHECK-NEXT:    [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
; CHECK-NEXT:    [[TMP2:%.*]] = add i8 [[Y1Y1]], [[Y2Y2]]
; CHECK-NEXT:    [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
; CHECK-NEXT:    ret i8 [[TMP3]]
;
  %x0 = extractelement <4 x i8> %x, i32 0
  %x3 = extractelement <4 x i8> %x, i32 3
  %y1 = extractelement <4 x i8> %y, i32 1
  %y2 = extractelement <4 x i8> %y, i32 2
  %x0x0 = mul i8 %x0, %x0
  %x3x3 = mul i8 %x3, %x3
  %y1y1 = mul i8 %y1, %y1
  %y2y2 = mul i8 %y2, %y2
  %1 = add i8 %x0x0, %x3x3
  %2 = add i8 %y1y1, %y2y2
  %3 = sdiv i8 %1, %2
  ret i8 %3
}

define i8 @k(<4 x i8> %x) {
; CHECK-LABEL: @k(
; CHECK-NEXT:    [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
; CHECK-NEXT:    [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
; CHECK-NEXT:    [[X1:%.*]] = extractelement <4 x i8> [[X]], i32 1
; CHECK-NEXT:    [[X2:%.*]] = extractelement <4 x i8> [[X]], i32 2
; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
; CHECK-NEXT:    [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
; CHECK-NEXT:    [[X1X1:%.*]] = mul i8 [[X1]], [[X1]]
; CHECK-NEXT:    [[X2X2:%.*]] = mul i8 [[X2]], [[X2]]
; CHECK-NEXT:    [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
; CHECK-NEXT:    [[TMP2:%.*]] = add i8 [[X1X1]], [[X2X2]]
; CHECK-NEXT:    [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
; CHECK-NEXT:    ret i8 [[TMP3]]
;
  %x0 = extractelement <4 x i8> %x, i32 0
  %x3 = extractelement <4 x i8> %x, i32 3
  %x1 = extractelement <4 x i8> %x, i32 1
  %x2 = extractelement <4 x i8> %x, i32 2
  %x0x0 = mul i8 %x0, %x0
  %x3x3 = mul i8 %x3, %x3
  %x1x1 = mul i8 %x1, %x1
  %x2x2 = mul i8 %x2, %x2
  %1 = add i8 %x0x0, %x3x3
  %2 = add i8 %x1x1, %x2x2
  %3 = sdiv i8 %1, %2
  ret i8 %3
}

define i8 @k_bb(<4 x i8> %x) {
; CHECK-LABEL: @k_bb(
; CHECK-NEXT:    [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
; CHECK-NEXT:    br label [[BB1:%.*]]
; CHECK:       bb1:
; CHECK-NEXT:    [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
; CHECK-NEXT:    [[X1:%.*]] = extractelement <4 x i8> [[X]], i32 1
; CHECK-NEXT:    [[X2:%.*]] = extractelement <4 x i8> [[X]], i32 2
; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
; CHECK-NEXT:    [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
; CHECK-NEXT:    [[X1X1:%.*]] = mul i8 [[X1]], [[X1]]
; CHECK-NEXT:    [[X2X2:%.*]] = mul i8 [[X2]], [[X2]]
; CHECK-NEXT:    [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
; CHECK-NEXT:    [[TMP2:%.*]] = add i8 [[X1X1]], [[X2X2]]
; CHECK-NEXT:    [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
; CHECK-NEXT:    ret i8 [[TMP3]]
;
  %x0 = extractelement <4 x i8> %x, i32 0
  br label %bb1
bb1:
  %x3 = extractelement <4 x i8> %x, i32 3
  %x1 = extractelement <4 x i8> %x, i32 1
  %x2 = extractelement <4 x i8> %x, i32 2
  %x0x0 = mul i8 %x0, %x0
  %x3x3 = mul i8 %x3, %x3
  %x1x1 = mul i8 %x1, %x1
  %x2x2 = mul i8 %x2, %x2
  %1 = add i8 %x0x0, %x3x3
  %2 = add i8 %x1x1, %x2x2
  %3 = sdiv i8 %1, %2
  ret i8 %3
}