; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=slp-vectorizer -S -mtriple=riscv64-unknown-linux-gnu -mattr=+v < %s | FileCheck %s

define void @test(ptr %p, ptr noalias %s) {
; CHECK-LABEL: @test(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [48 x float], ptr [[P:%.*]], i64 0, i64 0
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [48 x float], ptr [[P]], i64 0, i64 30
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds float, ptr [[S:%.*]], i64 0
; CHECK-NEXT:    [[TMP0:%.*]] = call <8 x float> @llvm.experimental.vp.strided.load.v8f32.p0.i64(ptr align 4 [[ARRAYIDX]], i64 16, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, i32 8)
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x float> @llvm.experimental.vp.strided.load.v8f32.p0.i64(ptr align 4 [[ARRAYIDX1]], i64 -16, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, i32 8)
; CHECK-NEXT:    [[TMP2:%.*]] = fsub fast <8 x float> [[TMP1]], [[TMP0]]
; CHECK-NEXT:    store <8 x float> [[TMP2]], ptr [[ARRAYIDX2]], align 4
; CHECK-NEXT:    ret void
;
entry:
  %arrayidx = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 0
  %i = load float, ptr %arrayidx, align 4
  %arrayidx1 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 30
  %i1 = load float, ptr %arrayidx1, align 4
  %add = fsub fast float %i1, %i
  %arrayidx2 = getelementptr inbounds float, ptr %s, i64 0
  store float %add, ptr %arrayidx2, align 4
  %arrayidx4 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 4
  %i2 = load float, ptr %arrayidx4, align 4
  %arrayidx6 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 26
  %i3 = load float, ptr %arrayidx6, align 4
  %add7 = fsub fast float %i3, %i2
  %arrayidx9 = getelementptr inbounds float, ptr %s, i64 1
  store float %add7, ptr %arrayidx9, align 4
  %arrayidx11 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 8
  %i4 = load float, ptr %arrayidx11, align 4
  %arrayidx13 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 22
  %i5 = load float, ptr %arrayidx13, align 4
  %add14 = fsub fast float %i5, %i4
  %arrayidx16 = getelementptr inbounds float, ptr %s, i64 2
  store float %add14, ptr %arrayidx16, align 4
  %arrayidx18 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 12
  %i6 = load float, ptr %arrayidx18, align 4
  %arrayidx20 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 18
  %i7 = load float, ptr %arrayidx20, align 4
  %add21 = fsub fast float %i7, %i6
  %arrayidx23 = getelementptr inbounds float, ptr %s, i64 3
  store float %add21, ptr %arrayidx23, align 4
  %arrayidx25 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 16
  %i8 = load float, ptr %arrayidx25, align 4
  %arrayidx27 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 14
  %i9 = load float, ptr %arrayidx27, align 4
  %add28 = fsub fast float %i9, %i8
  %arrayidx30 = getelementptr inbounds float, ptr %s, i64 4
  store float %add28, ptr %arrayidx30, align 4
  %arrayidx32 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 20
  %i10 = load float, ptr %arrayidx32, align 4
  %arrayidx34 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 10
  %i11 = load float, ptr %arrayidx34, align 4
  %add35 = fsub fast float %i11, %i10
  %arrayidx37 = getelementptr inbounds float, ptr %s, i64 5
  store float %add35, ptr %arrayidx37, align 4
  %arrayidx39 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 24
  %i12 = load float, ptr %arrayidx39, align 4
  %arrayidx41 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 6
  %i13 = load float, ptr %arrayidx41, align 4
  %add42 = fsub fast float %i13, %i12
  %arrayidx44 = getelementptr inbounds float, ptr %s, i64 6
  store float %add42, ptr %arrayidx44, align 4
  %arrayidx46 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 28
  %i14 = load float, ptr %arrayidx46, align 4
  %arrayidx48 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 2
  %i15 = load float, ptr %arrayidx48, align 4
  %add49 = fsub fast float %i15, %i14
  %arrayidx51 = getelementptr inbounds float, ptr %s, i64 7
  store float %add49, ptr %arrayidx51, align 4
  ret void
}

define void @test1(ptr %p, ptr noalias %s, i32 %stride) {
; CHECK-LABEL: @test1(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STR:%.*]] = zext i32 [[STRIDE:%.*]] to i64
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [48 x float], ptr [[P:%.*]], i64 0, i64 0
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [48 x float], ptr [[P]], i64 0, i64 30
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds float, ptr [[S:%.*]], i64 0
; CHECK-NEXT:    [[TMP0:%.*]] = mul i64 [[STR]], 4
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x float> @llvm.experimental.vp.strided.load.v8f32.p0.i64(ptr align 4 [[ARRAYIDX]], i64 [[TMP0]], <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, i32 8)
; CHECK-NEXT:    [[TMP2:%.*]] = call <8 x float> @llvm.experimental.vp.strided.load.v8f32.p0.i64(ptr align 4 [[ARRAYIDX1]], i64 -16, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, i32 8)
; CHECK-NEXT:    [[TMP3:%.*]] = fsub fast <8 x float> [[TMP2]], [[TMP1]]
; CHECK-NEXT:    store <8 x float> [[TMP3]], ptr [[ARRAYIDX2]], align 4
; CHECK-NEXT:    ret void
;
entry:
  %str = zext i32 %stride to i64
  %arrayidx = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 0
  %i = load float, ptr %arrayidx, align 4
  %arrayidx1 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 30
  %i1 = load float, ptr %arrayidx1, align 4
  %add = fsub fast float %i1, %i
  %arrayidx2 = getelementptr inbounds float, ptr %s, i64 0
  store float %add, ptr %arrayidx2, align 4
  %arrayidx4 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %str
  %i2 = load float, ptr %arrayidx4, align 4
  %arrayidx6 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 26
  %i3 = load float, ptr %arrayidx6, align 4
  %add7 = fsub fast float %i3, %i2
  %arrayidx9 = getelementptr inbounds float, ptr %s, i64 1
  store float %add7, ptr %arrayidx9, align 4
  %st1 = mul i64 %str, 2
  %arrayidx11 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %st1
  %i4 = load float, ptr %arrayidx11, align 4
  %arrayidx13 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 22
  %i5 = load float, ptr %arrayidx13, align 4
  %add14 = fsub fast float %i5, %i4
  %arrayidx16 = getelementptr inbounds float, ptr %s, i64 2
  store float %add14, ptr %arrayidx16, align 4
  %st2 = mul i64 %str, 3
  %arrayidx18 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %st2
  %i6 = load float, ptr %arrayidx18, align 4
  %arrayidx20 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 18
  %i7 = load float, ptr %arrayidx20, align 4
  %add21 = fsub fast float %i7, %i6
  %arrayidx23 = getelementptr inbounds float, ptr %s, i64 3
  store float %add21, ptr %arrayidx23, align 4
  %st3 = mul i64 %str, 4
  %arrayidx25 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %st3
  %i8 = load float, ptr %arrayidx25, align 4
  %arrayidx27 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 14
  %i9 = load float, ptr %arrayidx27, align 4
  %add28 = fsub fast float %i9, %i8
  %arrayidx30 = getelementptr inbounds float, ptr %s, i64 4
  store float %add28, ptr %arrayidx30, align 4
  %st4 = mul i64 %str, 5
  %arrayidx32 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %st4
  %i10 = load float, ptr %arrayidx32, align 4
  %arrayidx34 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 10
  %i11 = load float, ptr %arrayidx34, align 4
  %add35 = fsub fast float %i11, %i10
  %arrayidx37 = getelementptr inbounds float, ptr %s, i64 5
  store float %add35, ptr %arrayidx37, align 4
  %st5 = mul i64 %str, 6
  %arrayidx39 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %st5
  %i12 = load float, ptr %arrayidx39, align 4
  %arrayidx41 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 6
  %i13 = load float, ptr %arrayidx41, align 4
  %add42 = fsub fast float %i13, %i12
  %arrayidx44 = getelementptr inbounds float, ptr %s, i64 6
  store float %add42, ptr %arrayidx44, align 4
  %st6 = mul i64 %str, 7
  %arrayidx46 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %st6
  %i14 = load float, ptr %arrayidx46, align 4
  %arrayidx48 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 2
  %i15 = load float, ptr %arrayidx48, align 4
  %add49 = fsub fast float %i15, %i14
  %arrayidx51 = getelementptr inbounds float, ptr %s, i64 7
  store float %add49, ptr %arrayidx51, align 4
  ret void
}

define void @test2(ptr %p, ptr noalias %s, i32 %stride) {
; CHECK-LABEL: @test2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[STR:%.*]] = zext i32 [[STRIDE:%.*]] to i64
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [48 x float], ptr [[P:%.*]], i64 0, i64 2
; CHECK-NEXT:    [[ST6:%.*]] = mul i64 [[STR]], 7
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [48 x float], ptr [[P]], i64 0, i64 [[ST6]]
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds float, ptr [[S:%.*]], i64 0
; CHECK-NEXT:    [[TMP0:%.*]] = call <8 x float> @llvm.experimental.vp.strided.load.v8f32.p0.i64(ptr align 4 [[ARRAYIDX]], i64 16, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, i32 8)
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[STR]], -4
; CHECK-NEXT:    [[TMP2:%.*]] = call <8 x float> @llvm.experimental.vp.strided.load.v8f32.p0.i64(ptr align 4 [[ARRAYIDX1]], i64 [[TMP1]], <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, i32 8)
; CHECK-NEXT:    [[TMP3:%.*]] = fsub fast <8 x float> [[TMP2]], [[TMP0]]
; CHECK-NEXT:    store <8 x float> [[TMP3]], ptr [[ARRAYIDX2]], align 4
; CHECK-NEXT:    ret void
;
entry:
  %str = zext i32 %stride to i64
  %arrayidx = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 2
  %i = load float, ptr %arrayidx, align 4
  %st6 = mul i64 %str, 7
  %arrayidx1 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %st6
  %i1 = load float, ptr %arrayidx1, align 4
  %add = fsub fast float %i1, %i
  %arrayidx2 = getelementptr inbounds float, ptr %s, i64 0
  store float %add, ptr %arrayidx2, align 4
  %arrayidx4 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 6
  %i2 = load float, ptr %arrayidx4, align 4
  %st5 = mul i64 %str, 6
  %arrayidx6 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %st5
  %i3 = load float, ptr %arrayidx6, align 4
  %add7 = fsub fast float %i3, %i2
  %arrayidx9 = getelementptr inbounds float, ptr %s, i64 1
  store float %add7, ptr %arrayidx9, align 4
  %arrayidx11 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 10
  %i4 = load float, ptr %arrayidx11, align 4
  %st4 = mul i64 %str, 5
  %arrayidx13 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %st4
  %i5 = load float, ptr %arrayidx13, align 4
  %add14 = fsub fast float %i5, %i4
  %arrayidx16 = getelementptr inbounds float, ptr %s, i64 2
  store float %add14, ptr %arrayidx16, align 4
  %arrayidx18 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 14
  %i6 = load float, ptr %arrayidx18, align 4
  %st3 = mul i64 %str, 4
  %arrayidx20 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %st3
  %i7 = load float, ptr %arrayidx20, align 4
  %add21 = fsub fast float %i7, %i6
  %arrayidx23 = getelementptr inbounds float, ptr %s, i64 3
  store float %add21, ptr %arrayidx23, align 4
  %arrayidx25 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 18
  %st2 = mul i64 %str, 3
  %i8 = load float, ptr %arrayidx25, align 4
  %arrayidx27 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %st2
  %i9 = load float, ptr %arrayidx27, align 4
  %add28 = fsub fast float %i9, %i8
  %arrayidx30 = getelementptr inbounds float, ptr %s, i64 4
  store float %add28, ptr %arrayidx30, align 4
  %arrayidx32 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 22
  %i10 = load float, ptr %arrayidx32, align 4
  %st1 = mul i64 %str, 2
  %arrayidx34 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %st1
  %i11 = load float, ptr %arrayidx34, align 4
  %add35 = fsub fast float %i11, %i10
  %arrayidx37 = getelementptr inbounds float, ptr %s, i64 5
  store float %add35, ptr %arrayidx37, align 4
  %arrayidx39 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 26
  %i12 = load float, ptr %arrayidx39, align 4
  %arrayidx41 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 %str
  %i13 = load float, ptr %arrayidx41, align 4
  %add42 = fsub fast float %i13, %i12
  %arrayidx44 = getelementptr inbounds float, ptr %s, i64 6
  store float %add42, ptr %arrayidx44, align 4
  %arrayidx46 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 30
  %i14 = load float, ptr %arrayidx46, align 4
  %arrayidx48 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 0
  %i15 = load float, ptr %arrayidx48, align 4
  %add49 = fsub fast float %i15, %i14
  %arrayidx51 = getelementptr inbounds float, ptr %s, i64 7
  store float %add49, ptr %arrayidx51, align 4
  ret void
}

define void @test3(ptr %p, ptr noalias %s) {
; CHECK-LABEL: @test3(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [48 x float], ptr [[P:%.*]], i64 0, i64 0
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds float, ptr [[S:%.*]], i64 0
; CHECK-NEXT:    [[ARRAYIDX48:%.*]] = getelementptr inbounds [48 x float], ptr [[P]], i64 0, i64 23
; CHECK-NEXT:    [[TMP0:%.*]] = call <8 x float> @llvm.experimental.vp.strided.load.v8f32.p0.i64(ptr align 4 [[ARRAYIDX]], i64 16, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, i32 8)
; CHECK-NEXT:    [[TMP1:%.*]] = load <8 x float>, ptr [[ARRAYIDX48]], align 4
; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <8 x float> [[TMP1]], <8 x float> poison, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP3:%.*]] = fsub fast <8 x float> [[TMP2]], [[TMP0]]
; CHECK-NEXT:    store <8 x float> [[TMP3]], ptr [[ARRAYIDX2]], align 4
; CHECK-NEXT:    ret void
;
entry:
  %arrayidx = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 0
  %i = load float, ptr %arrayidx, align 4
  %arrayidx1 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 30
  %i1 = load float, ptr %arrayidx1, align 4
  %add = fsub fast float %i1, %i
  %arrayidx2 = getelementptr inbounds float, ptr %s, i64 0
  store float %add, ptr %arrayidx2, align 4
  %arrayidx4 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 4
  %i2 = load float, ptr %arrayidx4, align 4
  %arrayidx6 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 29
  %i3 = load float, ptr %arrayidx6, align 4
  %add7 = fsub fast float %i3, %i2
  %arrayidx9 = getelementptr inbounds float, ptr %s, i64 1
  store float %add7, ptr %arrayidx9, align 4
  %arrayidx11 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 8
  %i4 = load float, ptr %arrayidx11, align 4
  %arrayidx13 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 28
  %i5 = load float, ptr %arrayidx13, align 4
  %add14 = fsub fast float %i5, %i4
  %arrayidx16 = getelementptr inbounds float, ptr %s, i64 2
  store float %add14, ptr %arrayidx16, align 4
  %arrayidx18 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 12
  %i6 = load float, ptr %arrayidx18, align 4
  %arrayidx20 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 27
  %i7 = load float, ptr %arrayidx20, align 4
  %add21 = fsub fast float %i7, %i6
  %arrayidx23 = getelementptr inbounds float, ptr %s, i64 3
  store float %add21, ptr %arrayidx23, align 4
  %arrayidx25 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 16
  %i8 = load float, ptr %arrayidx25, align 4
  %arrayidx27 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 26
  %i9 = load float, ptr %arrayidx27, align 4
  %add28 = fsub fast float %i9, %i8
  %arrayidx30 = getelementptr inbounds float, ptr %s, i64 4
  store float %add28, ptr %arrayidx30, align 4
  %arrayidx32 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 20
  %i10 = load float, ptr %arrayidx32, align 4
  %arrayidx34 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 25
  %i11 = load float, ptr %arrayidx34, align 4
  %add35 = fsub fast float %i11, %i10
  %arrayidx37 = getelementptr inbounds float, ptr %s, i64 5
  store float %add35, ptr %arrayidx37, align 4
  %arrayidx39 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 24
  %i12 = load float, ptr %arrayidx39, align 4
  %arrayidx41 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 24
  %i13 = load float, ptr %arrayidx41, align 4
  %add42 = fsub fast float %i13, %i12
  %arrayidx44 = getelementptr inbounds float, ptr %s, i64 6
  store float %add42, ptr %arrayidx44, align 4
  %arrayidx46 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 28
  %i14 = load float, ptr %arrayidx46, align 4
  %arrayidx48 = getelementptr inbounds [48 x float], ptr %p, i64 0, i64 23
  %i15 = load float, ptr %arrayidx48, align 4
  %add49 = fsub fast float %i15, %i14
  %arrayidx51 = getelementptr inbounds float, ptr %s, i64 7
  store float %add49, ptr %arrayidx51, align 4
  ret void
}