xref: /llvm-project/llvm/test/Transforms/SLPVectorizer/RISCV/strided-loads-vectorized.ll (revision 343a810725f27bfe92fbd04a42d42aa9caaee7a6)

; 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 --check-prefixes=CHECK,NO-ZVFHMIN-ZVFBFMIN
; RUN: opt -passes=slp-vectorizer -S -mtriple=riscv64-unknown-linux-gnu -mattr=+v,+zvfhmin,+zvfbfmin < %s | FileCheck %s --check-prefixes=CHECK,ZVFHMIN-ZVFBFMIN


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> splat (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> splat (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> splat (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> splat (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> splat (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> splat (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:    [[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> splat (i1 true), i32 8)
; CHECK-NEXT:    [[TMP2:%.*]] = call <8 x float> @llvm.experimental.vp.strided.load.v8f32.p0.i64(ptr align 4 [[ARRAYIDX1]], i64 -4, <8 x i1> splat (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:
  %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
}


define void @test_bf16(ptr %p, ptr noalias %s) {
; NO-ZVFHMIN-ZVFBFMIN-LABEL: @test_bf16(
; NO-ZVFHMIN-ZVFBFMIN-NEXT:  entry:
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P:%.*]], i64 0, i64 0
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I:%.*]] = load bfloat, ptr [[ARRAYIDX]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 30
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I1:%.*]] = load bfloat, ptr [[ARRAYIDX1]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD:%.*]] = fsub fast bfloat [[I1]], [[I]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds bfloat, ptr [[S:%.*]], i64 0
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store bfloat [[ADD]], ptr [[ARRAYIDX2]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I2:%.*]] = load bfloat, ptr [[ARRAYIDX4]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX6:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 26
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I3:%.*]] = load bfloat, ptr [[ARRAYIDX6]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD7:%.*]] = fsub fast bfloat [[I3]], [[I2]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX9:%.*]] = getelementptr inbounds bfloat, ptr [[S]], i64 1
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store bfloat [[ADD7]], ptr [[ARRAYIDX9]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX11:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 8
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I4:%.*]] = load bfloat, ptr [[ARRAYIDX11]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX13:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 22
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I5:%.*]] = load bfloat, ptr [[ARRAYIDX13]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD14:%.*]] = fsub fast bfloat [[I5]], [[I4]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX16:%.*]] = getelementptr inbounds bfloat, ptr [[S]], i64 2
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store bfloat [[ADD14]], ptr [[ARRAYIDX16]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX18:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 12
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I6:%.*]] = load bfloat, ptr [[ARRAYIDX18]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX20:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 18
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I7:%.*]] = load bfloat, ptr [[ARRAYIDX20]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD21:%.*]] = fsub fast bfloat [[I7]], [[I6]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX23:%.*]] = getelementptr inbounds bfloat, ptr [[S]], i64 3
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store bfloat [[ADD21]], ptr [[ARRAYIDX23]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX25:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 16
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I8:%.*]] = load bfloat, ptr [[ARRAYIDX25]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX27:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 14
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I9:%.*]] = load bfloat, ptr [[ARRAYIDX27]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD28:%.*]] = fsub fast bfloat [[I9]], [[I8]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX30:%.*]] = getelementptr inbounds bfloat, ptr [[S]], i64 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store bfloat [[ADD28]], ptr [[ARRAYIDX30]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX32:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 20
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I10:%.*]] = load bfloat, ptr [[ARRAYIDX32]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX34:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 10
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I11:%.*]] = load bfloat, ptr [[ARRAYIDX34]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD35:%.*]] = fsub fast bfloat [[I11]], [[I10]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX37:%.*]] = getelementptr inbounds bfloat, ptr [[S]], i64 5
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store bfloat [[ADD35]], ptr [[ARRAYIDX37]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX39:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 24
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I12:%.*]] = load bfloat, ptr [[ARRAYIDX39]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX41:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 6
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I13:%.*]] = load bfloat, ptr [[ARRAYIDX41]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD42:%.*]] = fsub fast bfloat [[I13]], [[I12]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX44:%.*]] = getelementptr inbounds bfloat, ptr [[S]], i64 6
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store bfloat [[ADD42]], ptr [[ARRAYIDX44]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX46:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 28
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I14:%.*]] = load bfloat, ptr [[ARRAYIDX46]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX48:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 2
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I15:%.*]] = load bfloat, ptr [[ARRAYIDX48]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD49:%.*]] = fsub fast bfloat [[I15]], [[I14]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX51:%.*]] = getelementptr inbounds bfloat, ptr [[S]], i64 7
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store bfloat [[ADD49]], ptr [[ARRAYIDX51]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    ret void
;
; ZVFHMIN-ZVFBFMIN-LABEL: @test_bf16(
; ZVFHMIN-ZVFBFMIN-NEXT:  entry:
; ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P:%.*]], i64 0, i64 0
; ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [48 x bfloat], ptr [[P]], i64 0, i64 30
; ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds bfloat, ptr [[S:%.*]], i64 0
; ZVFHMIN-ZVFBFMIN-NEXT:    [[TMP15:%.*]] = call <8 x bfloat> @llvm.experimental.vp.strided.load.v8bf16.p0.i64(ptr align 4 [[ARRAYIDX]], i64 8, <8 x i1> splat (i1 true), i32 8)
; ZVFHMIN-ZVFBFMIN-NEXT:    [[TMP7:%.*]] = call <8 x bfloat> @llvm.experimental.vp.strided.load.v8bf16.p0.i64(ptr align 4 [[ARRAYIDX1]], i64 -8, <8 x i1> splat (i1 true), i32 8)
; ZVFHMIN-ZVFBFMIN-NEXT:    [[TMP16:%.*]] = fsub fast <8 x bfloat> [[TMP7]], [[TMP15]]
; ZVFHMIN-ZVFBFMIN-NEXT:    store <8 x bfloat> [[TMP16]], ptr [[ARRAYIDX2]], align 4
; ZVFHMIN-ZVFBFMIN-NEXT:    ret void
;
entry:
  %arrayidx = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 0
  %i = load bfloat, ptr %arrayidx, align 4
  %arrayidx1 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 30
  %i1 = load bfloat, ptr %arrayidx1, align 4
  %add = fsub fast bfloat %i1, %i
  %arrayidx2 = getelementptr inbounds bfloat, ptr %s, i64 0
  store bfloat %add, ptr %arrayidx2, align 4
  %arrayidx4 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 4
  %i2 = load bfloat, ptr %arrayidx4, align 4
  %arrayidx6 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 26
  %i3 = load bfloat, ptr %arrayidx6, align 4
  %add7 = fsub fast bfloat %i3, %i2
  %arrayidx9 = getelementptr inbounds bfloat, ptr %s, i64 1
  store bfloat %add7, ptr %arrayidx9, align 4
  %arrayidx11 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 8
  %i4 = load bfloat, ptr %arrayidx11, align 4
  %arrayidx13 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 22
  %i5 = load bfloat, ptr %arrayidx13, align 4
  %add14 = fsub fast bfloat %i5, %i4
  %arrayidx16 = getelementptr inbounds bfloat, ptr %s, i64 2
  store bfloat %add14, ptr %arrayidx16, align 4
  %arrayidx18 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 12
  %i6 = load bfloat, ptr %arrayidx18, align 4
  %arrayidx20 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 18
  %i7 = load bfloat, ptr %arrayidx20, align 4
  %add21 = fsub fast bfloat %i7, %i6
  %arrayidx23 = getelementptr inbounds bfloat, ptr %s, i64 3
  store bfloat %add21, ptr %arrayidx23, align 4
  %arrayidx25 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 16
  %i8 = load bfloat, ptr %arrayidx25, align 4
  %arrayidx27 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 14
  %i9 = load bfloat, ptr %arrayidx27, align 4
  %add28 = fsub fast bfloat %i9, %i8
  %arrayidx30 = getelementptr inbounds bfloat, ptr %s, i64 4
  store bfloat %add28, ptr %arrayidx30, align 4
  %arrayidx32 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 20
  %i10 = load bfloat, ptr %arrayidx32, align 4
  %arrayidx34 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 10
  %i11 = load bfloat, ptr %arrayidx34, align 4
  %add35 = fsub fast bfloat %i11, %i10
  %arrayidx37 = getelementptr inbounds bfloat, ptr %s, i64 5
  store bfloat %add35, ptr %arrayidx37, align 4
  %arrayidx39 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 24
  %i12 = load bfloat, ptr %arrayidx39, align 4
  %arrayidx41 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 6
  %i13 = load bfloat, ptr %arrayidx41, align 4
  %add42 = fsub fast bfloat %i13, %i12
  %arrayidx44 = getelementptr inbounds bfloat, ptr %s, i64 6
  store bfloat %add42, ptr %arrayidx44, align 4
  %arrayidx46 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 28
  %i14 = load bfloat, ptr %arrayidx46, align 4
  %arrayidx48 = getelementptr inbounds [48 x bfloat], ptr %p, i64 0, i64 2
  %i15 = load bfloat, ptr %arrayidx48, align 4
  %add49 = fsub fast bfloat %i15, %i14
  %arrayidx51 = getelementptr inbounds bfloat, ptr %s, i64 7
  store bfloat %add49, ptr %arrayidx51, align 4
  ret void
}

define void @test_f16(ptr %p, ptr noalias %s) {
; NO-ZVFHMIN-ZVFBFMIN-LABEL: @test_f16(
; NO-ZVFHMIN-ZVFBFMIN-NEXT:  entry:
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [48 x half], ptr [[P:%.*]], i64 0, i64 0
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I:%.*]] = load half, ptr [[ARRAYIDX]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 30
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I1:%.*]] = load half, ptr [[ARRAYIDX1]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD:%.*]] = fsub fast half [[I1]], [[I]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds half, ptr [[S:%.*]], i64 0
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store half [[ADD]], ptr [[ARRAYIDX2]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I2:%.*]] = load half, ptr [[ARRAYIDX4]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX6:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 26
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I3:%.*]] = load half, ptr [[ARRAYIDX6]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD7:%.*]] = fsub fast half [[I3]], [[I2]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX9:%.*]] = getelementptr inbounds half, ptr [[S]], i64 1
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store half [[ADD7]], ptr [[ARRAYIDX9]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX11:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 8
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I4:%.*]] = load half, ptr [[ARRAYIDX11]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX13:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 22
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I5:%.*]] = load half, ptr [[ARRAYIDX13]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD14:%.*]] = fsub fast half [[I5]], [[I4]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX16:%.*]] = getelementptr inbounds half, ptr [[S]], i64 2
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store half [[ADD14]], ptr [[ARRAYIDX16]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX18:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 12
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I6:%.*]] = load half, ptr [[ARRAYIDX18]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX20:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 18
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I7:%.*]] = load half, ptr [[ARRAYIDX20]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD21:%.*]] = fsub fast half [[I7]], [[I6]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX23:%.*]] = getelementptr inbounds half, ptr [[S]], i64 3
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store half [[ADD21]], ptr [[ARRAYIDX23]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX25:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 16
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I8:%.*]] = load half, ptr [[ARRAYIDX25]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX27:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 14
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I9:%.*]] = load half, ptr [[ARRAYIDX27]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD28:%.*]] = fsub fast half [[I9]], [[I8]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX30:%.*]] = getelementptr inbounds half, ptr [[S]], i64 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store half [[ADD28]], ptr [[ARRAYIDX30]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX32:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 20
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I10:%.*]] = load half, ptr [[ARRAYIDX32]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX34:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 10
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I11:%.*]] = load half, ptr [[ARRAYIDX34]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD35:%.*]] = fsub fast half [[I11]], [[I10]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX37:%.*]] = getelementptr inbounds half, ptr [[S]], i64 5
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store half [[ADD35]], ptr [[ARRAYIDX37]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX39:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 24
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I12:%.*]] = load half, ptr [[ARRAYIDX39]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX41:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 6
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I13:%.*]] = load half, ptr [[ARRAYIDX41]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD42:%.*]] = fsub fast half [[I13]], [[I12]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX44:%.*]] = getelementptr inbounds half, ptr [[S]], i64 6
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store half [[ADD42]], ptr [[ARRAYIDX44]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX46:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 28
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I14:%.*]] = load half, ptr [[ARRAYIDX46]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX48:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 2
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[I15:%.*]] = load half, ptr [[ARRAYIDX48]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ADD49:%.*]] = fsub fast half [[I15]], [[I14]]
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX51:%.*]] = getelementptr inbounds half, ptr [[S]], i64 7
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    store half [[ADD49]], ptr [[ARRAYIDX51]], align 4
; NO-ZVFHMIN-ZVFBFMIN-NEXT:    ret void
;
; ZVFHMIN-ZVFBFMIN-LABEL: @test_f16(
; ZVFHMIN-ZVFBFMIN-NEXT:  entry:
; ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [48 x half], ptr [[P:%.*]], i64 0, i64 0
; ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [48 x half], ptr [[P]], i64 0, i64 30
; ZVFHMIN-ZVFBFMIN-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds half, ptr [[S:%.*]], i64 0
; ZVFHMIN-ZVFBFMIN-NEXT:    [[TMP15:%.*]] = call <8 x half> @llvm.experimental.vp.strided.load.v8f16.p0.i64(ptr align 4 [[ARRAYIDX]], i64 8, <8 x i1> splat (i1 true), i32 8)
; ZVFHMIN-ZVFBFMIN-NEXT:    [[TMP7:%.*]] = call <8 x half> @llvm.experimental.vp.strided.load.v8f16.p0.i64(ptr align 4 [[ARRAYIDX1]], i64 -8, <8 x i1> splat (i1 true), i32 8)
; ZVFHMIN-ZVFBFMIN-NEXT:    [[TMP16:%.*]] = fsub fast <8 x half> [[TMP7]], [[TMP15]]
; ZVFHMIN-ZVFBFMIN-NEXT:    store <8 x half> [[TMP16]], ptr [[ARRAYIDX2]], align 4
; ZVFHMIN-ZVFBFMIN-NEXT:    ret void
;
entry:
  %arrayidx = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 0
  %i = load half, ptr %arrayidx, align 4
  %arrayidx1 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 30
  %i1 = load half, ptr %arrayidx1, align 4
  %add = fsub fast half %i1, %i
  %arrayidx2 = getelementptr inbounds half, ptr %s, i64 0
  store half %add, ptr %arrayidx2, align 4
  %arrayidx4 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 4
  %i2 = load half, ptr %arrayidx4, align 4
  %arrayidx6 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 26
  %i3 = load half, ptr %arrayidx6, align 4
  %add7 = fsub fast half %i3, %i2
  %arrayidx9 = getelementptr inbounds half, ptr %s, i64 1
  store half %add7, ptr %arrayidx9, align 4
  %arrayidx11 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 8
  %i4 = load half, ptr %arrayidx11, align 4
  %arrayidx13 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 22
  %i5 = load half, ptr %arrayidx13, align 4
  %add14 = fsub fast half %i5, %i4
  %arrayidx16 = getelementptr inbounds half, ptr %s, i64 2
  store half %add14, ptr %arrayidx16, align 4
  %arrayidx18 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 12
  %i6 = load half, ptr %arrayidx18, align 4
  %arrayidx20 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 18
  %i7 = load half, ptr %arrayidx20, align 4
  %add21 = fsub fast half %i7, %i6
  %arrayidx23 = getelementptr inbounds half, ptr %s, i64 3
  store half %add21, ptr %arrayidx23, align 4
  %arrayidx25 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 16
  %i8 = load half, ptr %arrayidx25, align 4
  %arrayidx27 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 14
  %i9 = load half, ptr %arrayidx27, align 4
  %add28 = fsub fast half %i9, %i8
  %arrayidx30 = getelementptr inbounds half, ptr %s, i64 4
  store half %add28, ptr %arrayidx30, align 4
  %arrayidx32 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 20
  %i10 = load half, ptr %arrayidx32, align 4
  %arrayidx34 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 10
  %i11 = load half, ptr %arrayidx34, align 4
  %add35 = fsub fast half %i11, %i10
  %arrayidx37 = getelementptr inbounds half, ptr %s, i64 5
  store half %add35, ptr %arrayidx37, align 4
  %arrayidx39 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 24
  %i12 = load half, ptr %arrayidx39, align 4
  %arrayidx41 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 6
  %i13 = load half, ptr %arrayidx41, align 4
  %add42 = fsub fast half %i13, %i12
  %arrayidx44 = getelementptr inbounds half, ptr %s, i64 6
  store half %add42, ptr %arrayidx44, align 4
  %arrayidx46 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 28
  %i14 = load half, ptr %arrayidx46, align 4
  %arrayidx48 = getelementptr inbounds [48 x half], ptr %p, i64 0, i64 2
  %i15 = load half, ptr %arrayidx48, align 4
  %add49 = fsub fast half %i15, %i14
  %arrayidx51 = getelementptr inbounds half, ptr %s, i64 7
  store half %add49, ptr %arrayidx51, align 4
  ret void
}