; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64--linux-gnu | FileCheck %s

define i32 @v1(ptr nocapture noundef readonly %p1, i32 noundef %i1, ptr nocapture noundef readonly %p2, i32 noundef %i2) {
; CHECK-LABEL: v1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    // kill: def $w3 killed $w3 def $x3
; CHECK-NEXT:    // kill: def $w1 killed $w1 def $x1
; CHECK-NEXT:    sxtw x8, w1
; CHECK-NEXT:    sxtw x9, w3
; CHECK-NEXT:    ldr d0, [x0]
; CHECK-NEXT:    ldr d1, [x2]
; CHECK-NEXT:    add x10, x0, x8
; CHECK-NEXT:    add x11, x2, x9
; CHECK-NEXT:    ldr d2, [x10]
; CHECK-NEXT:    add x10, x10, x8
; CHECK-NEXT:    ldr d3, [x11]
; CHECK-NEXT:    add x11, x11, x9
; CHECK-NEXT:    ldr d4, [x10]
; CHECK-NEXT:    ldr d6, [x10, x8]
; CHECK-NEXT:    ldr d5, [x11]
; CHECK-NEXT:    ldr d7, [x11, x9]
; CHECK-NEXT:    usubl v2.8h, v2.8b, v3.8b
; CHECK-NEXT:    usubl v0.8h, v0.8b, v1.8b
; CHECK-NEXT:    usubl v1.8h, v4.8b, v5.8b
; CHECK-NEXT:    usubl v3.8h, v6.8b, v7.8b
; CHECK-NEXT:    shll2 v4.4s, v2.8h, #16
; CHECK-NEXT:    shll2 v5.4s, v0.8h, #16
; CHECK-NEXT:    shll2 v6.4s, v3.8h, #16
; CHECK-NEXT:    shll2 v7.4s, v1.8h, #16
; CHECK-NEXT:    saddw v2.4s, v4.4s, v2.4h
; CHECK-NEXT:    saddw v0.4s, v5.4s, v0.4h
; CHECK-NEXT:    saddw v3.4s, v6.4s, v3.4h
; CHECK-NEXT:    saddw v1.4s, v7.4s, v1.4h
; CHECK-NEXT:    mov v7.16b, v2.16b
; CHECK-NEXT:    zip1 v4.4s, v2.4s, v0.4s
; CHECK-NEXT:    zip2 v6.4s, v2.4s, v0.4s
; CHECK-NEXT:    uzp2 v5.4s, v3.4s, v1.4s
; CHECK-NEXT:    mov v17.16b, v1.16b
; CHECK-NEXT:    zip2 v16.4s, v1.4s, v3.4s
; CHECK-NEXT:    mov v7.s[3], v0.s[2]
; CHECK-NEXT:    ext v18.16b, v3.16b, v3.16b, #12
; CHECK-NEXT:    ext v2.16b, v2.16b, v4.16b, #8
; CHECK-NEXT:    mov v17.s[1], v3.s[0]
; CHECK-NEXT:    uzp2 v0.4s, v5.4s, v3.4s
; CHECK-NEXT:    zip2 v5.4s, v3.4s, v1.4s
; CHECK-NEXT:    mov v3.s[0], v1.s[1]
; CHECK-NEXT:    ext v1.16b, v1.16b, v18.16b, #12
; CHECK-NEXT:    mov v16.d[1], v7.d[1]
; CHECK-NEXT:    mov v17.d[1], v2.d[1]
; CHECK-NEXT:    mov v0.d[1], v6.d[1]
; CHECK-NEXT:    mov v5.d[1], v7.d[1]
; CHECK-NEXT:    mov v3.d[1], v4.d[1]
; CHECK-NEXT:    mov v1.d[1], v6.d[1]
; CHECK-NEXT:    add v0.4s, v0.4s, v5.4s
; CHECK-NEXT:    add v2.4s, v3.4s, v17.4s
; CHECK-NEXT:    sub v3.4s, v17.4s, v3.4s
; CHECK-NEXT:    sub v1.4s, v16.4s, v1.4s
; CHECK-NEXT:    rev64 v4.4s, v0.4s
; CHECK-NEXT:    rev64 v5.4s, v2.4s
; CHECK-NEXT:    add v6.4s, v1.4s, v3.4s
; CHECK-NEXT:    sub v1.4s, v3.4s, v1.4s
; CHECK-NEXT:    mov v4.d[1], v0.d[1]
; CHECK-NEXT:    mov v5.d[1], v2.d[1]
; CHECK-NEXT:    rev64 v3.4s, v1.4s
; CHECK-NEXT:    sub v2.4s, v2.4s, v4.4s
; CHECK-NEXT:    add v0.4s, v0.4s, v5.4s
; CHECK-NEXT:    rev64 v4.4s, v6.4s
; CHECK-NEXT:    rev64 v5.4s, v2.4s
; CHECK-NEXT:    rev64 v7.4s, v0.4s
; CHECK-NEXT:    addp v16.4s, v0.4s, v6.4s
; CHECK-NEXT:    addp v17.4s, v2.4s, v1.4s
; CHECK-NEXT:    sub v4.4s, v6.4s, v4.4s
; CHECK-NEXT:    sub v1.4s, v1.4s, v3.4s
; CHECK-NEXT:    sub v2.4s, v2.4s, v5.4s
; CHECK-NEXT:    sub v0.4s, v0.4s, v7.4s
; CHECK-NEXT:    zip1 v21.4s, v16.4s, v16.4s
; CHECK-NEXT:    ext v5.16b, v17.16b, v1.16b, #4
; CHECK-NEXT:    ext v6.16b, v16.16b, v4.16b, #4
; CHECK-NEXT:    mov v18.16b, v1.16b
; CHECK-NEXT:    mov v19.16b, v4.16b
; CHECK-NEXT:    ext v3.16b, v2.16b, v17.16b, #8
; CHECK-NEXT:    ext v7.16b, v0.16b, v16.16b, #4
; CHECK-NEXT:    mov v18.s[2], v17.s[3]
; CHECK-NEXT:    zip2 v5.4s, v5.4s, v17.4s
; CHECK-NEXT:    zip2 v6.4s, v6.4s, v16.4s
; CHECK-NEXT:    mov v19.s[2], v16.s[3]
; CHECK-NEXT:    trn2 v0.4s, v21.4s, v0.4s
; CHECK-NEXT:    ext v20.16b, v3.16b, v2.16b, #4
; CHECK-NEXT:    ext v7.16b, v7.16b, v7.16b, #4
; CHECK-NEXT:    mov v2.s[2], v17.s[1]
; CHECK-NEXT:    ext v1.16b, v1.16b, v5.16b, #12
; CHECK-NEXT:    ext v4.16b, v4.16b, v6.16b, #12
; CHECK-NEXT:    mov v5.16b, v18.16b
; CHECK-NEXT:    uzp2 v3.4s, v3.4s, v20.4s
; CHECK-NEXT:    mov v6.16b, v7.16b
; CHECK-NEXT:    mov v20.16b, v19.16b
; CHECK-NEXT:    mov v21.16b, v2.16b
; CHECK-NEXT:    mov v5.s[1], v17.s[2]
; CHECK-NEXT:    sub v7.4s, v0.4s, v7.4s
; CHECK-NEXT:    mov v6.s[0], v16.s[1]
; CHECK-NEXT:    mov v20.s[1], v16.s[2]
; CHECK-NEXT:    sub v16.4s, v19.4s, v4.4s
; CHECK-NEXT:    mov v21.s[1], v17.s[0]
; CHECK-NEXT:    sub v2.4s, v2.4s, v3.4s
; CHECK-NEXT:    sub v17.4s, v18.4s, v1.4s
; CHECK-NEXT:    add v1.4s, v5.4s, v1.4s
; CHECK-NEXT:    add v0.4s, v0.4s, v6.4s
; CHECK-NEXT:    add v4.4s, v20.4s, v4.4s
; CHECK-NEXT:    add v3.4s, v21.4s, v3.4s
; CHECK-NEXT:    mov v1.d[1], v17.d[1]
; CHECK-NEXT:    mov v0.d[1], v7.d[1]
; CHECK-NEXT:    mov v4.d[1], v16.d[1]
; CHECK-NEXT:    mov v3.d[1], v2.d[1]
; CHECK-NEXT:    cmlt v7.8h, v1.8h, #0
; CHECK-NEXT:    cmlt v2.8h, v0.8h, #0
; CHECK-NEXT:    cmlt v6.8h, v4.8h, #0
; CHECK-NEXT:    cmlt v5.8h, v3.8h, #0
; CHECK-NEXT:    add v1.4s, v7.4s, v1.4s
; CHECK-NEXT:    add v0.4s, v2.4s, v0.4s
; CHECK-NEXT:    add v4.4s, v6.4s, v4.4s
; CHECK-NEXT:    add v3.4s, v5.4s, v3.4s
; CHECK-NEXT:    eor v1.16b, v1.16b, v7.16b
; CHECK-NEXT:    eor v0.16b, v0.16b, v2.16b
; CHECK-NEXT:    eor v2.16b, v3.16b, v5.16b
; CHECK-NEXT:    eor v3.16b, v4.16b, v6.16b
; CHECK-NEXT:    add v1.4s, v3.4s, v1.4s
; CHECK-NEXT:    add v0.4s, v0.4s, v2.4s
; CHECK-NEXT:    add v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    addv s0, v0.4s
; CHECK-NEXT:    fmov w8, s0
; CHECK-NEXT:    lsr w9, w8, #16
; CHECK-NEXT:    add w8, w9, w8, uxth
; CHECK-NEXT:    lsr w0, w8, #1
; CHECK-NEXT:    ret
entry:
  %idx.ext = sext i32 %i1 to i64
  %idx.ext63 = sext i32 %i2 to i64
  %arrayidx3 = getelementptr inbounds i8, ptr %p1, i64 4
  %arrayidx5 = getelementptr inbounds i8, ptr %p2, i64 4
  %0 = load <4 x i8>, ptr %p1, align 1
  %1 = load <4 x i8>, ptr %p2, align 1
  %add.ptr = getelementptr inbounds i8, ptr %p1, i64 %idx.ext
  %add.ptr64 = getelementptr inbounds i8, ptr %p2, i64 %idx.ext63
  %arrayidx3.1 = getelementptr inbounds i8, ptr %add.ptr, i64 4
  %arrayidx5.1 = getelementptr inbounds i8, ptr %add.ptr64, i64 4
  %2 = load <4 x i8>, ptr %add.ptr, align 1
  %3 = load <4 x i8>, ptr %add.ptr64, align 1
  %add.ptr.1 = getelementptr inbounds i8, ptr %add.ptr, i64 %idx.ext
  %add.ptr64.1 = getelementptr inbounds i8, ptr %add.ptr64, i64 %idx.ext63
  %arrayidx3.2 = getelementptr inbounds i8, ptr %add.ptr.1, i64 4
  %arrayidx5.2 = getelementptr inbounds i8, ptr %add.ptr64.1, i64 4
  %4 = load <4 x i8>, ptr %add.ptr.1, align 1
  %5 = load <4 x i8>, ptr %add.ptr64.1, align 1
  %add.ptr.2 = getelementptr inbounds i8, ptr %add.ptr.1, i64 %idx.ext
  %add.ptr64.2 = getelementptr inbounds i8, ptr %add.ptr64.1, i64 %idx.ext63
  %arrayidx3.3 = getelementptr inbounds i8, ptr %add.ptr.2, i64 4
  %arrayidx5.3 = getelementptr inbounds i8, ptr %add.ptr64.2, i64 4
  %6 = load <4 x i8>, ptr %add.ptr.2, align 1
  %7 = load <4 x i8>, ptr %add.ptr64.2, align 1
  %8 = load <4 x i8>, ptr %arrayidx3, align 1
  %9 = load <4 x i8>, ptr %arrayidx3.1, align 1
  %10 = load <4 x i8>, ptr %arrayidx3.2, align 1
  %11 = load <4 x i8>, ptr %arrayidx3.3, align 1
  %12 = shufflevector <4 x i8> %11, <4 x i8> %10, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %13 = shufflevector <4 x i8> %9, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %14 = shufflevector <16 x i8> %12, <16 x i8> %13, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 undef, i32 undef, i32 undef, i32 undef>
  %15 = shufflevector <4 x i8> %8, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %16 = shufflevector <16 x i8> %14, <16 x i8> %15, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
  %17 = zext <16 x i8> %16 to <16 x i32>
  %18 = load <4 x i8>, ptr %arrayidx5, align 1
  %19 = load <4 x i8>, ptr %arrayidx5.1, align 1
  %20 = load <4 x i8>, ptr %arrayidx5.2, align 1
  %21 = load <4 x i8>, ptr %arrayidx5.3, align 1
  %22 = shufflevector <4 x i8> %21, <4 x i8> %20, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %23 = shufflevector <4 x i8> %19, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %24 = shufflevector <16 x i8> %22, <16 x i8> %23, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 undef, i32 undef, i32 undef, i32 undef>
  %25 = shufflevector <4 x i8> %18, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %26 = shufflevector <16 x i8> %24, <16 x i8> %25, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
  %27 = zext <16 x i8> %26 to <16 x i32>
  %28 = shufflevector <4 x i8> %6, <4 x i8> %4, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %29 = shufflevector <4 x i8> %2, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %30 = shufflevector <16 x i8> %28, <16 x i8> %29, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 undef, i32 undef, i32 undef, i32 undef>
  %31 = shufflevector <4 x i8> %0, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %32 = shufflevector <16 x i8> %30, <16 x i8> %31, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
  %33 = zext <16 x i8> %32 to <16 x i32>
  %34 = shufflevector <4 x i8> %7, <4 x i8> %5, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %35 = shufflevector <4 x i8> %3, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %36 = shufflevector <16 x i8> %34, <16 x i8> %35, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 undef, i32 undef, i32 undef, i32 undef>
  %37 = shufflevector <4 x i8> %1, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %38 = shufflevector <16 x i8> %36, <16 x i8> %37, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
  %39 = zext <16 x i8> %38 to <16 x i32>
  %40 = sub nsw <16 x i32> %33, %39
  %41 = sub nsw <16 x i32> %17, %27
  %42 = shl nsw <16 x i32> %41, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
  %43 = add nsw <16 x i32> %42, %40
  %44 = shufflevector <16 x i32> %43, <16 x i32> poison, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 6, i32 2, i32 10, i32 14, i32 5, i32 1, i32 9, i32 13, i32 4, i32 0, i32 8, i32 12>
  %45 = shufflevector <16 x i32> %43, <16 x i32> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 7, i32 3, i32 11, i32 15, i32 4, i32 0, i32 8, i32 12, i32 5, i32 1, i32 9, i32 13>
  %46 = add nsw <16 x i32> %44, %45
  %47 = sub nsw <16 x i32> %44, %45
  %48 = shufflevector <16 x i32> %46, <16 x i32> %47, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 28, i32 29, i32 30, i32 31>
  %49 = shufflevector <16 x i32> %46, <16 x i32> %47, <16 x i32> <i32 9, i32 8, i32 10, i32 11, i32 28, i32 29, i32 30, i32 31, i32 1, i32 0, i32 2, i32 3, i32 20, i32 21, i32 22, i32 23>
  %50 = add nsw <16 x i32> %48, %49
  %51 = sub nsw <16 x i32> %48, %49
  %52 = shufflevector <16 x i32> %50, <16 x i32> %51, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
  %53 = shufflevector <16 x i32> %50, <16 x i32> %51, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 25, i32 24, i32 27, i32 26, i32 29, i32 28, i32 31, i32 30>
  %54 = add nsw <16 x i32> %52, %53
  %55 = sub nsw <16 x i32> %52, %53
  %56 = shufflevector <16 x i32> %54, <16 x i32> %55, <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 20, i32 5, i32 6, i32 23, i32 24, i32 9, i32 10, i32 27, i32 28, i32 13, i32 14, i32 31>
  %57 = shufflevector <16 x i32> %54, <16 x i32> %55, <16 x i32> <i32 2, i32 19, i32 0, i32 17, i32 23, i32 6, i32 5, i32 20, i32 27, i32 10, i32 9, i32 24, i32 31, i32 14, i32 13, i32 28>
  %58 = add nsw <16 x i32> %56, %57
  %59 = sub nsw <16 x i32> %56, %57
  %60 = shufflevector <16 x i32> %58, <16 x i32> %59, <16 x i32> <i32 0, i32 1, i32 18, i32 19, i32 4, i32 5, i32 22, i32 23, i32 8, i32 9, i32 26, i32 27, i32 12, i32 13, i32 30, i32 31>
  %61 = lshr <16 x i32> %60, <i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15>
  %62 = and <16 x i32> %61, <i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537>
  %63 = mul nuw <16 x i32> %62, <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
  %64 = add <16 x i32> %63, %60
  %65 = xor <16 x i32> %64, %63
  %66 = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %65)
  %conv118 = and i32 %66, 65535
  %shr = lshr i32 %66, 16
  %add119 = add nuw nsw i32 %conv118, %shr
  %shr120 = lshr i32 %add119, 1
  ret i32 %shr120
}

define i32 @v2(ptr nocapture noundef readonly %p1, i32 noundef %i1, ptr nocapture noundef readonly %p2, i32 noundef %i2) {
; CHECK-LABEL: v2:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    // kill: def $w1 killed $w1 def $x1
; CHECK-NEXT:    sxtw x8, w1
; CHECK-NEXT:    // kill: def $w3 killed $w3 def $x3
; CHECK-NEXT:    sxtw x9, w3
; CHECK-NEXT:    ldr d4, [x0]
; CHECK-NEXT:    ldr d5, [x2]
; CHECK-NEXT:    add x10, x0, x8
; CHECK-NEXT:    add x11, x2, x9
; CHECK-NEXT:    add x12, x10, x8
; CHECK-NEXT:    ldr d6, [x10]
; CHECK-NEXT:    ldr d7, [x11]
; CHECK-NEXT:    ldr d0, [x12, x8]
; CHECK-NEXT:    add x8, x11, x9
; CHECK-NEXT:    ldr d1, [x12]
; CHECK-NEXT:    ldr d2, [x8, x9]
; CHECK-NEXT:    ldr d3, [x8]
; CHECK-NEXT:    usubl v1.8h, v1.8b, v3.8b
; CHECK-NEXT:    usubl v0.8h, v0.8b, v2.8b
; CHECK-NEXT:    usubl v3.8h, v6.8b, v7.8b
; CHECK-NEXT:    usubl v2.8h, v4.8b, v5.8b
; CHECK-NEXT:    shll2 v4.4s, v0.8h, #16
; CHECK-NEXT:    shll2 v5.4s, v1.8h, #16
; CHECK-NEXT:    shll2 v7.4s, v3.8h, #16
; CHECK-NEXT:    shll2 v6.4s, v2.8h, #16
; CHECK-NEXT:    saddw v0.4s, v4.4s, v0.4h
; CHECK-NEXT:    saddw v1.4s, v5.4s, v1.4h
; CHECK-NEXT:    saddw v3.4s, v7.4s, v3.4h
; CHECK-NEXT:    saddw v2.4s, v6.4s, v2.4h
; CHECK-NEXT:    uzp2 v4.4s, v0.4s, v1.4s
; CHECK-NEXT:    mov v7.16b, v3.16b
; CHECK-NEXT:    mov v17.16b, v1.16b
; CHECK-NEXT:    zip1 v5.4s, v3.4s, v2.4s
; CHECK-NEXT:    zip2 v6.4s, v3.4s, v2.4s
; CHECK-NEXT:    zip2 v16.4s, v0.4s, v1.4s
; CHECK-NEXT:    ext v18.16b, v0.16b, v0.16b, #12
; CHECK-NEXT:    mov v7.s[3], v2.s[2]
; CHECK-NEXT:    mov v17.s[1], v0.s[0]
; CHECK-NEXT:    uzp2 v2.4s, v4.4s, v0.4s
; CHECK-NEXT:    mov v4.16b, v0.16b
; CHECK-NEXT:    zip2 v0.4s, v1.4s, v0.4s
; CHECK-NEXT:    ext v3.16b, v3.16b, v5.16b, #8
; CHECK-NEXT:    mov v4.s[0], v1.s[1]
; CHECK-NEXT:    mov v16.d[1], v7.d[1]
; CHECK-NEXT:    ext v1.16b, v1.16b, v18.16b, #12
; CHECK-NEXT:    mov v2.d[1], v6.d[1]
; CHECK-NEXT:    mov v0.d[1], v7.d[1]
; CHECK-NEXT:    mov v17.d[1], v3.d[1]
; CHECK-NEXT:    mov v4.d[1], v5.d[1]
; CHECK-NEXT:    mov v1.d[1], v6.d[1]
; CHECK-NEXT:    add v2.4s, v2.4s, v16.4s
; CHECK-NEXT:    add v3.4s, v4.4s, v17.4s
; CHECK-NEXT:    sub v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    sub v1.4s, v17.4s, v4.4s
; CHECK-NEXT:    rev64 v5.4s, v2.4s
; CHECK-NEXT:    rev64 v6.4s, v3.4s
; CHECK-NEXT:    sub v4.4s, v1.4s, v0.4s
; CHECK-NEXT:    add v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    mov v5.d[1], v2.d[1]
; CHECK-NEXT:    mov v6.d[1], v3.d[1]
; CHECK-NEXT:    sub v3.4s, v3.4s, v5.4s
; CHECK-NEXT:    add v1.4s, v2.4s, v6.4s
; CHECK-NEXT:    zip1 v2.4s, v3.4s, v4.4s
; CHECK-NEXT:    zip2 v7.4s, v3.4s, v4.4s
; CHECK-NEXT:    zip1 v5.4s, v1.4s, v0.4s
; CHECK-NEXT:    uzp2 v6.4s, v1.4s, v0.4s
; CHECK-NEXT:    mov v18.16b, v1.16b
; CHECK-NEXT:    ext v16.16b, v3.16b, v2.16b, #8
; CHECK-NEXT:    zip2 v17.4s, v1.4s, v0.4s
; CHECK-NEXT:    mov v3.s[3], v4.s[2]
; CHECK-NEXT:    mov v18.s[1], v0.s[1]
; CHECK-NEXT:    trn2 v4.4s, v1.4s, v5.4s
; CHECK-NEXT:    uzp2 v1.4s, v6.4s, v1.4s
; CHECK-NEXT:    mov v17.d[1], v3.d[1]
; CHECK-NEXT:    mov v18.d[1], v2.d[1]
; CHECK-NEXT:    mov v4.d[1], v16.d[1]
; CHECK-NEXT:    mov v1.d[1], v7.d[1]
; CHECK-NEXT:    add v0.4s, v17.4s, v1.4s
; CHECK-NEXT:    sub v1.4s, v1.4s, v17.4s
; CHECK-NEXT:    add v2.4s, v18.4s, v4.4s
; CHECK-NEXT:    sub v3.4s, v4.4s, v18.4s
; CHECK-NEXT:    zip2 v4.4s, v0.4s, v1.4s
; CHECK-NEXT:    ext v5.16b, v0.16b, v0.16b, #4
; CHECK-NEXT:    ext v6.16b, v2.16b, v2.16b, #4
; CHECK-NEXT:    zip2 v7.4s, v1.4s, v0.4s
; CHECK-NEXT:    zip2 v16.4s, v3.4s, v2.4s
; CHECK-NEXT:    zip2 v17.4s, v2.4s, v3.4s
; CHECK-NEXT:    zip1 v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    zip1 v2.4s, v2.4s, v3.4s
; CHECK-NEXT:    ext v1.16b, v5.16b, v1.16b, #8
; CHECK-NEXT:    ext v18.16b, v6.16b, v3.16b, #8
; CHECK-NEXT:    add v3.4s, v16.4s, v7.4s
; CHECK-NEXT:    sub v4.4s, v4.4s, v17.4s
; CHECK-NEXT:    sub v0.4s, v0.4s, v2.4s
; CHECK-NEXT:    ext v1.16b, v1.16b, v5.16b, #4
; CHECK-NEXT:    ext v5.16b, v18.16b, v6.16b, #4
; CHECK-NEXT:    cmlt v2.8h, v4.8h, #0
; CHECK-NEXT:    cmlt v6.8h, v3.8h, #0
; CHECK-NEXT:    add v3.4s, v6.4s, v3.4s
; CHECK-NEXT:    add v4.4s, v2.4s, v4.4s
; CHECK-NEXT:    add v1.4s, v5.4s, v1.4s
; CHECK-NEXT:    cmlt v5.8h, v0.8h, #0
; CHECK-NEXT:    add v0.4s, v5.4s, v0.4s
; CHECK-NEXT:    eor v2.16b, v4.16b, v2.16b
; CHECK-NEXT:    eor v3.16b, v3.16b, v6.16b
; CHECK-NEXT:    cmlt v4.8h, v1.8h, #0
; CHECK-NEXT:    add v2.4s, v3.4s, v2.4s
; CHECK-NEXT:    add v1.4s, v4.4s, v1.4s
; CHECK-NEXT:    eor v0.16b, v0.16b, v5.16b
; CHECK-NEXT:    add v0.4s, v0.4s, v2.4s
; CHECK-NEXT:    eor v1.16b, v1.16b, v4.16b
; CHECK-NEXT:    add v0.4s, v1.4s, v0.4s
; CHECK-NEXT:    addv s0, v0.4s
; CHECK-NEXT:    fmov w8, s0
; CHECK-NEXT:    lsr w9, w8, #16
; CHECK-NEXT:    add w8, w9, w8, uxth
; CHECK-NEXT:    lsr w0, w8, #1
; CHECK-NEXT:    ret
entry:
  %idx.ext = sext i32 %i1 to i64
  %idx.ext63 = sext i32 %i2 to i64
  %arrayidx3 = getelementptr inbounds i8, ptr %p1, i64 4
  %arrayidx5 = getelementptr inbounds i8, ptr %p2, i64 4
  %0 = load <4 x i8>, ptr %p1, align 1
  %1 = load <4 x i8>, ptr %p2, align 1
  %add.ptr = getelementptr inbounds i8, ptr %p1, i64 %idx.ext
  %add.ptr64 = getelementptr inbounds i8, ptr %p2, i64 %idx.ext63
  %arrayidx3.1 = getelementptr inbounds i8, ptr %add.ptr, i64 4
  %arrayidx5.1 = getelementptr inbounds i8, ptr %add.ptr64, i64 4
  %2 = load <4 x i8>, ptr %add.ptr, align 1
  %3 = load <4 x i8>, ptr %add.ptr64, align 1
  %add.ptr.1 = getelementptr inbounds i8, ptr %add.ptr, i64 %idx.ext
  %add.ptr64.1 = getelementptr inbounds i8, ptr %add.ptr64, i64 %idx.ext63
  %arrayidx3.2 = getelementptr inbounds i8, ptr %add.ptr.1, i64 4
  %arrayidx5.2 = getelementptr inbounds i8, ptr %add.ptr64.1, i64 4
  %4 = load <4 x i8>, ptr %add.ptr.1, align 1
  %5 = load <4 x i8>, ptr %add.ptr64.1, align 1
  %add.ptr.2 = getelementptr inbounds i8, ptr %add.ptr.1, i64 %idx.ext
  %add.ptr64.2 = getelementptr inbounds i8, ptr %add.ptr64.1, i64 %idx.ext63
  %arrayidx3.3 = getelementptr inbounds i8, ptr %add.ptr.2, i64 4
  %arrayidx5.3 = getelementptr inbounds i8, ptr %add.ptr64.2, i64 4
  %6 = load <4 x i8>, ptr %add.ptr.2, align 1
  %7 = load <4 x i8>, ptr %add.ptr64.2, align 1
  %8 = load <4 x i8>, ptr %arrayidx3, align 1
  %9 = load <4 x i8>, ptr %arrayidx3.1, align 1
  %10 = load <4 x i8>, ptr %arrayidx3.2, align 1
  %11 = load <4 x i8>, ptr %arrayidx3.3, align 1
  %12 = shufflevector <4 x i8> %11, <4 x i8> %10, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %13 = shufflevector <4 x i8> %9, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %14 = shufflevector <16 x i8> %12, <16 x i8> %13, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 undef, i32 undef, i32 undef, i32 undef>
  %15 = shufflevector <4 x i8> %8, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %16 = shufflevector <16 x i8> %14, <16 x i8> %15, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
  %17 = zext <16 x i8> %16 to <16 x i32>
  %18 = load <4 x i8>, ptr %arrayidx5, align 1
  %19 = load <4 x i8>, ptr %arrayidx5.1, align 1
  %20 = load <4 x i8>, ptr %arrayidx5.2, align 1
  %21 = load <4 x i8>, ptr %arrayidx5.3, align 1
  %22 = shufflevector <4 x i8> %21, <4 x i8> %20, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %23 = shufflevector <4 x i8> %19, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %24 = shufflevector <16 x i8> %22, <16 x i8> %23, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 undef, i32 undef, i32 undef, i32 undef>
  %25 = shufflevector <4 x i8> %18, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %26 = shufflevector <16 x i8> %24, <16 x i8> %25, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
  %27 = zext <16 x i8> %26 to <16 x i32>
  %28 = shufflevector <4 x i8> %6, <4 x i8> %4, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %29 = shufflevector <4 x i8> %2, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %30 = shufflevector <16 x i8> %28, <16 x i8> %29, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 undef, i32 undef, i32 undef, i32 undef>
  %31 = shufflevector <4 x i8> %0, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %32 = shufflevector <16 x i8> %30, <16 x i8> %31, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
  %33 = zext <16 x i8> %32 to <16 x i32>
  %34 = shufflevector <4 x i8> %7, <4 x i8> %5, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %35 = shufflevector <4 x i8> %3, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %36 = shufflevector <16 x i8> %34, <16 x i8> %35, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 undef, i32 undef, i32 undef, i32 undef>
  %37 = shufflevector <4 x i8> %1, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %38 = shufflevector <16 x i8> %36, <16 x i8> %37, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
  %39 = zext <16 x i8> %38 to <16 x i32>
  %40 = sub nsw <16 x i32> %33, %39
  %41 = sub nsw <16 x i32> %17, %27
  %42 = shl nsw <16 x i32> %41, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
  %43 = add nsw <16 x i32> %42, %40
  %44 = shufflevector <16 x i32> %43, <16 x i32> poison, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 6, i32 2, i32 10, i32 14, i32 5, i32 1, i32 9, i32 13, i32 4, i32 0, i32 8, i32 12>
  %reorder = shufflevector <16 x i32> %44, <16 x i32> poison, <16 x i32> <i32 5, i32 4, i32 6, i32 7, i32 1, i32 0, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15, i32 8, i32 9, i32 10, i32 11>
  %45 = add nsw <16 x i32> %44, %reorder
  %46 = sub nsw <16 x i32> %44, %reorder
  %47 = shufflevector <16 x i32> %45, <16 x i32> %46, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 28, i32 29, i32 30, i32 31>
  %reorder191 = shufflevector <16 x i32> %45, <16 x i32> %46, <16 x i32> <i32 9, i32 8, i32 10, i32 11, i32 28, i32 29, i32 30, i32 31, i32 1, i32 0, i32 2, i32 3, i32 20, i32 21, i32 22, i32 23>
  %48 = add nsw <16 x i32> %47, %reorder191
  %49 = sub nsw <16 x i32> %47, %reorder191
  %50 = shufflevector <16 x i32> %48, <16 x i32> %49, <16 x i32> <i32 0, i32 5, i32 25, i32 29, i32 2, i32 6, i32 26, i32 30, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %51 = shufflevector <16 x i32> %48, <16 x i32> %49, <16 x i32> <i32 1, i32 4, i32 24, i32 28, i32 3, i32 7, i32 27, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %52 = shufflevector <16 x i32> %48, <16 x i32> %49, <16 x i32> <i32 1, i32 4, i32 24, i32 28, i32 3, i32 7, i32 27, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %53 = shufflevector <16 x i32> %48, <16 x i32> %49, <16 x i32> <i32 0, i32 5, i32 25, i32 29, i32 2, i32 6, i32 26, i32 30, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %54 = add nsw <16 x i32> %50, %52
  %55 = sub nsw <16 x i32> %51, %53
  %56 = shufflevector <16 x i32> %54, <16 x i32> %55, <16 x i32> <i32 0, i32 16, i32 17, i32 1, i32 18, i32 2, i32 19, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %57 = shufflevector <16 x i32> %54, <16 x i32> %55, <16 x i32> <i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %58 = shufflevector <16 x i32> %54, <16 x i32> %55, <16 x i32> <i32 4, i32 20, i32 21, i32 5, i32 22, i32 6, i32 23, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %59 = shufflevector <16 x i32> %54, <16 x i32> %55, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %60 = add nsw <16 x i32> %56, %58
  %61 = sub nsw <16 x i32> %57, %59
  %62 = shufflevector <16 x i32> %60, <16 x i32> %61, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
  %63 = lshr <16 x i32> %62, <i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15>
  %64 = and <16 x i32> %63, <i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537>
  %65 = mul nuw <16 x i32> %64, <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
  %66 = add <16 x i32> %65, %62
  %67 = xor <16 x i32> %66, %65
  %68 = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %67)
  %conv118 = and i32 %68, 65535
  %shr = lshr i32 %68, 16
  %add119 = add nuw nsw i32 %conv118, %shr
  %shr120 = lshr i32 %add119, 1
  ret i32 %shr120
}


define i32 @v3(ptr nocapture noundef readonly %p1, i32 noundef %i1, ptr nocapture noundef readonly %p2, i32 noundef %i2) {
; CHECK-LABEL: v3:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    // kill: def $w3 killed $w3 def $x3
; CHECK-NEXT:    // kill: def $w1 killed $w1 def $x1
; CHECK-NEXT:    sxtw x8, w1
; CHECK-NEXT:    sxtw x9, w3
; CHECK-NEXT:    ldr d0, [x0]
; CHECK-NEXT:    ldr d1, [x2]
; CHECK-NEXT:    add x10, x0, x8
; CHECK-NEXT:    add x11, x2, x9
; CHECK-NEXT:    ldr d2, [x10]
; CHECK-NEXT:    ldr d3, [x11]
; CHECK-NEXT:    usubl v0.8h, v0.8b, v1.8b
; CHECK-NEXT:    add x10, x10, x8
; CHECK-NEXT:    add x11, x11, x9
; CHECK-NEXT:    usubl v1.8h, v2.8b, v3.8b
; CHECK-NEXT:    ldr d2, [x10, x8]
; CHECK-NEXT:    ldr d3, [x11, x9]
; CHECK-NEXT:    ldr d4, [x10]
; CHECK-NEXT:    ldr d5, [x11]
; CHECK-NEXT:    usubl v2.8h, v2.8b, v3.8b
; CHECK-NEXT:    usubl v3.8h, v4.8b, v5.8b
; CHECK-NEXT:    shll2 v4.4s, v0.8h, #16
; CHECK-NEXT:    shll2 v5.4s, v1.8h, #16
; CHECK-NEXT:    saddw v0.4s, v4.4s, v0.4h
; CHECK-NEXT:    shll2 v4.4s, v2.8h, #16
; CHECK-NEXT:    saddw v1.4s, v5.4s, v1.4h
; CHECK-NEXT:    shll2 v5.4s, v3.8h, #16
; CHECK-NEXT:    saddw v2.4s, v4.4s, v2.4h
; CHECK-NEXT:    saddw v3.4s, v5.4s, v3.4h
; CHECK-NEXT:    rev64 v4.4s, v0.4s
; CHECK-NEXT:    rev64 v5.4s, v1.4s
; CHECK-NEXT:    rev64 v6.4s, v2.4s
; CHECK-NEXT:    rev64 v7.4s, v3.4s
; CHECK-NEXT:    sub v4.4s, v0.4s, v4.4s
; CHECK-NEXT:    addp v0.4s, v1.4s, v0.4s
; CHECK-NEXT:    sub v5.4s, v1.4s, v5.4s
; CHECK-NEXT:    sub v6.4s, v2.4s, v6.4s
; CHECK-NEXT:    addp v2.4s, v2.4s, v3.4s
; CHECK-NEXT:    sub v1.4s, v3.4s, v7.4s
; CHECK-NEXT:    ext v3.16b, v0.16b, v0.16b, #8
; CHECK-NEXT:    ext v7.16b, v5.16b, v4.16b, #4
; CHECK-NEXT:    mov v4.s[3], v5.s[2]
; CHECK-NEXT:    zip2 v16.4s, v6.4s, v1.4s
; CHECK-NEXT:    zip1 v1.4s, v6.4s, v1.4s
; CHECK-NEXT:    uzp2 v6.4s, v2.4s, v0.4s
; CHECK-NEXT:    ext v5.16b, v7.16b, v5.16b, #4
; CHECK-NEXT:    uzp1 v0.4s, v2.4s, v0.4s
; CHECK-NEXT:    uzp1 v7.4s, v2.4s, v3.4s
; CHECK-NEXT:    uzp2 v2.4s, v2.4s, v3.4s
; CHECK-NEXT:    mov v16.d[1], v4.d[1]
; CHECK-NEXT:    rev64 v3.4s, v6.4s
; CHECK-NEXT:    mov v1.d[1], v5.d[1]
; CHECK-NEXT:    rev64 v0.4s, v0.4s
; CHECK-NEXT:    sub v2.4s, v7.4s, v2.4s
; CHECK-NEXT:    sub v4.4s, v1.4s, v16.4s
; CHECK-NEXT:    add v0.4s, v3.4s, v0.4s
; CHECK-NEXT:    add v1.4s, v16.4s, v1.4s
; CHECK-NEXT:    zip1 v3.4s, v2.4s, v4.4s
; CHECK-NEXT:    zip1 v5.4s, v0.4s, v1.4s
; CHECK-NEXT:    uzp2 v6.4s, v0.4s, v1.4s
; CHECK-NEXT:    zip2 v7.4s, v0.4s, v1.4s
; CHECK-NEXT:    zip2 v17.4s, v2.4s, v4.4s
; CHECK-NEXT:    ext v16.16b, v2.16b, v3.16b, #8
; CHECK-NEXT:    trn2 v5.4s, v0.4s, v5.4s
; CHECK-NEXT:    uzp2 v6.4s, v6.4s, v0.4s
; CHECK-NEXT:    mov v2.s[3], v4.s[2]
; CHECK-NEXT:    mov v0.s[1], v1.s[1]
; CHECK-NEXT:    mov v5.d[1], v16.d[1]
; CHECK-NEXT:    mov v6.d[1], v17.d[1]
; CHECK-NEXT:    mov v7.d[1], v2.d[1]
; CHECK-NEXT:    mov v0.d[1], v3.d[1]
; CHECK-NEXT:    add v1.4s, v6.4s, v7.4s
; CHECK-NEXT:    sub v2.4s, v7.4s, v6.4s
; CHECK-NEXT:    add v3.4s, v5.4s, v0.4s
; CHECK-NEXT:    sub v0.4s, v0.4s, v5.4s
; CHECK-NEXT:    zip2 v4.4s, v1.4s, v2.4s
; CHECK-NEXT:    ext v5.16b, v1.16b, v1.16b, #4
; CHECK-NEXT:    ext v6.16b, v3.16b, v3.16b, #4
; CHECK-NEXT:    zip2 v7.4s, v2.4s, v1.4s
; CHECK-NEXT:    zip2 v16.4s, v0.4s, v3.4s
; CHECK-NEXT:    zip2 v17.4s, v3.4s, v0.4s
; CHECK-NEXT:    zip1 v1.4s, v1.4s, v2.4s
; CHECK-NEXT:    ext v2.16b, v5.16b, v2.16b, #8
; CHECK-NEXT:    ext v18.16b, v6.16b, v0.16b, #8
; CHECK-NEXT:    zip1 v0.4s, v3.4s, v0.4s
; CHECK-NEXT:    add v3.4s, v16.4s, v7.4s
; CHECK-NEXT:    sub v4.4s, v4.4s, v17.4s
; CHECK-NEXT:    ext v2.16b, v2.16b, v5.16b, #4
; CHECK-NEXT:    ext v5.16b, v18.16b, v6.16b, #4
; CHECK-NEXT:    sub v0.4s, v1.4s, v0.4s
; CHECK-NEXT:    cmlt v1.8h, v4.8h, #0
; CHECK-NEXT:    cmlt v6.8h, v3.8h, #0
; CHECK-NEXT:    add v3.4s, v6.4s, v3.4s
; CHECK-NEXT:    add v4.4s, v1.4s, v4.4s
; CHECK-NEXT:    add v2.4s, v5.4s, v2.4s
; CHECK-NEXT:    cmlt v5.8h, v0.8h, #0
; CHECK-NEXT:    add v0.4s, v5.4s, v0.4s
; CHECK-NEXT:    eor v1.16b, v4.16b, v1.16b
; CHECK-NEXT:    eor v3.16b, v3.16b, v6.16b
; CHECK-NEXT:    cmlt v4.8h, v2.8h, #0
; CHECK-NEXT:    add v1.4s, v3.4s, v1.4s
; CHECK-NEXT:    add v2.4s, v4.4s, v2.4s
; CHECK-NEXT:    eor v0.16b, v0.16b, v5.16b
; CHECK-NEXT:    add v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    eor v1.16b, v2.16b, v4.16b
; CHECK-NEXT:    add v0.4s, v1.4s, v0.4s
; CHECK-NEXT:    addv s0, v0.4s
; CHECK-NEXT:    fmov w8, s0
; CHECK-NEXT:    lsr w9, w8, #16
; CHECK-NEXT:    add w8, w9, w8, uxth
; CHECK-NEXT:    lsr w0, w8, #1
; CHECK-NEXT:    ret
entry:
  %idx.ext = sext i32 %i1 to i64
  %idx.ext63 = sext i32 %i2 to i64
  %arrayidx3 = getelementptr inbounds i8, ptr %p1, i64 4
  %arrayidx5 = getelementptr inbounds i8, ptr %p2, i64 4
  %add.ptr = getelementptr inbounds i8, ptr %p1, i64 %idx.ext
  %add.ptr64 = getelementptr inbounds i8, ptr %p2, i64 %idx.ext63
  %arrayidx3.1 = getelementptr inbounds i8, ptr %add.ptr, i64 4
  %arrayidx5.1 = getelementptr inbounds i8, ptr %add.ptr64, i64 4
  %add.ptr.1 = getelementptr inbounds i8, ptr %add.ptr, i64 %idx.ext
  %add.ptr64.1 = getelementptr inbounds i8, ptr %add.ptr64, i64 %idx.ext63
  %arrayidx3.2 = getelementptr inbounds i8, ptr %add.ptr.1, i64 4
  %arrayidx5.2 = getelementptr inbounds i8, ptr %add.ptr64.1, i64 4
  %add.ptr.2 = getelementptr inbounds i8, ptr %add.ptr.1, i64 %idx.ext
  %add.ptr64.2 = getelementptr inbounds i8, ptr %add.ptr64.1, i64 %idx.ext63
  %arrayidx3.3 = getelementptr inbounds i8, ptr %add.ptr.2, i64 4
  %arrayidx5.3 = getelementptr inbounds i8, ptr %add.ptr64.2, i64 4
  %0 = load <4 x i8>, ptr %p1, align 1
  %1 = load <4 x i8>, ptr %p2, align 1
  %2 = load <4 x i8>, ptr %arrayidx3, align 1
  %3 = load <4 x i8>, ptr %arrayidx5, align 1
  %4 = load <4 x i8>, ptr %add.ptr, align 1
  %5 = load <4 x i8>, ptr %add.ptr64, align 1
  %6 = load <4 x i8>, ptr %arrayidx3.1, align 1
  %7 = load <4 x i8>, ptr %arrayidx5.1, align 1
  %8 = load <4 x i8>, ptr %add.ptr.1, align 1
  %9 = load <4 x i8>, ptr %add.ptr64.1, align 1
  %10 = load <4 x i8>, ptr %arrayidx3.2, align 1
  %11 = load <4 x i8>, ptr %arrayidx5.2, align 1
  %12 = load <4 x i8>, ptr %add.ptr.2, align 1
  %13 = shufflevector <4 x i8> %12, <4 x i8> %8, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %14 = shufflevector <4 x i8> %4, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %15 = shufflevector <16 x i8> %13, <16 x i8> %14, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 undef, i32 undef, i32 undef, i32 undef>
  %16 = shufflevector <4 x i8> %0, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %17 = shufflevector <16 x i8> %15, <16 x i8> %16, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
  %18 = zext <16 x i8> %17 to <16 x i32>
  %19 = load <4 x i8>, ptr %add.ptr64.2, align 1
  %20 = shufflevector <4 x i8> %19, <4 x i8> %9, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %21 = shufflevector <4 x i8> %5, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %22 = shufflevector <16 x i8> %20, <16 x i8> %21, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 undef, i32 undef, i32 undef, i32 undef>
  %23 = shufflevector <4 x i8> %1, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %24 = shufflevector <16 x i8> %22, <16 x i8> %23, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
  %25 = zext <16 x i8> %24 to <16 x i32>
  %26 = sub nsw <16 x i32> %18, %25
  %27 = load <4 x i8>, ptr %arrayidx3.3, align 1
  %28 = shufflevector <4 x i8> %27, <4 x i8> %10, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %29 = shufflevector <4 x i8> %6, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %30 = shufflevector <16 x i8> %28, <16 x i8> %29, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 undef, i32 undef, i32 undef, i32 undef>
  %31 = shufflevector <4 x i8> %2, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %32 = shufflevector <16 x i8> %30, <16 x i8> %31, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
  %33 = zext <16 x i8> %32 to <16 x i32>
  %34 = load <4 x i8>, ptr %arrayidx5.3, align 1
  %35 = shufflevector <4 x i8> %34, <4 x i8> %11, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %36 = shufflevector <4 x i8> %7, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %37 = shufflevector <16 x i8> %35, <16 x i8> %36, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 undef, i32 undef, i32 undef, i32 undef>
  %38 = shufflevector <4 x i8> %3, <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %39 = shufflevector <16 x i8> %37, <16 x i8> %38, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
  %40 = zext <16 x i8> %39 to <16 x i32>
  %41 = sub nsw <16 x i32> %33, %40
  %42 = shl nsw <16 x i32> %41, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
  %43 = add nsw <16 x i32> %42, %26
  %reorder = shufflevector <16 x i32> %43, <16 x i32> poison, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
  %44 = add nsw <16 x i32> %43, %reorder
  %45 = sub nsw <16 x i32> %43, %reorder
  %46 = shufflevector <16 x i32> %44, <16 x i32> %45, <16 x i32> <i32 7, i32 3, i32 15, i32 11, i32 18, i32 22, i32 30, i32 26, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %47 = shufflevector <16 x i32> %44, <16 x i32> %45, <16 x i32> <i32 1, i32 5, i32 13, i32 9, i32 16, i32 20, i32 28, i32 24, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %48 = shufflevector <16 x i32> %44, <16 x i32> %45, <16 x i32> <i32 5, i32 1, i32 13, i32 9, i32 16, i32 20, i32 28, i32 24, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %49 = shufflevector <16 x i32> %44, <16 x i32> %45, <16 x i32> <i32 3, i32 7, i32 15, i32 11, i32 18, i32 22, i32 30, i32 26, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %50 = add nsw <16 x i32> %46, %48
  %51 = sub nsw <16 x i32> %47, %49
  %52 = shufflevector <16 x i32> %50, <16 x i32> %51, <16 x i32> <i32 1, i32 4, i32 16, i32 20, i32 3, i32 7, i32 19, i32 23, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %53 = shufflevector <16 x i32> %50, <16 x i32> %51, <16 x i32> <i32 0, i32 5, i32 17, i32 21, i32 2, i32 6, i32 18, i32 22, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %54 = shufflevector <16 x i32> %50, <16 x i32> %51, <16 x i32> <i32 0, i32 5, i32 17, i32 21, i32 2, i32 6, i32 18, i32 22, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %55 = shufflevector <16 x i32> %50, <16 x i32> %51, <16 x i32> <i32 1, i32 4, i32 16, i32 20, i32 3, i32 7, i32 19, i32 23, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %56 = add nsw <16 x i32> %52, %54
  %57 = sub nsw <16 x i32> %53, %55
  %58 = shufflevector <16 x i32> %56, <16 x i32> %57, <16 x i32> <i32 0, i32 16, i32 17, i32 1, i32 18, i32 2, i32 19, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %59 = shufflevector <16 x i32> %56, <16 x i32> %57, <16 x i32> <i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %60 = shufflevector <16 x i32> %56, <16 x i32> %57, <16 x i32> <i32 4, i32 20, i32 21, i32 5, i32 22, i32 6, i32 23, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %61 = shufflevector <16 x i32> %56, <16 x i32> %57, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %62 = add nsw <16 x i32> %58, %60
  %63 = sub nsw <16 x i32> %59, %61
  %64 = shufflevector <16 x i32> %62, <16 x i32> %63, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
  %65 = lshr <16 x i32> %64, <i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15>
  %66 = and <16 x i32> %65, <i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537>
  %67 = mul nuw <16 x i32> %66, <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
  %68 = add <16 x i32> %67, %64
  %69 = xor <16 x i32> %68, %67
  %70 = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %69)
  %conv118 = and i32 %70, 65535
  %shr = lshr i32 %70, 16
  %add119 = add nuw nsw i32 %conv118, %shr
  %shr120 = lshr i32 %add119, 1
  ret i32 %shr120
}

declare i32 @llvm.vector.reduce.add.v16i32(<16 x i32>)