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

; TODO: ldp don't support r+r, we need to avoid lsr optimize this pattern
define void @convolution(ptr %src0, ptr %src1, i64 %stride_xm, i64 %stride_xp, ptr %dst, i32 %w) {
; CHECK-LABEL: convolution:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    mov x8, xzr
; CHECK-NEXT:    add x9, x1, x3
; CHECK-NEXT:    add x10, x1, x2
; CHECK-NEXT:    add x11, x0, x2
; CHECK-NEXT:    add x12, x0, x3
; CHECK-NEXT:  .LBB0_1: // %do.body
; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr q0, [x11, x8]
; CHECK-NEXT:    add x13, x0, x8
; CHECK-NEXT:    ldr q1, [x12, x8]
; CHECK-NEXT:    add x14, x1, x8
; CHECK-NEXT:    ldr q4, [x10, x8]
; CHECK-NEXT:    subs w5, w5, #1
; CHECK-NEXT:    ldp q2, q3, [x13]
; CHECK-NEXT:    fadd v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    ldp q6, q1, [x14]
; CHECK-NEXT:    fadd v2.4s, v2.4s, v3.4s
; CHECK-NEXT:    fadd v0.4s, v0.4s, v2.4s
; CHECK-NEXT:    ldr q5, [x9, x8]
; CHECK-NEXT:    add x8, x8, #32
; CHECK-NEXT:    fadd v1.4s, v6.4s, v1.4s
; CHECK-NEXT:    fadd v3.4s, v4.4s, v5.4s
; CHECK-NEXT:    fadd v1.4s, v3.4s, v1.4s
; CHECK-NEXT:    fadd v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    str q0, [x4], #16
; CHECK-NEXT:    b.ne .LBB0_1
; CHECK-NEXT:  // %bb.2: // %do.end
; CHECK-NEXT:    ret
entry:
  br label %do.body

do.body:
  %dst.addr.0 = phi ptr [ %dst, %entry ], [ %incdec.ptr, %do.body ]
  %src1.addr.0 = phi ptr [ %src1, %entry ], [ %incdec.ptr2.i7, %do.body ]
  %src0.addr.0 = phi ptr [ %src0, %entry ], [ %incdec.ptr2.i, %do.body ]
  %w.addr.0 = phi i32 [ %w, %entry ], [ %dec, %do.body ]
  %add.ptr.i = getelementptr inbounds i8, ptr %src0.addr.0, i64 %stride_xm
  %0 = load <4 x float>, ptr %add.ptr.i, align 16
  %add.ptr1.i = getelementptr inbounds i8, ptr %src0.addr.0, i64 %stride_xp
  %1 = load <4 x float>, ptr %add.ptr1.i, align 16
  %incdec.ptr.i = getelementptr inbounds <4 x float>, ptr %src0.addr.0, i64 1
  %2 = load <4 x float>, ptr %src0.addr.0, align 16
  %incdec.ptr2.i = getelementptr inbounds <4 x float>, ptr %src0.addr.0, i64 2
  %3 = load <4 x float>, ptr %incdec.ptr.i, align 16
  %add.i = fadd <4 x float> %0, %1
  %add3.i = fadd <4 x float> %2, %3
  %add4.i = fadd <4 x float> %add.i, %add3.i
  %add.ptr.i4 = getelementptr inbounds i8, ptr %src1.addr.0, i64 %stride_xm
  %4 = load <4 x float>, ptr %add.ptr.i4, align 16
  %add.ptr1.i5 = getelementptr inbounds i8, ptr %src1.addr.0, i64 %stride_xp
  %5 = load <4 x float>, ptr %add.ptr1.i5, align 16
  %incdec.ptr.i6 = getelementptr inbounds <4 x float>, ptr %src1.addr.0, i64 1
  %6 = load <4 x float>, ptr %src1.addr.0, align 16
  %incdec.ptr2.i7 = getelementptr inbounds <4 x float>, ptr %src1.addr.0, i64 2
  %7 = load <4 x float>, ptr %incdec.ptr.i6, align 16
  %add.i8 = fadd <4 x float> %4, %5
  %add3.i9 = fadd <4 x float> %6, %7
  %add4.i10 = fadd <4 x float> %add.i8, %add3.i9
  %add = fadd <4 x float> %add4.i, %add4.i10
  %incdec.ptr = getelementptr inbounds <4 x float>, ptr %dst.addr.0, i64 1
  store <4 x float> %add, ptr %dst.addr.0, align 16
  %dec = add nsw i32 %w.addr.0, -1
  %tobool.not = icmp eq i32 %dec, 0
  br i1 %tobool.not, label %do.end, label %do.body

do.end:
  ret void
}