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

define void @test(i32* %p1, i32* %p2) {
; CHECK-LABEL: test:
; CHECK:       // %bb.0:
; CHECK-NEXT:    mov w8, #3
; CHECK-NEXT:    mov w9, #1
; CHECK-NEXT:    str w8, [x0]
; CHECK-NEXT:    str w9, [x1]
; CHECK-NEXT:    ret
  %tmp = shufflevector <1 x i32> <i32 1>, <1 x i32> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
  %tmp2 = shufflevector <3 x i32> <i32 2, i32 3, i32 4>, <3 x i32> %tmp, <3 x i32> <i32 0, i32 1, i32 3>
  %tmp3 = shufflevector <3 x i32> %tmp2, <3 x i32> undef, <6 x i32> <i32 0, i32 1, i32 2, i32 undef, i32 undef, i32 undef>
  %tmp4 = shufflevector <6 x i32> undef, <6 x i32> %tmp3, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
  %tmp6 = extractelement <9 x i32> %tmp4, i32 7
  %tmp8 = extractelement <9 x i32> %tmp4, i32 8
  store i32 %tmp6, i32* %p1, align 4
  store i32 %tmp8, i32* %p2, align 4
  ret void
}

; Test case from PR41951
define <4 x i32> @widen_shuffles_reduced(<3 x i32> %x, <3 x i32> %y) {
; CHECK-LABEL: widen_shuffles_reduced:
; CHECK:       // %bb.0:
; CHECK-NEXT:    zip1 v2.4s, v0.4s, v1.4s
; CHECK-NEXT:    zip1 v0.4s, v1.4s, v0.4s
; CHECK-NEXT:    ext v0.16b, v0.16b, v2.16b, #8
; CHECK-NEXT:    ret
  %s3 = shufflevector <3 x i32> %y, <3 x i32> %x, <4 x i32> <i32 1, i32 4, i32 3, i32 0>
  ret <4 x i32> %s3
}

define void @zip_mask_check(<3 x float>* %p1, <3 x float>* %p2, i32* %p3) {
; CHECK-LABEL: zip_mask_check:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ldr q0, [x0]
; CHECK-NEXT:    ldr d1, [x1]
; CHECK-NEXT:    trn2 v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    fmla v0.4s, v0.4s, v0.4s
; CHECK-NEXT:    fmla v0.4s, v0.4s, v0.4s
; CHECK-NEXT:    str s0, [x2]
; CHECK-NEXT:    ret
  %tmp3 = load <3 x float>, <3 x float>* %p1, align 16
  %tmp4 = load <3 x float>, <3 x float>* %p2, align 4
  %tmp5 = shufflevector <3 x float> %tmp3, <3 x float> %tmp4, <4 x i32> <i32 1, i32 4, i32 undef, i32 undef>
  %tmp6 = shufflevector <4 x float> %tmp5, <4 x float> undef, <4 x i32> <i32 0, i32 1, i32 5, i32 undef>
  %tmp7 = shufflevector <4 x float> %tmp6, <4 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 5>
  %tmp8 = call <4 x float> @llvm.fma.v4f32(<4 x float> %tmp7, <4 x float> undef, <4 x float> undef)
  %tmp9 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> %tmp8)
  %tmp10 = shufflevector <4 x float> %tmp9, <4 x float> undef, <16 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %tmp11 = bitcast <16 x float> %tmp10 to <16 x i32>
  %tmp12 = extractelement <16 x i32> %tmp11, i32 0
  store i32 %tmp12, i32* %p3, align 4
  ret void
}

declare <4 x float> @llvm.fma.v4f32(<4 x float>, <4 x float>, <4 x float>) #1