llvm/llvm/test/CodeGen/AArch64/complex-deinterleaving-i32-add-scalable.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s --mattr=+sve2 -o - | FileCheck %s

target triple = "aarch64"

; Expected to transform
define <vscale x 4 x i32> @complex_add_v4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: complex_add_v4i32:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cadd z1.s, z1.s, z0.s, #90
; CHECK-NEXT:    mov z0.d, z1.d
; CHECK-NEXT:    ret
entry:
  %a.deinterleaved = tail call { <vscale x 2 x i32>, <vscale x 2 x i32> } @llvm.vector.deinterleave2.nxv4i32(<vscale x 4 x i32> %a)
  %a.real = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } %a.deinterleaved, 0
  %a.imag = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } %a.deinterleaved, 1
  %b.deinterleaved = tail call { <vscale x 2 x i32>, <vscale x 2 x i32> } @llvm.vector.deinterleave2.nxv4i32(<vscale x 4 x i32> %b)
  %b.real = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } %b.deinterleaved, 0
  %b.imag = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } %b.deinterleaved, 1
  %0 = sub <vscale x 2 x i32> %b.real, %a.imag
  %1 = add <vscale x 2 x i32> %b.imag, %a.real
  %interleaved.vec = tail call <vscale x 4 x i32> @llvm.vector.interleave2.nxv4i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1)
  ret <vscale x 4 x i32> %interleaved.vec
}

; Expected to transform
define <vscale x 8 x i32> @complex_add_v8i32(<vscale x 8 x i32> %a, <vscale x 8 x i32> %b) {
; CHECK-LABEL: complex_add_v8i32:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cadd z3.s, z3.s, z1.s, #90
; CHECK-NEXT:    cadd z2.s, z2.s, z0.s, #90
; CHECK-NEXT:    mov z0.d, z2.d
; CHECK-NEXT:    mov z1.d, z3.d
; CHECK-NEXT:    ret
entry:
  %a.deinterleaved = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %a)
  %a.real = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %a.deinterleaved, 0
  %a.imag = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %a.deinterleaved, 1
  %b.deinterleaved = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %b)
  %b.real = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %b.deinterleaved, 0
  %b.imag = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %b.deinterleaved, 1
  %0 = sub <vscale x 4 x i32> %b.real, %a.imag
  %1 = add <vscale x 4 x i32> %b.imag, %a.real
  %interleaved.vec = tail call <vscale x 8 x i32> @llvm.vector.interleave2.nxv8i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1)
  ret <vscale x 8 x i32> %interleaved.vec
}

; Expected to transform
define <vscale x 16 x i32> @complex_add_v16i32(<vscale x 16 x i32> %a, <vscale x 16 x i32> %b) {
; CHECK-LABEL: complex_add_v16i32:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    cadd z6.s, z6.s, z2.s, #90
; CHECK-NEXT:    cadd z4.s, z4.s, z0.s, #90
; CHECK-NEXT:    cadd z5.s, z5.s, z1.s, #90
; CHECK-NEXT:    cadd z7.s, z7.s, z3.s, #90
; CHECK-NEXT:    mov z0.d, z4.d
; CHECK-NEXT:    mov z1.d, z5.d
; CHECK-NEXT:    mov z2.d, z6.d
; CHECK-NEXT:    mov z3.d, z7.d
; CHECK-NEXT:    ret
entry:
  %a.deinterleaved = tail call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> %a)
  %a.real = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %a.deinterleaved, 0
  %a.imag = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %a.deinterleaved, 1
  %b.deinterleaved = tail call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> %b)
  %b.real = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %b.deinterleaved, 0
  %b.imag = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %b.deinterleaved, 1
  %0 = sub <vscale x 8 x i32> %b.real, %a.imag
  %1 = add <vscale x 8 x i32> %b.imag, %a.real
  %interleaved.vec = tail call <vscale x 16 x i32> @llvm.vector.interleave2.nxv16i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1)
  ret <vscale x 16 x i32> %interleaved.vec
}

declare { <vscale x 2 x i32>, <vscale x 2 x i32> } @llvm.vector.deinterleave2.nxv4i32(<vscale x 4 x i32>)
declare <vscale x 4 x i32> @llvm.vector.interleave2.nxv4i32(<vscale x 2 x i32>, <vscale x 2 x i32>)

declare { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32>)
declare <vscale x 8 x i32> @llvm.vector.interleave2.nxv8i32(<vscale x 4 x i32>, <vscale x 4 x i32>)

declare { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32>)
declare <vscale x 16 x i32> @llvm.vector.interleave2.nxv16i32(<vscale x 8 x i32>, <vscale x 8 x i32>)