; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s --mattr=+complxnum,+neon,+fullfp16 -o - | FileCheck %s
; RUN: llc < %s --mattr=+complxnum,+neon,+fullfp16,+sve -o - | FileCheck %s
; RUN: llc < %s --mattr=+complxnum,+neon,+fullfp16,+sve2 -o - | FileCheck %s

target triple = "aarch64"

; Expected to not transform
define <2 x half> @complex_add_v2f16(<2 x half> %a, <2 x half> %b) {
; CHECK-LABEL: complex_add_v2f16:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    mov h2, v0.h[1]
; CHECK-NEXT:    mov h3, v1.h[1]
; CHECK-NEXT:    fsub h1, h1, h2
; CHECK-NEXT:    fadd h0, h3, h0
; CHECK-NEXT:    mov v1.h[1], v0.h[0]
; CHECK-NEXT:    fmov d0, d1
; CHECK-NEXT:    ret
entry:
  %a.real = shufflevector <2 x half> %a, <2 x half> zeroinitializer, <1 x i32> <i32 0>
  %a.imag = shufflevector <2 x half> %a, <2 x half> zeroinitializer, <1 x i32> <i32 1>
  %b.real = shufflevector <2 x half> %b, <2 x half> zeroinitializer, <1 x i32> <i32 0>
  %b.imag = shufflevector <2 x half> %b, <2 x half> zeroinitializer, <1 x i32> <i32 1>
  %0 = fsub fast <1 x half> %b.real, %a.imag
  %1 = fadd fast <1 x half> %b.imag, %a.real
  %interleaved.vec = shufflevector <1 x half> %0, <1 x half> %1, <2 x i32> <i32 0, i32 1>
  ret <2 x half> %interleaved.vec
}

; Expected to transform
define <4 x half> @complex_add_v4f16(<4 x half> %a, <4 x half> %b) {
; CHECK-LABEL: complex_add_v4f16:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    fcadd v0.4h, v1.4h, v0.4h, #90
; CHECK-NEXT:    ret
entry:
  %a.real = shufflevector <4 x half> %a, <4 x half> zeroinitializer, <2 x i32> <i32 0, i32 2>
  %a.imag = shufflevector <4 x half> %a, <4 x half> zeroinitializer, <2 x i32> <i32 1, i32 3>
  %b.real = shufflevector <4 x half> %b, <4 x half> zeroinitializer, <2 x i32> <i32 0, i32 2>
  %b.imag = shufflevector <4 x half> %b, <4 x half> zeroinitializer, <2 x i32> <i32 1, i32 3>
  %0 = fsub fast <2 x half> %b.real, %a.imag
  %1 = fadd fast <2 x half> %b.imag, %a.real
  %interleaved.vec = shufflevector <2 x half> %0, <2 x half> %1, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
  ret <4 x half> %interleaved.vec
}

; Expected to transform
define <8 x half> @complex_add_v8f16(<8 x half> %a, <8 x half> %b) {
; CHECK-LABEL: complex_add_v8f16:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    fcadd v0.8h, v1.8h, v0.8h, #90
; CHECK-NEXT:    ret
entry:
  %a.real = shufflevector <8 x half> %a, <8 x half> zeroinitializer, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
  %a.imag = shufflevector <8 x half> %a, <8 x half> zeroinitializer, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
  %b.real = shufflevector <8 x half> %b, <8 x half> zeroinitializer, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
  %b.imag = shufflevector <8 x half> %b, <8 x half> zeroinitializer, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
  %0 = fsub fast <4 x half> %b.real, %a.imag
  %1 = fadd fast <4 x half> %b.imag, %a.real
  %interleaved.vec = shufflevector <4 x half> %0, <4 x half> %1, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
  ret <8 x half> %interleaved.vec
}

; Expected to transform
define <16 x half> @complex_add_v16f16(<16 x half> %a, <16 x half> %b) {
; CHECK-LABEL: complex_add_v16f16:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    fcadd v1.8h, v3.8h, v1.8h, #90
; CHECK-NEXT:    fcadd v0.8h, v2.8h, v0.8h, #90
; CHECK-NEXT:    ret
entry:
  %a.real = shufflevector <16 x half> %a, <16 x half> zeroinitializer, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
  %a.imag = shufflevector <16 x half> %a, <16 x half> zeroinitializer, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
  %b.real = shufflevector <16 x half> %b, <16 x half> zeroinitializer, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
  %b.imag = shufflevector <16 x half> %b, <16 x half> zeroinitializer, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
  %0 = fsub fast <8 x half> %b.real, %a.imag
  %1 = fadd fast <8 x half> %b.imag, %a.real
  %interleaved.vec = shufflevector <8 x half> %0, <8 x half> %1, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
  ret <16 x half> %interleaved.vec
}

; Expected to transform
define <32 x half> @complex_add_v32f16(<32 x half> %a, <32 x half> %b) {
; CHECK-LABEL: complex_add_v32f16:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    fcadd v2.8h, v6.8h, v2.8h, #90
; CHECK-NEXT:    fcadd v0.8h, v4.8h, v0.8h, #90
; CHECK-NEXT:    fcadd v1.8h, v5.8h, v1.8h, #90
; CHECK-NEXT:    fcadd v3.8h, v7.8h, v3.8h, #90
; CHECK-NEXT:    ret
entry:
  %a.real = shufflevector <32 x half> %a, <32 x half> zeroinitializer, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
  %a.imag = shufflevector <32 x half> %a, <32 x half> zeroinitializer, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
  %b.real = shufflevector <32 x half> %b, <32 x half> zeroinitializer, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
  %b.imag = shufflevector <32 x half> %b, <32 x half> zeroinitializer, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
  %0 = fsub fast <16 x half> %b.real, %a.imag
  %1 = fadd fast <16 x half> %b.imag, %a.real
  %interleaved.vec = shufflevector <16 x half> %0, <16 x half> %1, <32 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
  ret <32 x half> %interleaved.vec
}

; Expected to transform
define <4 x half> @complex_add_v4f16_with_intrinsic(<4 x half> %a, <4 x half> %b) {
; CHECK-LABEL: complex_add_v4f16_with_intrinsic:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    fcadd v0.4h, v1.4h, v0.4h, #90
; CHECK-NEXT:    ret
entry:
  %a.deinterleaved = tail call { <2 x half>, <2 x half> } @llvm.experimental.vector.deinterleave2.v4f16(<4 x half> %a)
  %a.real = extractvalue { <2 x half>, <2 x half> } %a.deinterleaved, 0
  %a.imag = extractvalue { <2 x half>, <2 x half> } %a.deinterleaved, 1
  %b.deinterleaved = tail call { <2 x half>, <2 x half> } @llvm.experimental.vector.deinterleave2.v4f16(<4 x half> %b)
  %b.real = extractvalue { <2 x half>, <2 x half> } %b.deinterleaved, 0
  %b.imag = extractvalue { <2 x half>, <2 x half> } %b.deinterleaved, 1
  %0 = fsub fast <2 x half> %b.real, %a.imag
  %1 = fadd fast <2 x half> %b.imag, %a.real
  %interleaved.vec = tail call <4 x half> @llvm.experimental.vector.interleave2.v4f16(<2 x half> %0, <2 x half> %1)
  ret <4 x half> %interleaved.vec
}

; Expected to transform
define <8 x half> @complex_add_v8f16_with_intrinsic(<8 x half> %a, <8 x half> %b) {
; CHECK-LABEL: complex_add_v8f16_with_intrinsic:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    fcadd v0.8h, v1.8h, v0.8h, #90
; CHECK-NEXT:    ret
entry:
  %a.deinterleaved = tail call { <4 x half>, <4 x half> } @llvm.experimental.vector.deinterleave2.v8f16(<8 x half> %a)
  %a.real = extractvalue { <4 x half>, <4 x half> } %a.deinterleaved, 0
  %a.imag = extractvalue { <4 x half>, <4 x half> } %a.deinterleaved, 1
  %b.deinterleaved = tail call { <4 x half>, <4 x half> } @llvm.experimental.vector.deinterleave2.v8f16(<8 x half> %b)
  %b.real = extractvalue { <4 x half>, <4 x half> } %b.deinterleaved, 0
  %b.imag = extractvalue { <4 x half>, <4 x half> } %b.deinterleaved, 1
  %0 = fsub fast <4 x half> %b.real, %a.imag
  %1 = fadd fast <4 x half> %b.imag, %a.real
  %interleaved.vec = tail call <8 x half> @llvm.experimental.vector.interleave2.v8f16(<4 x half> %0, <4 x half> %1)
  ret <8 x half> %interleaved.vec
}

; Expected to transform
define <16 x half> @complex_add_v16f16_with_intrinsic(<16 x half> %a, <16 x half> %b) {
; CHECK-LABEL: complex_add_v16f16_with_intrinsic:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    fcadd v1.8h, v3.8h, v1.8h, #90
; CHECK-NEXT:    fcadd v0.8h, v2.8h, v0.8h, #90
; CHECK-NEXT:    ret
entry:
  %a.deinterleaved = tail call { <8 x half>, <8 x half> } @llvm.experimental.vector.deinterleave2.v16f16(<16 x half> %a)
  %a.real = extractvalue { <8 x half>, <8 x half> } %a.deinterleaved, 0
  %a.imag = extractvalue { <8 x half>, <8 x half> } %a.deinterleaved, 1
  %b.deinterleaved = tail call { <8 x half>, <8 x half> } @llvm.experimental.vector.deinterleave2.v16f16(<16 x half> %b)
  %b.real = extractvalue { <8 x half>, <8 x half> } %b.deinterleaved, 0
  %b.imag = extractvalue { <8 x half>, <8 x half> } %b.deinterleaved, 1
  %0 = fsub fast <8 x half> %b.real, %a.imag
  %1 = fadd fast <8 x half> %b.imag, %a.real
  %interleaved.vec = tail call <16 x half> @llvm.experimental.vector.interleave2.v16f16(<8 x half> %0, <8 x half> %1)
  ret <16 x half> %interleaved.vec
}


; Expected not to transform as it is integer
define <16 x i16> @complex_add_v16i16(<16 x i16> %a, <16 x i16> %b) {
; CHECK-LABEL: complex_add_v16i16:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    uzp1 v4.8h, v2.8h, v3.8h
; CHECK-NEXT:    uzp1 v5.8h, v0.8h, v1.8h
; CHECK-NEXT:    uzp2 v0.8h, v0.8h, v1.8h
; CHECK-NEXT:    uzp2 v1.8h, v2.8h, v3.8h
; CHECK-NEXT:    sub v2.8h, v4.8h, v0.8h
; CHECK-NEXT:    add v1.8h, v1.8h, v5.8h
; CHECK-NEXT:    zip1 v0.8h, v2.8h, v1.8h
; CHECK-NEXT:    zip2 v1.8h, v2.8h, v1.8h
; CHECK-NEXT:    ret
entry:
  %a.real = shufflevector <16 x i16> %a, <16 x i16> zeroinitializer, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
  %a.imag = shufflevector <16 x i16> %a, <16 x i16> zeroinitializer, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
  %b.real = shufflevector <16 x i16> %b, <16 x i16> zeroinitializer, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
  %b.imag = shufflevector <16 x i16> %b, <16 x i16> zeroinitializer, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
  %0 = sub <8 x i16> %b.real, %a.imag
  %1 = add <8 x i16> %b.imag, %a.real
  %interleaved.vec = shufflevector <8 x i16> %0, <8 x i16> %1, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
  ret <16 x i16> %interleaved.vec
}


declare { <2 x half>, <2 x half> } @llvm.experimental.vector.deinterleave2.v4f16(<4 x half>)
declare <4 x half> @llvm.experimental.vector.interleave2.v4f16(<2 x half>, <2 x half>)

declare { <4 x half>, <4 x half> } @llvm.experimental.vector.deinterleave2.v8f16(<8 x half>)
declare <8 x half> @llvm.experimental.vector.interleave2.v8f16(<4 x half>, <4 x half>)

declare { <8 x half>, <8 x half> } @llvm.experimental.vector.deinterleave2.v16f16(<16 x half>)
declare <16 x half> @llvm.experimental.vector.interleave2.v16f16(<8 x half>, <8 x half>)