; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-none-eabi -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=CHECK,CHECK-SD,CHECK-SD-NOFP16
; RUN: llc -mtriple=aarch64-none-eabi -mattr=+fullfp16 -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=CHECK,CHECK-SD,CHECK-SD-FP16

define float @add_HalfS(<2 x float> %bin.rdx)  {
; CHECK-LABEL: add_HalfS:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    faddp s0, v0.2s
; CHECK-NEXT:    ret
  %r = call float @llvm.vector.reduce.fadd.f32.v2f32(float -0.0, <2 x float> %bin.rdx)
  ret float %r
}

define half @add_HalfH(<4 x half> %bin.rdx)  {
; CHECK-SD-NOFP16-LABEL: add_HalfH:
; CHECK-SD-NOFP16:       // %bb.0:
; CHECK-SD-NOFP16-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-SD-NOFP16-NEXT:    mov h1, v0.h[1]
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h0
; CHECK-SD-NOFP16-NEXT:    fcvt s1, h1
; CHECK-SD-NOFP16-NEXT:    fadd s1, s2, s1
; CHECK-SD-NOFP16-NEXT:    mov h2, v0.h[2]
; CHECK-SD-NOFP16-NEXT:    mov h0, v0.h[3]
; CHECK-SD-NOFP16-NEXT:    fcvt h1, s1
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fcvt s0, h0
; CHECK-SD-NOFP16-NEXT:    fcvt s1, h1
; CHECK-SD-NOFP16-NEXT:    fadd s1, s1, s2
; CHECK-SD-NOFP16-NEXT:    fcvt h1, s1
; CHECK-SD-NOFP16-NEXT:    fcvt s1, h1
; CHECK-SD-NOFP16-NEXT:    fadd s0, s1, s0
; CHECK-SD-NOFP16-NEXT:    fcvt h0, s0
; CHECK-SD-NOFP16-NEXT:    ret
;
; CHECK-SD-FP16-LABEL: add_HalfH:
; CHECK-SD-FP16:       // %bb.0:
; CHECK-SD-FP16-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-SD-FP16-NEXT:    mov h1, v0.h[2]
; CHECK-SD-FP16-NEXT:    faddp h2, v0.2h
; CHECK-SD-FP16-NEXT:    mov h0, v0.h[3]
; CHECK-SD-FP16-NEXT:    fadd h1, h2, h1
; CHECK-SD-FP16-NEXT:    fadd h0, h1, h0
; CHECK-SD-FP16-NEXT:    ret
  %r = call half @llvm.vector.reduce.fadd.f16.v4f16(half -0.0, <4 x half> %bin.rdx)
  ret half %r
}


define half @add_H(<8 x half> %bin.rdx)  {
; CHECK-SD-NOFP16-LABEL: add_H:
; CHECK-SD-NOFP16:       // %bb.0:
; CHECK-SD-NOFP16-NEXT:    mov h1, v0.h[1]
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h0
; CHECK-SD-NOFP16-NEXT:    fcvt s1, h1
; CHECK-SD-NOFP16-NEXT:    fadd s1, s2, s1
; CHECK-SD-NOFP16-NEXT:    mov h2, v0.h[2]
; CHECK-SD-NOFP16-NEXT:    fcvt h1, s1
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fcvt s1, h1
; CHECK-SD-NOFP16-NEXT:    fadd s1, s1, s2
; CHECK-SD-NOFP16-NEXT:    mov h2, v0.h[3]
; CHECK-SD-NOFP16-NEXT:    fcvt h1, s1
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fcvt s1, h1
; CHECK-SD-NOFP16-NEXT:    fadd s1, s1, s2
; CHECK-SD-NOFP16-NEXT:    mov h2, v0.h[4]
; CHECK-SD-NOFP16-NEXT:    fcvt h1, s1
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fcvt s1, h1
; CHECK-SD-NOFP16-NEXT:    fadd s1, s1, s2
; CHECK-SD-NOFP16-NEXT:    mov h2, v0.h[5]
; CHECK-SD-NOFP16-NEXT:    fcvt h1, s1
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fcvt s1, h1
; CHECK-SD-NOFP16-NEXT:    fadd s1, s1, s2
; CHECK-SD-NOFP16-NEXT:    mov h2, v0.h[6]
; CHECK-SD-NOFP16-NEXT:    mov h0, v0.h[7]
; CHECK-SD-NOFP16-NEXT:    fcvt h1, s1
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fcvt s0, h0
; CHECK-SD-NOFP16-NEXT:    fcvt s1, h1
; CHECK-SD-NOFP16-NEXT:    fadd s1, s1, s2
; CHECK-SD-NOFP16-NEXT:    fcvt h1, s1
; CHECK-SD-NOFP16-NEXT:    fcvt s1, h1
; CHECK-SD-NOFP16-NEXT:    fadd s0, s1, s0
; CHECK-SD-NOFP16-NEXT:    fcvt h0, s0
; CHECK-SD-NOFP16-NEXT:    ret
;
; CHECK-SD-FP16-LABEL: add_H:
; CHECK-SD-FP16:       // %bb.0:
; CHECK-SD-FP16-NEXT:    mov h1, v0.h[2]
; CHECK-SD-FP16-NEXT:    faddp h2, v0.2h
; CHECK-SD-FP16-NEXT:    mov h3, v0.h[3]
; CHECK-SD-FP16-NEXT:    fadd h1, h2, h1
; CHECK-SD-FP16-NEXT:    mov h2, v0.h[4]
; CHECK-SD-FP16-NEXT:    fadd h1, h1, h3
; CHECK-SD-FP16-NEXT:    mov h3, v0.h[5]
; CHECK-SD-FP16-NEXT:    fadd h1, h1, h2
; CHECK-SD-FP16-NEXT:    mov h2, v0.h[6]
; CHECK-SD-FP16-NEXT:    mov h0, v0.h[7]
; CHECK-SD-FP16-NEXT:    fadd h1, h1, h3
; CHECK-SD-FP16-NEXT:    fadd h1, h1, h2
; CHECK-SD-FP16-NEXT:    fadd h0, h1, h0
; CHECK-SD-FP16-NEXT:    ret
  %r = call half @llvm.vector.reduce.fadd.f16.v8f16(half -0.0, <8 x half> %bin.rdx)
  ret half %r
}

define float @add_S(<4 x float> %bin.rdx)  {
; CHECK-LABEL: add_S:
; CHECK:       // %bb.0:
; CHECK-NEXT:    mov s1, v0.s[2]
; CHECK-NEXT:    faddp s2, v0.2s
; CHECK-NEXT:    mov s0, v0.s[3]
; CHECK-NEXT:    fadd s1, s2, s1
; CHECK-NEXT:    fadd s0, s1, s0
; CHECK-NEXT:    ret
  %r = call float @llvm.vector.reduce.fadd.f32.v4f32(float -0.0, <4 x float> %bin.rdx)
  ret float %r
}

define double @add_D(<2 x double> %bin.rdx)  {
; CHECK-LABEL: add_D:
; CHECK:       // %bb.0:
; CHECK-NEXT:    faddp d0, v0.2d
; CHECK-NEXT:    ret
  %r = call double @llvm.vector.reduce.fadd.f64.v2f64(double -0.0, <2 x double> %bin.rdx)
  ret double %r
}

define half @add_2H(<16 x half> %bin.rdx)  {
; CHECK-SD-NOFP16-LABEL: add_2H:
; CHECK-SD-NOFP16:       // %bb.0:
; CHECK-SD-NOFP16-NEXT:    mov h2, v0.h[1]
; CHECK-SD-NOFP16-NEXT:    fcvt s3, h0
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fadd s2, s3, s2
; CHECK-SD-NOFP16-NEXT:    mov h3, v0.h[2]
; CHECK-SD-NOFP16-NEXT:    fcvt h2, s2
; CHECK-SD-NOFP16-NEXT:    fcvt s3, h3
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fadd s2, s2, s3
; CHECK-SD-NOFP16-NEXT:    mov h3, v0.h[3]
; CHECK-SD-NOFP16-NEXT:    fcvt h2, s2
; CHECK-SD-NOFP16-NEXT:    fcvt s3, h3
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fadd s2, s2, s3
; CHECK-SD-NOFP16-NEXT:    mov h3, v0.h[4]
; CHECK-SD-NOFP16-NEXT:    fcvt h2, s2
; CHECK-SD-NOFP16-NEXT:    fcvt s3, h3
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fadd s2, s2, s3
; CHECK-SD-NOFP16-NEXT:    mov h3, v0.h[5]
; CHECK-SD-NOFP16-NEXT:    fcvt h2, s2
; CHECK-SD-NOFP16-NEXT:    fcvt s3, h3
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fadd s2, s2, s3
; CHECK-SD-NOFP16-NEXT:    mov h3, v0.h[6]
; CHECK-SD-NOFP16-NEXT:    mov h0, v0.h[7]
; CHECK-SD-NOFP16-NEXT:    fcvt h2, s2
; CHECK-SD-NOFP16-NEXT:    fcvt s3, h3
; CHECK-SD-NOFP16-NEXT:    fcvt s0, h0
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fadd s2, s2, s3
; CHECK-SD-NOFP16-NEXT:    fcvt h2, s2
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fadd s0, s2, s0
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h1
; CHECK-SD-NOFP16-NEXT:    fcvt h0, s0
; CHECK-SD-NOFP16-NEXT:    fcvt s0, h0
; CHECK-SD-NOFP16-NEXT:    fadd s0, s0, s2
; CHECK-SD-NOFP16-NEXT:    mov h2, v1.h[1]
; CHECK-SD-NOFP16-NEXT:    fcvt h0, s0
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fcvt s0, h0
; CHECK-SD-NOFP16-NEXT:    fadd s0, s0, s2
; CHECK-SD-NOFP16-NEXT:    mov h2, v1.h[2]
; CHECK-SD-NOFP16-NEXT:    fcvt h0, s0
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fcvt s0, h0
; CHECK-SD-NOFP16-NEXT:    fadd s0, s0, s2
; CHECK-SD-NOFP16-NEXT:    mov h2, v1.h[3]
; CHECK-SD-NOFP16-NEXT:    fcvt h0, s0
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fcvt s0, h0
; CHECK-SD-NOFP16-NEXT:    fadd s0, s0, s2
; CHECK-SD-NOFP16-NEXT:    mov h2, v1.h[4]
; CHECK-SD-NOFP16-NEXT:    fcvt h0, s0
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fcvt s0, h0
; CHECK-SD-NOFP16-NEXT:    fadd s0, s0, s2
; CHECK-SD-NOFP16-NEXT:    mov h2, v1.h[5]
; CHECK-SD-NOFP16-NEXT:    fcvt h0, s0
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fcvt s0, h0
; CHECK-SD-NOFP16-NEXT:    fadd s0, s0, s2
; CHECK-SD-NOFP16-NEXT:    mov h2, v1.h[6]
; CHECK-SD-NOFP16-NEXT:    mov h1, v1.h[7]
; CHECK-SD-NOFP16-NEXT:    fcvt h0, s0
; CHECK-SD-NOFP16-NEXT:    fcvt s2, h2
; CHECK-SD-NOFP16-NEXT:    fcvt s1, h1
; CHECK-SD-NOFP16-NEXT:    fcvt s0, h0
; CHECK-SD-NOFP16-NEXT:    fadd s0, s0, s2
; CHECK-SD-NOFP16-NEXT:    fcvt h0, s0
; CHECK-SD-NOFP16-NEXT:    fcvt s0, h0
; CHECK-SD-NOFP16-NEXT:    fadd s0, s0, s1
; CHECK-SD-NOFP16-NEXT:    fcvt h0, s0
; CHECK-SD-NOFP16-NEXT:    ret
;
; CHECK-SD-FP16-LABEL: add_2H:
; CHECK-SD-FP16:       // %bb.0:
; CHECK-SD-FP16-NEXT:    mov h2, v0.h[2]
; CHECK-SD-FP16-NEXT:    faddp h3, v0.2h
; CHECK-SD-FP16-NEXT:    mov h4, v0.h[3]
; CHECK-SD-FP16-NEXT:    fadd h2, h3, h2
; CHECK-SD-FP16-NEXT:    mov h3, v0.h[4]
; CHECK-SD-FP16-NEXT:    fadd h2, h2, h4
; CHECK-SD-FP16-NEXT:    mov h4, v0.h[5]
; CHECK-SD-FP16-NEXT:    fadd h2, h2, h3
; CHECK-SD-FP16-NEXT:    mov h3, v0.h[6]
; CHECK-SD-FP16-NEXT:    mov h0, v0.h[7]
; CHECK-SD-FP16-NEXT:    fadd h2, h2, h4
; CHECK-SD-FP16-NEXT:    fadd h2, h2, h3
; CHECK-SD-FP16-NEXT:    mov h3, v1.h[2]
; CHECK-SD-FP16-NEXT:    fadd h0, h2, h0
; CHECK-SD-FP16-NEXT:    mov h2, v1.h[1]
; CHECK-SD-FP16-NEXT:    fadd h0, h0, h1
; CHECK-SD-FP16-NEXT:    fadd h0, h0, h2
; CHECK-SD-FP16-NEXT:    mov h2, v1.h[3]
; CHECK-SD-FP16-NEXT:    fadd h0, h0, h3
; CHECK-SD-FP16-NEXT:    mov h3, v1.h[4]
; CHECK-SD-FP16-NEXT:    fadd h0, h0, h2
; CHECK-SD-FP16-NEXT:    mov h2, v1.h[5]
; CHECK-SD-FP16-NEXT:    fadd h0, h0, h3
; CHECK-SD-FP16-NEXT:    mov h3, v1.h[6]
; CHECK-SD-FP16-NEXT:    mov h1, v1.h[7]
; CHECK-SD-FP16-NEXT:    fadd h0, h0, h2
; CHECK-SD-FP16-NEXT:    fadd h0, h0, h3
; CHECK-SD-FP16-NEXT:    fadd h0, h0, h1
; CHECK-SD-FP16-NEXT:    ret
  %r = call half @llvm.vector.reduce.fadd.f16.v16f16(half -0.0, <16 x half> %bin.rdx)
  ret half %r
}

define float @add_2S(<8 x float> %bin.rdx)  {
; CHECK-LABEL: add_2S:
; CHECK:       // %bb.0:
; CHECK-NEXT:    mov s2, v0.s[2]
; CHECK-NEXT:    faddp s3, v0.2s
; CHECK-NEXT:    mov s0, v0.s[3]
; CHECK-NEXT:    fadd s2, s3, s2
; CHECK-NEXT:    mov s3, v1.s[2]
; CHECK-NEXT:    fadd s0, s2, s0
; CHECK-NEXT:    mov s2, v1.s[1]
; CHECK-NEXT:    fadd s0, s0, s1
; CHECK-NEXT:    mov s1, v1.s[3]
; CHECK-NEXT:    fadd s0, s0, s2
; CHECK-NEXT:    fadd s0, s0, s3
; CHECK-NEXT:    fadd s0, s0, s1
; CHECK-NEXT:    ret
  %r = call float @llvm.vector.reduce.fadd.f32.v8f32(float -0.0, <8 x float> %bin.rdx)
  ret float %r
}

define double @add_2D(<4 x double> %bin.rdx)  {
; CHECK-LABEL: add_2D:
; CHECK:       // %bb.0:
; CHECK-NEXT:    faddp d0, v0.2d
; CHECK-NEXT:    mov d2, v1.d[1]
; CHECK-NEXT:    fadd d0, d0, d1
; CHECK-NEXT:    fadd d0, d0, d2
; CHECK-NEXT:    ret
  %r = call double @llvm.vector.reduce.fadd.f64.v4f64(double -0.0, <4 x double> %bin.rdx)
  ret double %r
}

; Added at least one test where the start value is not -0.0.
define float @add_S_init_42(<4 x float> %bin.rdx)  {
; CHECK-LABEL: add_S_init_42:
; CHECK:       // %bb.0:
; CHECK-NEXT:    mov w8, #1109917696 // =0x42280000
; CHECK-NEXT:    mov s2, v0.s[1]
; CHECK-NEXT:    mov s3, v0.s[2]
; CHECK-NEXT:    fmov s1, w8
; CHECK-NEXT:    fadd s1, s0, s1
; CHECK-NEXT:    mov s0, v0.s[3]
; CHECK-NEXT:    fadd s1, s1, s2
; CHECK-NEXT:    fadd s1, s1, s3
; CHECK-NEXT:    fadd s0, s1, s0
; CHECK-NEXT:    ret
  %r = call float @llvm.vector.reduce.fadd.f32.v4f32(float 42.0, <4 x float> %bin.rdx)
  ret float %r
}

; Function Attrs: nounwind readnone
declare half @llvm.vector.reduce.fadd.f16.v4f16(half, <4 x half>)
declare half @llvm.vector.reduce.fadd.f16.v8f16(half, <8 x half>)
declare half @llvm.vector.reduce.fadd.f16.v16f16(half, <16 x half>)
declare float @llvm.vector.reduce.fadd.f32.v2f32(float, <2 x float>)
declare float @llvm.vector.reduce.fadd.f32.v4f32(float, <4 x float>)
declare float @llvm.vector.reduce.fadd.f32.v8f32(float, <8 x float>)
declare double @llvm.vector.reduce.fadd.f64.v2f64(double, <2 x double>)
declare double @llvm.vector.reduce.fadd.f64.v4f64(double, <4 x double>)
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; CHECK-SD: {{.*}}