reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    1
    2
    3
    4
    5
    6
    7
    8
    9
   10
   11
   12
   13
   14
   15
   16
   17
   18
   19
   20
   21
   22
   23
   24
   25
   26
   27
   28
   29
   30
   31
   32
   33
   34
   35
   36
   37
   38
   39
   40
   41
   42
   43
   44
   45
   46
   47
   48
   49
   50
   51
   52
   53
   54
   55
   56
   57
   58
   59
   60
   61
   62
   63
   64
   65
   66
   67
   68
   69
   70
   71
   72
   73
   74
   75
   76
   77
   78
   79
   80
   81
   82
   83
   84
   85
   86
   87
   88
   89
   90
   91
   92
   93
   94
   95
   96
   97
   98
   99
  100
  101
  102
  103
  104
  105
  106
  107
  108
  109
  110
  111
  112
  113
  114
  115
  116
  117
  118
  119
; RUN: llc < %s -mtriple=aarch64-eabi -aarch64-neon-syntax=generic -asm-verbose=0 -mattr=+fullfp16 | FileCheck %s
; RUN: llc < %s -mtriple=aarch64-eabi -aarch64-neon-syntax=generic -asm-verbose=0 | FileCheck %s --check-prefix=CHECKNOFP16

define float @add_HalfS(<2 x float> %bin.rdx)  {
; CHECK-LABEL: add_HalfS:
; CHECK:       faddp s0, v0.2s
; CHECK-NEXT:  ret
  %r = call fast float @llvm.experimental.vector.reduce.v2.fadd.f32.v2f32(float 0.0, <2 x float> %bin.rdx)
  ret float %r
}

define half @add_HalfH(<4 x half> %bin.rdx)  {
; CHECK-LABEL: add_HalfH:
; CHECK:       mov   h3, v0.h[1]
; CHECK-NEXT:  mov   h1, v0.h[3]
; CHECK-NEXT:  mov   h2, v0.h[2]
; CHECK-NEXT:  fadd  h0, h0, h3
; CHECK-NEXT:  fadd  h0, h0, h2
; CHECK-NEXT:  fadd  h0, h0, h1
; CHECK-NEXT:  ret
; CHECKNOFP16-LABEL: add_HalfH:
; CHECKNOFP16-NOT:   faddp
; CHECKNOFP16-NOT:   fadd h{{[0-9]+}}
; CHECKNOFP16-NOT:   fadd v{{[0-9]+}}.{{[0-9]}}h
; CHECKNOFP16:       ret
  %r = call fast half @llvm.experimental.vector.reduce.v2.fadd.f16.v4f16(half 0.0, <4 x half> %bin.rdx)
  ret half %r
}


define half @add_H(<8 x half> %bin.rdx)  {
; CHECK-LABEL: add_H:
; CHECK:       ext   v1.16b, v0.16b, v0.16b, #8
; CHECK-NEXT:  fadd  v0.4h, v0.4h, v1.4h
; CHECK-NEXT:  mov   h1, v0.h[1]
; CHECK-NEXT:  mov   h2, v0.h[2]
; CHECK-NEXT:  fadd  h1, h0, h1
; CHECK-NEXT:  fadd  h1, h1, h2
; CHECK-NEXT:  mov   h0, v0.h[3]
; CHECK-NEXT:  fadd  h0, h1, h0
; CHECK-NEXT:  ret

; CHECKNOFP16-LABEL: add_H:
; CHECKNOFP16-NOT:   faddp
; CHECKNOFP16-NOT:   fadd h{{[0-9]+}}
; CHECKNOFP16-NOT:   fadd v{{[0-9]+}}.{{[0-9]}}h
; CHECKNOFP16:       ret
  %r = call fast half @llvm.experimental.vector.reduce.v2.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:       ext   v1.16b, v0.16b, v0.16b, #8
; CHECK-NEXT:  fadd  v0.2s, v0.2s, v1.2s
; CHECK-NEXT:  faddp s0, v0.2s
; CHECK-NEXT:  ret
  %r = call fast float @llvm.experimental.vector.reduce.v2.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:       faddp d0, v0.2d
; CHECK-NEXT:  ret
  %r = call fast double @llvm.experimental.vector.reduce.v2.fadd.f64.v2f64(double 0.0, <2 x double> %bin.rdx)
  ret double %r
}

define half @add_2H(<16 x half> %bin.rdx)  {
; CHECK-LABEL: add_2H:
; CHECK:       fadd  v0.8h, v0.8h, v1.8h
; CHECK-NEXT:  ext   v1.16b, v0.16b, v0.16b, #8
; CHECK-NEXT:  fadd  v0.4h, v0.4h, v1.4h
; CHECK-NEXT:  mov   h1, v0.h[1]
; CHECK-NEXT:  mov   h2, v0.h[2]
; CHECK-NEXT:  fadd  h1, h0, h1
; CHECK-NEXT:  fadd  h1, h1, h2
; CHECK-NEXT:  mov   h0, v0.h[3]
; CHECK-NEXT:  fadd  h0, h1, h0
; CHECK-NEXT:  ret
; CHECKNOFP16-LABEL: add_2H:
; CHECKNOFP16-NOT:   faddp
; CHECKNOFP16-NOT:   fadd h{{[0-9]+}}
; CHECKNOFP16-NOT:   fadd v{{[0-9]+}}.{{[0-9]}}h
; CHECKNOFP16:       ret
  %r = call fast half @llvm.experimental.vector.reduce.v2.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:       fadd  v0.4s, v0.4s, v1.4s
; CHECK-NEXT:  ext   v1.16b, v0.16b, v0.16b, #8
; CHECK-NEXT:  fadd  v0.2s, v0.2s, v1.2s
; CHECK-NEXT:  faddp s0, v0.2s
; CHECK-NEXT:  ret
  %r = call fast float @llvm.experimental.vector.reduce.v2.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:       fadd v0.2d, v0.2d, v1.2d
; CHECK-NEXT:  faddp d0, v0.2d
; CHECK-NEXT:  ret
  %r = call fast double @llvm.experimental.vector.reduce.v2.fadd.f64.v4f64(double 0.0, <4 x double> %bin.rdx)
  ret double %r
}

; Function Attrs: nounwind readnone
declare half @llvm.experimental.vector.reduce.v2.fadd.f16.v4f16(half, <4 x half>)
declare half @llvm.experimental.vector.reduce.v2.fadd.f16.v8f16(half, <8 x half>)
declare half @llvm.experimental.vector.reduce.v2.fadd.f16.v16f16(half, <16 x half>)
declare float @llvm.experimental.vector.reduce.v2.fadd.f32.v2f32(float, <2 x float>)
declare float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float, <4 x float>)
declare float @llvm.experimental.vector.reduce.v2.fadd.f32.v8f32(float, <8 x float>)
declare double @llvm.experimental.vector.reduce.v2.fadd.f64.v2f64(double, <2 x double>)
declare double @llvm.experimental.vector.reduce.v2.fadd.f64.v4f64(double, <4 x double>)