; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s --check-prefix=CHECK

; Same as vecreduce-fadd-legalization.ll, but without fmf.

declare half @llvm.vector.reduce.fadd.f16.v1f16(half, <1 x half>)
declare float @llvm.vector.reduce.fadd.f32.v1f32(float, <1 x float>)
declare double @llvm.vector.reduce.fadd.f64.v1f64(double, <1 x double>)
declare fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128, <1 x fp128>)

declare float @llvm.vector.reduce.fadd.f32.v3f32(float, <3 x float>)
declare float @llvm.vector.reduce.fadd.f32.v5f32(float, <5 x float>)
declare fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128, <2 x fp128>)
declare float @llvm.vector.reduce.fadd.f32.v16f32(float, <16 x float>)

define half @test_v1f16(<1 x half> %a, half %s) nounwind {
; CHECK-LABEL: test_v1f16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvt s0, h0
; CHECK-NEXT:    fcvt s1, h1
; CHECK-NEXT:    fadd s0, s1, s0
; CHECK-NEXT:    fcvt h0, s0
; CHECK-NEXT:    ret
  %b = call half @llvm.vector.reduce.fadd.f16.v1f16(half %s, <1 x half> %a)
  ret half %b
}

define half @test_v1f16_neutral(<1 x half> %a) nounwind {
; CHECK-LABEL: test_v1f16_neutral:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ret
  %b = call half @llvm.vector.reduce.fadd.f16.v1f16(half -0.0, <1 x half> %a)
  ret half %b
}

define float @test_v1f32(<1 x float> %a, float %s) nounwind {
; CHECK-LABEL: test_v1f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    fadd s0, s1, s0
; CHECK-NEXT:    ret
  %b = call float @llvm.vector.reduce.fadd.f32.v1f32(float %s, <1 x float> %a)
  ret float %b
}

define float @test_v1f32_neutral(<1 x float> %a) nounwind {
; CHECK-LABEL: test_v1f32_neutral:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    // kill: def $s0 killed $s0 killed $q0
; CHECK-NEXT:    ret
  %b = call float @llvm.vector.reduce.fadd.f32.v1f32(float -0.0, <1 x float> %a)
  ret float %b
}

define double @test_v1f64(<1 x double> %a, double %s) nounwind {
; CHECK-LABEL: test_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fadd d0, d1, d0
; CHECK-NEXT:    ret
  %b = call double @llvm.vector.reduce.fadd.f64.v1f64(double %s, <1 x double> %a)
  ret double %b
}

define double @test_v1f64_neutral(<1 x double> %a) nounwind {
; CHECK-LABEL: test_v1f64_neutral:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ret
  %b = call double @llvm.vector.reduce.fadd.f64.v1f64(double -0.0, <1 x double> %a)
  ret double %b
}

define fp128 @test_v1f128(<1 x fp128> %a, fp128 %s) nounwind {
; CHECK-LABEL: test_v1f128:
; CHECK:       // %bb.0:
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    mov v2.16b, v0.16b
; CHECK-NEXT:    mov v0.16b, v1.16b
; CHECK-NEXT:    mov v1.16b, v2.16b
; CHECK-NEXT:    bl __addtf3
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  %b = call fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128 %s, <1 x fp128> %a)
  ret fp128 %b
}

define fp128 @test_v1f128_neutral(<1 x fp128> %a) nounwind {
; CHECK-LABEL: test_v1f128_neutral:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ret
  %b = call fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128 0xL00000000000000008000000000000000, <1 x fp128> %a)
  ret fp128 %b
}

define float @test_v3f32(<3 x float> %a, float %s) nounwind {
; CHECK-LABEL: test_v3f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fadd s1, s1, s0
; CHECK-NEXT:    mov s2, v0.s[1]
; CHECK-NEXT:    fadd s1, s1, s2
; CHECK-NEXT:    mov s0, v0.s[2]
; CHECK-NEXT:    fadd s0, s1, s0
; CHECK-NEXT:    ret
  %b = call float @llvm.vector.reduce.fadd.f32.v3f32(float %s, <3 x float> %a)
  ret float %b
}

define float @test_v3f32_neutral(<3 x float> %a) nounwind {
; CHECK-LABEL: test_v3f32_neutral:
; CHECK:       // %bb.0:
; CHECK-NEXT:    mov s1, v0.s[2]
; CHECK-NEXT:    faddp s0, v0.2s
; CHECK-NEXT:    fadd s0, s0, s1
; CHECK-NEXT:    ret
  %b = call float @llvm.vector.reduce.fadd.f32.v3f32(float -0.0, <3 x float> %a)
  ret float %b
}

define float @test_v5f32(<5 x float> %a, float %s) nounwind {
; CHECK-LABEL: test_v5f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fadd s0, s5, s0
; CHECK-NEXT:    fadd s0, s0, s1
; CHECK-NEXT:    fadd s0, s0, s2
; CHECK-NEXT:    fadd s0, s0, s3
; CHECK-NEXT:    fadd s0, s0, s4
; CHECK-NEXT:    ret
  %b = call float @llvm.vector.reduce.fadd.f32.v5f32(float %s, <5 x float> %a)
  ret float %b
}

define float @test_v5f32_neutral(<5 x float> %a) nounwind {
; CHECK-LABEL: test_v5f32_neutral:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fadd s0, s0, s1
; CHECK-NEXT:    fadd s0, s0, s2
; CHECK-NEXT:    fadd s0, s0, s3
; CHECK-NEXT:    fadd s0, s0, s4
; CHECK-NEXT:    ret
  %b = call float @llvm.vector.reduce.fadd.f32.v5f32(float -0.0, <5 x float> %a)
  ret float %b
}

define fp128 @test_v2f128(<2 x fp128> %a, fp128 %s) nounwind {
; CHECK-LABEL: test_v2f128:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sub sp, sp, #32 // =32
; CHECK-NEXT:    str q1, [sp] // 16-byte Folded Spill
; CHECK-NEXT:    mov v1.16b, v0.16b
; CHECK-NEXT:    mov v0.16b, v2.16b
; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
; CHECK-NEXT:    bl __addtf3
; CHECK-NEXT:    ldr q1, [sp] // 16-byte Folded Reload
; CHECK-NEXT:    bl __addtf3
; CHECK-NEXT:    ldr x30, [sp, #16] // 8-byte Folded Reload
; CHECK-NEXT:    add sp, sp, #32 // =32
; CHECK-NEXT:    ret
  %b = call fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 %s, <2 x fp128> %a)
  ret fp128 %b
}

define fp128 @test_v2f128_neutral(<2 x fp128> %a) nounwind {
; CHECK-LABEL: test_v2f128_neutral:
; CHECK:       // %bb.0:
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    bl __addtf3
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  %b = call fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 0xL00000000000000008000000000000000, <2 x fp128> %a)
  ret fp128 %b
}

define float @test_v16f32(<16 x float> %a, float %s) nounwind {
; CHECK-LABEL: test_v16f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    mov s22, v0.s[3]
; CHECK-NEXT:    mov s23, v0.s[2]
; CHECK-NEXT:    mov s24, v0.s[1]
; CHECK-NEXT:    fadd s0, s4, s0
; CHECK-NEXT:    fadd s0, s0, s24
; CHECK-NEXT:    fadd s0, s0, s23
; CHECK-NEXT:    fadd s0, s0, s22
; CHECK-NEXT:    mov s21, v1.s[1]
; CHECK-NEXT:    fadd s0, s0, s1
; CHECK-NEXT:    mov s20, v1.s[2]
; CHECK-NEXT:    fadd s0, s0, s21
; CHECK-NEXT:    mov s19, v1.s[3]
; CHECK-NEXT:    fadd s0, s0, s20
; CHECK-NEXT:    fadd s0, s0, s19
; CHECK-NEXT:    mov s18, v2.s[1]
; CHECK-NEXT:    fadd s0, s0, s2
; CHECK-NEXT:    mov s17, v2.s[2]
; CHECK-NEXT:    fadd s0, s0, s18
; CHECK-NEXT:    mov s16, v2.s[3]
; CHECK-NEXT:    fadd s0, s0, s17
; CHECK-NEXT:    fadd s0, s0, s16
; CHECK-NEXT:    mov s7, v3.s[1]
; CHECK-NEXT:    fadd s0, s0, s3
; CHECK-NEXT:    mov s6, v3.s[2]
; CHECK-NEXT:    fadd s0, s0, s7
; CHECK-NEXT:    mov s5, v3.s[3]
; CHECK-NEXT:    fadd s0, s0, s6
; CHECK-NEXT:    fadd s0, s0, s5
; CHECK-NEXT:    ret
  %b = call float @llvm.vector.reduce.fadd.f32.v16f32(float %s, <16 x float> %a)
  ret float %b
}

define float @test_v16f32_neutral(<16 x float> %a) nounwind {
; CHECK-LABEL: test_v16f32_neutral:
; CHECK:       // %bb.0:
; CHECK-NEXT:    mov s21, v0.s[3]
; CHECK-NEXT:    mov s22, v0.s[2]
; CHECK-NEXT:    faddp s0, v0.2s
; CHECK-NEXT:    fadd s0, s0, s22
; CHECK-NEXT:    fadd s0, s0, s21
; CHECK-NEXT:    mov s20, v1.s[1]
; CHECK-NEXT:    fadd s0, s0, s1
; CHECK-NEXT:    mov s19, v1.s[2]
; CHECK-NEXT:    fadd s0, s0, s20
; CHECK-NEXT:    mov s18, v1.s[3]
; CHECK-NEXT:    fadd s0, s0, s19
; CHECK-NEXT:    fadd s0, s0, s18
; CHECK-NEXT:    mov s17, v2.s[1]
; CHECK-NEXT:    fadd s0, s0, s2
; CHECK-NEXT:    mov s16, v2.s[2]
; CHECK-NEXT:    fadd s0, s0, s17
; CHECK-NEXT:    mov s7, v2.s[3]
; CHECK-NEXT:    fadd s0, s0, s16
; CHECK-NEXT:    fadd s0, s0, s7
; CHECK-NEXT:    mov s6, v3.s[1]
; CHECK-NEXT:    fadd s0, s0, s3
; CHECK-NEXT:    mov s5, v3.s[2]
; CHECK-NEXT:    fadd s0, s0, s6
; CHECK-NEXT:    mov s4, v3.s[3]
; CHECK-NEXT:    fadd s0, s0, s5
; CHECK-NEXT:    fadd s0, s0, s4
; CHECK-NEXT:    ret
  %b = call float @llvm.vector.reduce.fadd.f32.v16f32(float -0.0, <16 x float> %a)
  ret float %b
}