llvm/test/CodeGen/AArch64/fp-intrinsics-vector.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64 %s -disable-strictnode-mutation -o - | FileCheck %s --check-prefixes=CHECK,CHECK-SD
; RUN: llc -mtriple=aarch64 -global-isel=true -global-isel-abort=2 -disable-strictnode-mutation %s -o - 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK-GI

; Check that constrained fp vector intrinsics are correctly lowered.

; CHECK-GI:       warning: Instruction selection used fallback path for add_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for sub_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for mul_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for div_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fma_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptosi_v4i32_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptoui_v4i32_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptosi_v4i64_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptoui_v4i64_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for sitofp_v4f32_v4i32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for uitofp_v4f32_v4i32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for sitofp_v4f32_v4i64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for uitofp_v4f32_v4i64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for sqrt_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for rint_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for nearbyint_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for maxnum_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for minnum_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for ceil_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for floor_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for round_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for roundeven_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for trunc_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fcmp_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fcmps_v4f32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for add_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for sub_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for mul_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for div_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fma_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptosi_v2i32_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptoui_v2i32_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptosi_v2i64_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptoui_v2i64_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for sitofp_v2f64_v2i32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for uitofp_v2f64_v2i32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for sitofp_v2f64_v2i64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for uitofp_v2f64_v2i64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for sqrt_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for rint_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for nearbyint_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for maxnum_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for minnum_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for ceil_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for floor_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for round_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for roundeven_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for trunc_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fcmp_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fcmps_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for add_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for sub_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for mul_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for div_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fma_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptosi_v1i32_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptoui_v1i32_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptosi_v1i64_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptoui_v1i64_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for sitofp_v1f64_v1i32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for uitofp_v1f64_v1i32
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for sitofp_v1f64_v1i64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for uitofp_v1f64_v1i64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for sqrt_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for rint_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for nearbyint_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for maxnum_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for minnum_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for ceil_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for floor_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for round_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for roundeven_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for trunc_v1f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fcmp_v1f61
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fcmps_v1f61
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fptrunc_v2f32_v2f64
; CHECK-GI-NEXT:  warning: Instruction selection used fallback path for fpext_v2f64_v2f32

; Single-precision intrinsics

define <4 x float> @add_v4f32(<4 x float> %x, <4 x float> %y) #0 {
; CHECK-LABEL: add_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fadd v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.fadd.v4f32(<4 x float> %x, <4 x float> %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @sub_v4f32(<4 x float> %x, <4 x float> %y) #0 {
; CHECK-LABEL: sub_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fsub v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.fsub.v4f32(<4 x float> %x, <4 x float> %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @mul_v4f32(<4 x float> %x, <4 x float> %y) #0 {
; CHECK-LABEL: mul_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fmul v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.fmul.v4f32(<4 x float> %x, <4 x float> %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @div_v4f32(<4 x float> %x, <4 x float> %y) #0 {
; CHECK-LABEL: div_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fdiv v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.fdiv.v4f32(<4 x float> %x, <4 x float> %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @fma_v4f32(<4 x float> %x, <4 x float> %y, <4 x float> %z) #0 {
; CHECK-LABEL: fma_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fmla v2.4s, v1.4s, v0.4s
; CHECK-NEXT:    mov v0.16b, v2.16b
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.fma.v4f32(<4 x float> %x, <4 x float> %y, <4 x float> %z, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x i32> @fptosi_v4i32_v4f32(<4 x float> %x) #0 {
; CHECK-LABEL: fptosi_v4i32_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtzs v0.4s, v0.4s
; CHECK-NEXT:    ret
  %val = call <4 x i32> @llvm.experimental.constrained.fptosi.v4i32.v4f32(<4 x float> %x, metadata !"fpexcept.strict") #0
  ret <4 x i32> %val
}

define <4 x i32> @fptoui_v4i32_v4f32(<4 x float> %x) #0 {
; CHECK-LABEL: fptoui_v4i32_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtzu v0.4s, v0.4s
; CHECK-NEXT:    ret
  %val = call <4 x i32> @llvm.experimental.constrained.fptoui.v4i32.v4f32(<4 x float> %x, metadata !"fpexcept.strict") #0
  ret <4 x i32> %val
}

define <4 x i64> @fptosi_v4i64_v4f32(<4 x float> %x) #0 {
; CHECK-LABEL: fptosi_v4i64_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtl2 v1.2d, v0.4s
; CHECK-NEXT:    fcvtl v0.2d, v0.2s
; CHECK-NEXT:    fcvtzs v1.2d, v1.2d
; CHECK-NEXT:    fcvtzs v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <4 x i64> @llvm.experimental.constrained.fptosi.v4i64.v4f32(<4 x float> %x, metadata !"fpexcept.strict") #0
  ret <4 x i64> %val
}

define <4 x i64> @fptoui_v4i64_v4f32(<4 x float> %x) #0 {
; CHECK-LABEL: fptoui_v4i64_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtl2 v1.2d, v0.4s
; CHECK-NEXT:    fcvtl v0.2d, v0.2s
; CHECK-NEXT:    fcvtzu v1.2d, v1.2d
; CHECK-NEXT:    fcvtzu v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <4 x i64> @llvm.experimental.constrained.fptoui.v4i64.v4f32(<4 x float> %x, metadata !"fpexcept.strict") #0
  ret <4 x i64> %val
}

define <4 x float> @sitofp_v4f32_v4i32(<4 x i32> %x) #0 {
; CHECK-LABEL: sitofp_v4f32_v4i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    scvtf v0.4s, v0.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.sitofp.v4f32.v4i32(<4 x i32> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @uitofp_v4f32_v4i32(<4 x i32> %x) #0 {
; CHECK-LABEL: uitofp_v4f32_v4i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ucvtf v0.4s, v0.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.uitofp.v4f32.v4i32(<4 x i32> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @sitofp_v4f32_v4i64(<4 x i64> %x) #0 {
; CHECK-LABEL: sitofp_v4f32_v4i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    mov x8, v0.d[1]
; CHECK-NEXT:    fmov x9, d0
; CHECK-NEXT:    scvtf s0, x9
; CHECK-NEXT:    mov x9, v1.d[1]
; CHECK-NEXT:    scvtf s2, x8
; CHECK-NEXT:    fmov x8, d1
; CHECK-NEXT:    scvtf s1, x8
; CHECK-NEXT:    mov v0.s[1], v2.s[0]
; CHECK-NEXT:    mov v0.s[2], v1.s[0]
; CHECK-NEXT:    scvtf s1, x9
; CHECK-NEXT:    mov v0.s[3], v1.s[0]
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.sitofp.v4f32.v4i64(<4 x i64> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @uitofp_v4f32_v4i64(<4 x i64> %x) #0 {
; CHECK-LABEL: uitofp_v4f32_v4i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    movi v2.2d, #0x000000ffffffff
; CHECK-NEXT:    ushr v3.2d, v1.2d, #32
; CHECK-NEXT:    ushr v4.2d, v0.2d, #32
; CHECK-NEXT:    mov x8, v3.d[1]
; CHECK-NEXT:    mov x9, v4.d[1]
; CHECK-NEXT:    fmov x10, d3
; CHECK-NEXT:    and v1.16b, v1.16b, v2.16b
; CHECK-NEXT:    and v0.16b, v0.16b, v2.16b
; CHECK-NEXT:    fmov x11, d4
; CHECK-NEXT:    scvtf s2, x10
; CHECK-NEXT:    mov x10, v1.d[1]
; CHECK-NEXT:    scvtf s3, x8
; CHECK-NEXT:    scvtf s4, x11
; CHECK-NEXT:    mov x8, v0.d[1]
; CHECK-NEXT:    scvtf s5, x9
; CHECK-NEXT:    mov w9, #1333788672 // =0x4f800000
; CHECK-NEXT:    fmov x11, d1
; CHECK-NEXT:    dup v1.2s, w9
; CHECK-NEXT:    fmov x9, d0
; CHECK-NEXT:    scvtf s0, x10
; CHECK-NEXT:    mov v2.s[1], v3.s[0]
; CHECK-NEXT:    scvtf s6, x11
; CHECK-NEXT:    scvtf s3, x8
; CHECK-NEXT:    mov v4.s[1], v5.s[0]
; CHECK-NEXT:    scvtf s5, x9
; CHECK-NEXT:    mov v6.s[1], v0.s[0]
; CHECK-NEXT:    fmul v0.2s, v2.2s, v1.2s
; CHECK-NEXT:    fmul v1.2s, v4.2s, v1.2s
; CHECK-NEXT:    mov v5.s[1], v3.s[0]
; CHECK-NEXT:    fadd v2.2s, v0.2s, v6.2s
; CHECK-NEXT:    fadd v0.2s, v1.2s, v5.2s
; CHECK-NEXT:    mov v0.d[1], v2.d[0]
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.uitofp.v4f32.v4i64(<4 x i64> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @sqrt_v4f32(<4 x float> %x) #0 {
; CHECK-LABEL: sqrt_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fsqrt v0.4s, v0.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.sqrt.v4f32(<4 x float> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @rint_v4f32(<4 x float> %x) #0 {
; CHECK-LABEL: rint_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintx v0.4s, v0.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.rint.v4f32(<4 x float> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @nearbyint_v4f32(<4 x float> %x) #0 {
; CHECK-LABEL: nearbyint_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frinti v0.4s, v0.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.nearbyint.v4f32(<4 x float> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @maxnum_v4f32(<4 x float> %x, <4 x float> %y) #0 {
; CHECK-LABEL: maxnum_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fmaxnm v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.maxnum.v4f32(<4 x float> %x, <4 x float> %y, metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @minnum_v4f32(<4 x float> %x, <4 x float> %y) #0 {
; CHECK-LABEL: minnum_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fminnm v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.minnum.v4f32(<4 x float> %x, <4 x float> %y, metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @ceil_v4f32(<4 x float> %x) #0 {
; CHECK-LABEL: ceil_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintp v0.4s, v0.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.ceil.v4f32(<4 x float> %x, metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @floor_v4f32(<4 x float> %x) #0 {
; CHECK-LABEL: floor_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintm v0.4s, v0.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.floor.v4f32(<4 x float> %x, metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @round_v4f32(<4 x float> %x) #0 {
; CHECK-LABEL: round_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frinta v0.4s, v0.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.round.v4f32(<4 x float> %x, metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @roundeven_v4f32(<4 x float> %x) #0 {
; CHECK-LABEL: roundeven_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintn v0.4s, v0.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.roundeven.v4f32(<4 x float> %x, metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x float> @trunc_v4f32(<4 x float> %x) #0 {
; CHECK-LABEL: trunc_v4f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintz v0.4s, v0.4s
; CHECK-NEXT:    ret
  %val = call <4 x float> @llvm.experimental.constrained.trunc.v4f32(<4 x float> %x, metadata !"fpexcept.strict") #0
  ret <4 x float> %val
}

define <4 x i1> @fcmp_v4f32(<4 x float> %x, <4 x float> %y) #0 {
; CHECK-LABEL: fcmp_v4f32:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    mov s2, v1.s[1]
; CHECK-NEXT:    mov s3, v0.s[1]
; CHECK-NEXT:    fcmp s0, s1
; CHECK-NEXT:    csetm w8, eq
; CHECK-NEXT:    fcmp s3, s2
; CHECK-NEXT:    mov s2, v1.s[2]
; CHECK-NEXT:    mov s3, v0.s[2]
; CHECK-NEXT:    fmov s4, w8
; CHECK-NEXT:    mov s1, v1.s[3]
; CHECK-NEXT:    mov s0, v0.s[3]
; CHECK-NEXT:    csetm w8, eq
; CHECK-NEXT:    mov v4.s[1], w8
; CHECK-NEXT:    fcmp s3, s2
; CHECK-NEXT:    csetm w8, eq
; CHECK-NEXT:    fcmp s0, s1
; CHECK-NEXT:    mov v4.s[2], w8
; CHECK-NEXT:    csetm w8, eq
; CHECK-NEXT:    mov v4.s[3], w8
; CHECK-NEXT:    xtn v0.4h, v4.4s
; CHECK-NEXT:    ret
entry:
  %val = call <4 x i1> @llvm.experimental.constrained.fcmp.v4f64(<4 x float> %x, <4 x float> %y, metadata !"oeq", metadata !"fpexcept.strict")
  ret <4 x i1> %val
}

define <4 x i1> @fcmps_v4f32(<4 x float> %x, <4 x float> %y) #0 {
; CHECK-LABEL: fcmps_v4f32:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    mov s2, v1.s[1]
; CHECK-NEXT:    mov s3, v0.s[1]
; CHECK-NEXT:    fcmpe s0, s1
; CHECK-NEXT:    csetm w8, eq
; CHECK-NEXT:    fcmpe s3, s2
; CHECK-NEXT:    mov s2, v1.s[2]
; CHECK-NEXT:    mov s3, v0.s[2]
; CHECK-NEXT:    fmov s4, w8
; CHECK-NEXT:    mov s1, v1.s[3]
; CHECK-NEXT:    mov s0, v0.s[3]
; CHECK-NEXT:    csetm w8, eq
; CHECK-NEXT:    mov v4.s[1], w8
; CHECK-NEXT:    fcmpe s3, s2
; CHECK-NEXT:    csetm w8, eq
; CHECK-NEXT:    fcmpe s0, s1
; CHECK-NEXT:    mov v4.s[2], w8
; CHECK-NEXT:    csetm w8, eq
; CHECK-NEXT:    mov v4.s[3], w8
; CHECK-NEXT:    xtn v0.4h, v4.4s
; CHECK-NEXT:    ret
entry:
  %val = call <4 x i1> @llvm.experimental.constrained.fcmps.v4f32(<4 x float> %x, <4 x float> %y, metadata !"oeq", metadata !"fpexcept.strict")
  ret <4 x i1> %val
}


; Double-precision intrinsics

define <2 x double> @add_v2f64(<2 x double> %x, <2 x double> %y) #0 {
; CHECK-LABEL: add_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fadd v0.2d, v0.2d, v1.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.fadd.v2f64(<2 x double> %x, <2 x double> %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @sub_v2f64(<2 x double> %x, <2 x double> %y) #0 {
; CHECK-LABEL: sub_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fsub v0.2d, v0.2d, v1.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.fsub.v2f64(<2 x double> %x, <2 x double> %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @mul_v2f64(<2 x double> %x, <2 x double> %y) #0 {
; CHECK-LABEL: mul_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fmul v0.2d, v0.2d, v1.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.fmul.v2f64(<2 x double> %x, <2 x double> %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @div_v2f64(<2 x double> %x, <2 x double> %y) #0 {
; CHECK-LABEL: div_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fdiv v0.2d, v0.2d, v1.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.fdiv.v2f64(<2 x double> %x, <2 x double> %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @fma_v2f64(<2 x double> %x, <2 x double> %y, <2 x double> %z) #0 {
; CHECK-LABEL: fma_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fmla v2.2d, v1.2d, v0.2d
; CHECK-NEXT:    mov v0.16b, v2.16b
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.fma.v2f64(<2 x double> %x, <2 x double> %y, <2 x double> %z, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x i32> @fptosi_v2i32_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: fptosi_v2i32_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtzs v0.2d, v0.2d
; CHECK-NEXT:    xtn v0.2s, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x i32> @llvm.experimental.constrained.fptosi.v2i32.v2f64(<2 x double> %x, metadata !"fpexcept.strict") #0
  ret <2 x i32> %val
}

define <2 x i32> @fptoui_v2i32_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: fptoui_v2i32_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtzu v0.2d, v0.2d
; CHECK-NEXT:    xtn v0.2s, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x i32> @llvm.experimental.constrained.fptoui.v2i32.v2f64(<2 x double> %x, metadata !"fpexcept.strict") #0
  ret <2 x i32> %val
}

define <2 x i64> @fptosi_v2i64_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: fptosi_v2i64_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtzs v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x i64> @llvm.experimental.constrained.fptosi.v2i64.v2f64(<2 x double> %x, metadata !"fpexcept.strict") #0
  ret <2 x i64> %val
}

define <2 x i64> @fptoui_v2i64_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: fptoui_v2i64_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtzu v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x i64> @llvm.experimental.constrained.fptoui.v2i64.v2f64(<2 x double> %x, metadata !"fpexcept.strict") #0
  ret <2 x i64> %val
}

define <2 x double> @sitofp_v2f64_v2i32(<2 x i32> %x) #0 {
; CHECK-LABEL: sitofp_v2f64_v2i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sshll v0.2d, v0.2s, #0
; CHECK-NEXT:    scvtf v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i32(<2 x i32> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @uitofp_v2f64_v2i32(<2 x i32> %x) #0 {
; CHECK-LABEL: uitofp_v2f64_v2i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ushll v0.2d, v0.2s, #0
; CHECK-NEXT:    ucvtf v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i32(<2 x i32> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @sitofp_v2f64_v2i64(<2 x i64> %x) #0 {
; CHECK-LABEL: sitofp_v2f64_v2i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    scvtf v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i64(<2 x i64> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @uitofp_v2f64_v2i64(<2 x i64> %x) #0 {
; CHECK-LABEL: uitofp_v2f64_v2i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ucvtf v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i64(<2 x i64> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @sqrt_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: sqrt_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fsqrt v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.sqrt.v2f64(<2 x double> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @rint_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: rint_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintx v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.rint.v2f64(<2 x double> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @nearbyint_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: nearbyint_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frinti v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.nearbyint.v2f64(<2 x double> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @maxnum_v2f64(<2 x double> %x, <2 x double> %y) #0 {
; CHECK-LABEL: maxnum_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fmaxnm v0.2d, v0.2d, v1.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.maxnum.v2f64(<2 x double> %x, <2 x double> %y, metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @minnum_v2f64(<2 x double> %x, <2 x double> %y) #0 {
; CHECK-LABEL: minnum_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fminnm v0.2d, v0.2d, v1.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.minnum.v2f64(<2 x double> %x, <2 x double> %y, metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @ceil_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: ceil_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintp v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.ceil.v2f64(<2 x double> %x, metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @floor_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: floor_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintm v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.floor.v2f64(<2 x double> %x, metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @round_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: round_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frinta v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.round.v2f64(<2 x double> %x, metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @roundeven_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: roundeven_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintn v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.roundeven.v2f64(<2 x double> %x, metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x double> @trunc_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: trunc_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintz v0.2d, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.trunc.v2f64(<2 x double> %x, metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}

define <2 x i1> @fcmp_v2f64(<2 x double> %x, <2 x double> %y) #0 {
; CHECK-LABEL: fcmp_v2f64:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    mov d2, v1.d[1]
; CHECK-NEXT:    mov d3, v0.d[1]
; CHECK-NEXT:    fcmp d0, d1
; CHECK-NEXT:    csetm x8, eq
; CHECK-NEXT:    fcmp d3, d2
; CHECK-NEXT:    fmov d0, x8
; CHECK-NEXT:    csetm x8, eq
; CHECK-NEXT:    mov v0.d[1], x8
; CHECK-NEXT:    xtn v0.2s, v0.2d
; CHECK-NEXT:    ret
entry:
  %val = call <2 x i1> @llvm.experimental.constrained.fcmp.v2f64(<2 x double> %x, <2 x double> %y, metadata !"oeq", metadata !"fpexcept.strict")
  ret <2 x i1> %val
}

define <2 x i1> @fcmps_v2f64(<2 x double> %x, <2 x double> %y) #0 {
; CHECK-LABEL: fcmps_v2f64:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    mov d2, v1.d[1]
; CHECK-NEXT:    mov d3, v0.d[1]
; CHECK-NEXT:    fcmpe d0, d1
; CHECK-NEXT:    csetm x8, eq
; CHECK-NEXT:    fcmpe d3, d2
; CHECK-NEXT:    fmov d0, x8
; CHECK-NEXT:    csetm x8, eq
; CHECK-NEXT:    mov v0.d[1], x8
; CHECK-NEXT:    xtn v0.2s, v0.2d
; CHECK-NEXT:    ret
entry:
  %val = call <2 x i1> @llvm.experimental.constrained.fcmps.v2f64(<2 x double> %x, <2 x double> %y, metadata !"oeq", metadata !"fpexcept.strict")
  ret <2 x i1> %val
}


; Double-precision single element intrinsics

define <1 x double> @add_v1f64(<1 x double> %x, <1 x double> %y) #0 {
; CHECK-LABEL: add_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fadd d0, d0, d1
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.fadd.v1f64(<1 x double> %x, <1 x double> %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @sub_v1f64(<1 x double> %x, <1 x double> %y) #0 {
; CHECK-LABEL: sub_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fsub d0, d0, d1
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.fsub.v1f64(<1 x double> %x, <1 x double> %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @mul_v1f64(<1 x double> %x, <1 x double> %y) #0 {
; CHECK-LABEL: mul_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fmul d0, d0, d1
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.fmul.v1f64(<1 x double> %x, <1 x double> %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @div_v1f64(<1 x double> %x, <1 x double> %y) #0 {
; CHECK-LABEL: div_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fdiv d0, d0, d1
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.fdiv.v1f64(<1 x double> %x, <1 x double> %y, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @fma_v1f64(<1 x double> %x, <1 x double> %y, <1 x double> %z) #0 {
; CHECK-LABEL: fma_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fmadd d0, d0, d1, d2
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.fma.v1f64(<1 x double> %x, <1 x double> %y, <1 x double> %z, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x i32> @fptosi_v1i32_v1f64(<1 x double> %x) #0 {
; CHECK-LABEL: fptosi_v1i32_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtzs w8, d0
; CHECK-NEXT:    fmov s0, w8
; CHECK-NEXT:    ret
  %val = call <1 x i32> @llvm.experimental.constrained.fptosi.v1i32.v1f64(<1 x double> %x, metadata !"fpexcept.strict") #0
  ret <1 x i32> %val
}

define <1 x i32> @fptoui_v1i32_v1f64(<1 x double> %x) #0 {
; CHECK-LABEL: fptoui_v1i32_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtzu w8, d0
; CHECK-NEXT:    fmov s0, w8
; CHECK-NEXT:    ret
  %val = call <1 x i32> @llvm.experimental.constrained.fptoui.v1i32.v1f64(<1 x double> %x, metadata !"fpexcept.strict") #0
  ret <1 x i32> %val
}

define <1 x i64> @fptosi_v1i64_v1f64(<1 x double> %x) #0 {
; CHECK-LABEL: fptosi_v1i64_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtzs x8, d0
; CHECK-NEXT:    fmov d0, x8
; CHECK-NEXT:    ret
  %val = call <1 x i64> @llvm.experimental.constrained.fptosi.v1i64.v1f64(<1 x double> %x, metadata !"fpexcept.strict") #0
  ret <1 x i64> %val
}

define <1 x i64> @fptoui_v1i64_v1f64(<1 x double> %x) #0 {
; CHECK-LABEL: fptoui_v1i64_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtzu x8, d0
; CHECK-NEXT:    fmov d0, x8
; CHECK-NEXT:    ret
  %val = call <1 x i64> @llvm.experimental.constrained.fptoui.v1i64.v1f64(<1 x double> %x, metadata !"fpexcept.strict") #0
  ret <1 x i64> %val
}

define <1 x double> @sitofp_v1f64_v1i32(<1 x i32> %x) #0 {
; CHECK-LABEL: sitofp_v1f64_v1i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    fmov w8, s0
; CHECK-NEXT:    scvtf d0, w8
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.sitofp.v1f64.v1i32(<1 x i32> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @uitofp_v1f64_v1i32(<1 x i32> %x) #0 {
; CHECK-LABEL: uitofp_v1f64_v1i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    fmov w8, s0
; CHECK-NEXT:    ucvtf d0, w8
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.uitofp.v1f64.v1i32(<1 x i32> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @sitofp_v1f64_v1i64(<1 x i64> %x) #0 {
; CHECK-LABEL: sitofp_v1f64_v1i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    fmov x8, d0
; CHECK-NEXT:    scvtf d0, x8
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.sitofp.v1f64.v1i64(<1 x i64> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @uitofp_v1f64_v1i64(<1 x i64> %x) #0 {
; CHECK-LABEL: uitofp_v1f64_v1i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    fmov x8, d0
; CHECK-NEXT:    ucvtf d0, x8
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.uitofp.v1f64.v1i64(<1 x i64> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @sqrt_v1f64(<1 x double> %x) #0 {
; CHECK-LABEL: sqrt_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fsqrt d0, d0
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.sqrt.v1f64(<1 x double> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @rint_v1f64(<1 x double> %x) #0 {
; CHECK-LABEL: rint_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintx d0, d0
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.rint.v1f64(<1 x double> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @nearbyint_v1f64(<1 x double> %x) #0 {
; CHECK-LABEL: nearbyint_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frinti d0, d0
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.nearbyint.v1f64(<1 x double> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @maxnum_v1f64(<1 x double> %x, <1 x double> %y) #0 {
; CHECK-LABEL: maxnum_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fmaxnm d0, d0, d1
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.maxnum.v1f64(<1 x double> %x, <1 x double> %y, metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @minnum_v1f64(<1 x double> %x, <1 x double> %y) #0 {
; CHECK-LABEL: minnum_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fminnm d0, d0, d1
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.minnum.v1f64(<1 x double> %x, <1 x double> %y, metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @ceil_v1f64(<1 x double> %x) #0 {
; CHECK-LABEL: ceil_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintp d0, d0
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.ceil.v1f64(<1 x double> %x, metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @floor_v1f64(<1 x double> %x) #0 {
; CHECK-LABEL: floor_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintm d0, d0
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.floor.v1f64(<1 x double> %x, metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @round_v1f64(<1 x double> %x) #0 {
; CHECK-LABEL: round_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frinta d0, d0
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.round.v1f64(<1 x double> %x, metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @roundeven_v1f64(<1 x double> %x) #0 {
; CHECK-LABEL: roundeven_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintn d0, d0
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.roundeven.v1f64(<1 x double> %x, metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x double> @trunc_v1f64(<1 x double> %x) #0 {
; CHECK-LABEL: trunc_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    frintz d0, d0
; CHECK-NEXT:    ret
  %val = call <1 x double> @llvm.experimental.constrained.trunc.v1f64(<1 x double> %x, metadata !"fpexcept.strict") #0
  ret <1 x double> %val
}

define <1 x i1> @fcmp_v1f61(<1 x double> %x, <1 x double> %y) #0 {
; CHECK-LABEL: fcmp_v1f61:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    fcmp d0, d1
; CHECK-NEXT:    cset w0, eq
; CHECK-NEXT:    ret
entry:
  %val = call <1 x i1> @llvm.experimental.constrained.fcmp.v1f64(<1 x double> %x, <1 x double> %y, metadata !"oeq", metadata !"fpexcept.strict")
  ret <1 x i1> %val
}

define <1 x i1> @fcmps_v1f61(<1 x double> %x, <1 x double> %y) #0 {
; CHECK-LABEL: fcmps_v1f61:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    fcmpe d0, d1
; CHECK-NEXT:    cset w0, eq
; CHECK-NEXT:    ret
entry:
  %val = call <1 x i1> @llvm.experimental.constrained.fcmps.v1f64(<1 x double> %x, <1 x double> %y, metadata !"oeq", metadata !"fpexcept.strict")
  ret <1 x i1> %val
}


; Intrinsics to convert between floating-point types

define <2 x float> @fptrunc_v2f32_v2f64(<2 x double> %x) #0 {
; CHECK-LABEL: fptrunc_v2f32_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtn v0.2s, v0.2d
; CHECK-NEXT:    ret
  %val = call <2 x float> @llvm.experimental.constrained.fptrunc.v2f32.v2f64(<2 x double> %x, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
  ret <2 x float> %val
}

define <2 x double> @fpext_v2f64_v2f32(<2 x float> %x) #0 {
; CHECK-LABEL: fpext_v2f64_v2f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fcvtl v0.2d, v0.2s
; CHECK-NEXT:    ret
  %val = call <2 x double> @llvm.experimental.constrained.fpext.v2f64.v2f32(<2 x float> %x, metadata !"fpexcept.strict") #0
  ret <2 x double> %val
}


attributes #0 = { strictfp }

declare <4 x float> @llvm.experimental.constrained.fadd.v4f32(<4 x float>, <4 x float>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.fsub.v4f32(<4 x float>, <4 x float>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.fmul.v4f32(<4 x float>, <4 x float>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.fdiv.v4f32(<4 x float>, <4 x float>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.fma.v4f32(<4 x float>, <4 x float>, <4 x float>, metadata, metadata)
declare <4 x i32> @llvm.experimental.constrained.fptosi.v4i32.v4f32(<4 x float>, metadata)
declare <4 x i32> @llvm.experimental.constrained.fptoui.v4i32.v4f32(<4 x float>, metadata)
declare <4 x i64> @llvm.experimental.constrained.fptosi.v4i64.v4f32(<4 x float>, metadata)
declare <4 x i64> @llvm.experimental.constrained.fptoui.v4i64.v4f32(<4 x float>, metadata)
declare <4 x float> @llvm.experimental.constrained.sitofp.v4f32.v4i32(<4 x i32>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.uitofp.v4f32.v4i32(<4 x i32>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.sitofp.v4f32.v4i64(<4 x i64>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.uitofp.v4f32.v4i64(<4 x i64>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.sqrt.v4f32(<4 x float>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.rint.v4f32(<4 x float>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.nearbyint.v4f32(<4 x float>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.maxnum.v4f32(<4 x float>, <4 x float>, metadata)
declare <4 x float> @llvm.experimental.constrained.minnum.v4f32(<4 x float>, <4 x float>, metadata)
declare <4 x float> @llvm.experimental.constrained.ceil.v4f32(<4 x float>, metadata)
declare <4 x float> @llvm.experimental.constrained.floor.v4f32(<4 x float>, metadata)
declare <4 x float> @llvm.experimental.constrained.round.v4f32(<4 x float>, metadata)
declare <4 x float> @llvm.experimental.constrained.roundeven.v4f32(<4 x float>, metadata)
declare <4 x float> @llvm.experimental.constrained.trunc.v4f32(<4 x float>, metadata)
declare <4 x i1> @llvm.experimental.constrained.fcmp.v4f32(<4 x float>, <4 x float>, metadata, metadata)
declare <4 x i1> @llvm.experimental.constrained.fcmps.v4f32(<4 x float>, <4 x float>, metadata, metadata)

declare <2 x double> @llvm.experimental.constrained.fadd.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.fsub.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.fmul.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.fdiv.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.fma.v2f64(<2 x double>, <2 x double>, <2 x double>, metadata, metadata)
declare <2 x i32> @llvm.experimental.constrained.fptosi.v2i32.v2f64(<2 x double>, metadata)
declare <2 x i32> @llvm.experimental.constrained.fptoui.v2i32.v2f64(<2 x double>, metadata)
declare <2 x i64> @llvm.experimental.constrained.fptosi.v2i64.v2f64(<2 x double>, metadata)
declare <2 x i64> @llvm.experimental.constrained.fptoui.v2i64.v2f64(<2 x double>, metadata)
declare <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i32(<2 x i32>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i32(<2 x i32>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i64(<2 x i64>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i64(<2 x i64>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.sqrt.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.rint.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.nearbyint.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.maxnum.v2f64(<2 x double>, <2 x double>, metadata)
declare <2 x double> @llvm.experimental.constrained.minnum.v2f64(<2 x double>, <2 x double>, metadata)
declare <2 x double> @llvm.experimental.constrained.ceil.v2f64(<2 x double>, metadata)
declare <2 x double> @llvm.experimental.constrained.floor.v2f64(<2 x double>, metadata)
declare <2 x double> @llvm.experimental.constrained.round.v2f64(<2 x double>, metadata)
declare <2 x double> @llvm.experimental.constrained.roundeven.v2f64(<2 x double>, metadata)
declare <2 x double> @llvm.experimental.constrained.trunc.v2f64(<2 x double>, metadata)
declare <2 x i1> @llvm.experimental.constrained.fcmp.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x i1> @llvm.experimental.constrained.fcmps.v2f64(<2 x double>, <2 x double>, metadata, metadata)

declare <1 x double> @llvm.experimental.constrained.fadd.v1f64(<1 x double>, <1 x double>, metadata, metadata)
declare <1 x double> @llvm.experimental.constrained.fsub.v1f64(<1 x double>, <1 x double>, metadata, metadata)
declare <1 x double> @llvm.experimental.constrained.fmul.v1f64(<1 x double>, <1 x double>, metadata, metadata)
declare <1 x double> @llvm.experimental.constrained.fdiv.v1f64(<1 x double>, <1 x double>, metadata, metadata)
declare <1 x double> @llvm.experimental.constrained.fma.v1f64(<1 x double>, <1 x double>, <1 x double>, metadata, metadata)
declare <1 x i32> @llvm.experimental.constrained.fptosi.v1i32.v1f64(<1 x double>, metadata)
declare <1 x i32> @llvm.experimental.constrained.fptoui.v1i32.v1f64(<1 x double>, metadata)
declare <1 x i64> @llvm.experimental.constrained.fptosi.v1i64.v1f64(<1 x double>, metadata)
declare <1 x i64> @llvm.experimental.constrained.fptoui.v1i64.v1f64(<1 x double>, metadata)
declare <1 x double> @llvm.experimental.constrained.sitofp.v1f64.v1i32(<1 x i32>, metadata, metadata)
declare <1 x double> @llvm.experimental.constrained.uitofp.v1f64.v1i32(<1 x i32>, metadata, metadata)
declare <1 x double> @llvm.experimental.constrained.sitofp.v1f64.v1i64(<1 x i64>, metadata, metadata)
declare <1 x double> @llvm.experimental.constrained.uitofp.v1f64.v1i64(<1 x i64>, metadata, metadata)
declare <1 x double> @llvm.experimental.constrained.sqrt.v1f64(<1 x double>, metadata, metadata)
declare <1 x double> @llvm.experimental.constrained.rint.v1f64(<1 x double>, metadata, metadata)
declare <1 x double> @llvm.experimental.constrained.nearbyint.v1f64(<1 x double>, metadata, metadata)
declare <1 x double> @llvm.experimental.constrained.maxnum.v1f64(<1 x double>, <1 x double>, metadata)
declare <1 x double> @llvm.experimental.constrained.minnum.v1f64(<1 x double>, <1 x double>, metadata)
declare <1 x double> @llvm.experimental.constrained.ceil.v1f64(<1 x double>, metadata)
declare <1 x double> @llvm.experimental.constrained.floor.v1f64(<1 x double>, metadata)
declare <1 x double> @llvm.experimental.constrained.round.v1f64(<1 x double>, metadata)
declare <1 x double> @llvm.experimental.constrained.roundeven.v1f64(<1 x double>, metadata)
declare <1 x double> @llvm.experimental.constrained.trunc.v1f64(<1 x double>, metadata)
declare <1 x i1> @llvm.experimental.constrained.fcmp.v1f64(<1 x double>, <1 x double>, metadata, metadata)
declare <1 x i1> @llvm.experimental.constrained.fcmps.v1f64(<1 x double>, <1 x double>, metadata, metadata)

declare <2 x float> @llvm.experimental.constrained.fptrunc.v2f32.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.fpext.v2f64.v2f32(<2 x float>, metadata)

;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; CHECK-GI: {{.*}}
; CHECK-SD: {{.*}}