; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d,+zvfh,+v -target-abi=ilp32d \
; RUN:     -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -mtriple=riscv64 -mattr=+d,+zvfh,+v -target-abi=lp64d \
; RUN:     -verify-machineinstrs < %s | FileCheck %s

; This file tests the code generation for `llvm.experimental.constrained.round.*` on scalable vector type.

define <vscale x 1 x half> @round_nxv1f16(<vscale x 1 x half> %x) strictfp {
; CHECK-LABEL: round_nxv1f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e16, mf4, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, %hi(.LCPI0_0)
; CHECK-NEXT:    flh fa5, %lo(.LCPI0_0)(a0)
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    vfabs.v v9, v8
; CHECK-NEXT:    vmflt.vf v0, v9, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 1 x half> @llvm.experimental.constrained.round.nxv1f16(<vscale x 1 x half> %x, metadata !"fpexcept.strict")
  ret <vscale x 1 x half> %a
}
declare <vscale x 1 x half> @llvm.experimental.constrained.round.nxv1f16(<vscale x 1 x half>, metadata)

define <vscale x 2 x half> @round_nxv2f16(<vscale x 2 x half> %x) strictfp {
; CHECK-LABEL: round_nxv2f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, %hi(.LCPI1_0)
; CHECK-NEXT:    flh fa5, %lo(.LCPI1_0)(a0)
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    vfabs.v v9, v8
; CHECK-NEXT:    vmflt.vf v0, v9, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 2 x half> @llvm.experimental.constrained.round.nxv2f16(<vscale x 2 x half> %x, metadata !"fpexcept.strict")
  ret <vscale x 2 x half> %a
}
declare <vscale x 2 x half> @llvm.experimental.constrained.round.nxv2f16(<vscale x 2 x half>, metadata)

define <vscale x 4 x half> @round_nxv4f16(<vscale x 4 x half> %x) strictfp {
; CHECK-LABEL: round_nxv4f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, %hi(.LCPI2_0)
; CHECK-NEXT:    flh fa5, %lo(.LCPI2_0)(a0)
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    vfabs.v v9, v8
; CHECK-NEXT:    vmflt.vf v0, v9, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 4 x half> @llvm.experimental.constrained.round.nxv4f16(<vscale x 4 x half> %x, metadata !"fpexcept.strict")
  ret <vscale x 4 x half> %a
}
declare <vscale x 4 x half> @llvm.experimental.constrained.round.nxv4f16(<vscale x 4 x half>, metadata)

define <vscale x 8 x half> @round_nxv8f16(<vscale x 8 x half> %x) strictfp {
; CHECK-LABEL: round_nxv8f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, %hi(.LCPI3_0)
; CHECK-NEXT:    flh fa5, %lo(.LCPI3_0)(a0)
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    vfabs.v v10, v8
; CHECK-NEXT:    vmflt.vf v0, v10, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 8 x half> @llvm.experimental.constrained.round.nxv8f16(<vscale x 8 x half> %x, metadata !"fpexcept.strict")
  ret <vscale x 8 x half> %a
}
declare <vscale x 8 x half> @llvm.experimental.constrained.round.nxv8f16(<vscale x 8 x half>, metadata)

define <vscale x 16 x half> @round_nxv16f16(<vscale x 16 x half> %x) strictfp {
; CHECK-LABEL: round_nxv16f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e16, m4, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, %hi(.LCPI4_0)
; CHECK-NEXT:    flh fa5, %lo(.LCPI4_0)(a0)
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    vfabs.v v12, v8
; CHECK-NEXT:    vmflt.vf v0, v12, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 16 x half> @llvm.experimental.constrained.round.nxv16f16(<vscale x 16 x half> %x, metadata !"fpexcept.strict")
  ret <vscale x 16 x half> %a
}
declare <vscale x 16 x half> @llvm.experimental.constrained.round.nxv16f16(<vscale x 16 x half>, metadata)

define <vscale x 32 x half> @round_nxv32f16(<vscale x 32 x half> %x) strictfp {
; CHECK-LABEL: round_nxv32f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e16, m8, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, %hi(.LCPI5_0)
; CHECK-NEXT:    flh fa5, %lo(.LCPI5_0)(a0)
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    vfabs.v v16, v8
; CHECK-NEXT:    vmflt.vf v0, v16, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e16, m8, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 32 x half> @llvm.experimental.constrained.round.nxv32f16(<vscale x 32 x half> %x, metadata !"fpexcept.strict")
  ret <vscale x 32 x half> %a
}
declare <vscale x 32 x half> @llvm.experimental.constrained.round.nxv32f16(<vscale x 32 x half>, metadata)

define <vscale x 1 x float> @round_nxv1f32(<vscale x 1 x float> %x) strictfp {
; CHECK-LABEL: round_nxv1f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, 307200
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    fmv.w.x fa5, a0
; CHECK-NEXT:    vfabs.v v9, v8
; CHECK-NEXT:    vmflt.vf v0, v9, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 1 x float> @llvm.experimental.constrained.round.nxv1f32(<vscale x 1 x float> %x, metadata !"fpexcept.strict")
  ret <vscale x 1 x float> %a
}
declare <vscale x 1 x float> @llvm.experimental.constrained.round.nxv1f32(<vscale x 1 x float>, metadata)

define <vscale x 2 x float> @round_nxv2f32(<vscale x 2 x float> %x) strictfp {
; CHECK-LABEL: round_nxv2f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, 307200
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    fmv.w.x fa5, a0
; CHECK-NEXT:    vfabs.v v9, v8
; CHECK-NEXT:    vmflt.vf v0, v9, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 2 x float> @llvm.experimental.constrained.round.nxv2f32(<vscale x 2 x float> %x, metadata !"fpexcept.strict")
  ret <vscale x 2 x float> %a
}
declare <vscale x 2 x float> @llvm.experimental.constrained.round.nxv2f32(<vscale x 2 x float>, metadata)

define <vscale x 4 x float> @round_nxv4f32(<vscale x 4 x float> %x) strictfp {
; CHECK-LABEL: round_nxv4f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, 307200
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    fmv.w.x fa5, a0
; CHECK-NEXT:    vfabs.v v10, v8
; CHECK-NEXT:    vmflt.vf v0, v10, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 4 x float> @llvm.experimental.constrained.round.nxv4f32(<vscale x 4 x float> %x, metadata !"fpexcept.strict")
  ret <vscale x 4 x float> %a
}
declare <vscale x 4 x float> @llvm.experimental.constrained.round.nxv4f32(<vscale x 4 x float>, metadata)

define <vscale x 8 x float> @round_nxv8f32(<vscale x 8 x float> %x) strictfp {
; CHECK-LABEL: round_nxv8f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e32, m4, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, 307200
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    fmv.w.x fa5, a0
; CHECK-NEXT:    vfabs.v v12, v8
; CHECK-NEXT:    vmflt.vf v0, v12, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 8 x float> @llvm.experimental.constrained.round.nxv8f32(<vscale x 8 x float> %x, metadata !"fpexcept.strict")
  ret <vscale x 8 x float> %a
}
declare <vscale x 8 x float> @llvm.experimental.constrained.round.nxv8f32(<vscale x 8 x float>, metadata)

define <vscale x 16 x float> @round_nxv16f32(<vscale x 16 x float> %x) strictfp {
; CHECK-LABEL: round_nxv16f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e32, m8, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, 307200
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    fmv.w.x fa5, a0
; CHECK-NEXT:    vfabs.v v16, v8
; CHECK-NEXT:    vmflt.vf v0, v16, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e32, m8, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 16 x float> @llvm.experimental.constrained.round.nxv16f32(<vscale x 16 x float> %x, metadata !"fpexcept.strict")
  ret <vscale x 16 x float> %a
}
declare <vscale x 16 x float> @llvm.experimental.constrained.round.nxv16f32(<vscale x 16 x float>, metadata)

define <vscale x 1 x double> @round_nxv1f64(<vscale x 1 x double> %x) strictfp {
; CHECK-LABEL: round_nxv1f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e64, m1, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, %hi(.LCPI11_0)
; CHECK-NEXT:    fld fa5, %lo(.LCPI11_0)(a0)
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    vfabs.v v9, v8
; CHECK-NEXT:    vmflt.vf v0, v9, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v9, v9, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 1 x double> @llvm.experimental.constrained.round.nxv1f64(<vscale x 1 x double> %x, metadata !"fpexcept.strict")
  ret <vscale x 1 x double> %a
}
declare <vscale x 1 x double> @llvm.experimental.constrained.round.nxv1f64(<vscale x 1 x double>, metadata)

define <vscale x 2 x double> @round_nxv2f64(<vscale x 2 x double> %x) strictfp {
; CHECK-LABEL: round_nxv2f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e64, m2, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, %hi(.LCPI12_0)
; CHECK-NEXT:    fld fa5, %lo(.LCPI12_0)(a0)
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    vfabs.v v10, v8
; CHECK-NEXT:    vmflt.vf v0, v10, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v10, v10, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 2 x double> @llvm.experimental.constrained.round.nxv2f64(<vscale x 2 x double> %x, metadata !"fpexcept.strict")
  ret <vscale x 2 x double> %a
}
declare <vscale x 2 x double> @llvm.experimental.constrained.round.nxv2f64(<vscale x 2 x double>, metadata)

define <vscale x 4 x double> @round_nxv4f64(<vscale x 4 x double> %x) strictfp {
; CHECK-LABEL: round_nxv4f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, %hi(.LCPI13_0)
; CHECK-NEXT:    fld fa5, %lo(.LCPI13_0)(a0)
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    vfabs.v v12, v8
; CHECK-NEXT:    vmflt.vf v0, v12, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v12, v12, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 4 x double> @llvm.experimental.constrained.round.nxv4f64(<vscale x 4 x double> %x, metadata !"fpexcept.strict")
  ret <vscale x 4 x double> %a
}
declare <vscale x 4 x double> @llvm.experimental.constrained.round.nxv4f64(<vscale x 4 x double>, metadata)

define <vscale x 8 x double> @round_nxv8f64(<vscale x 8 x double> %x) strictfp {
; CHECK-LABEL: round_nxv8f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    lui a0, %hi(.LCPI14_0)
; CHECK-NEXT:    fld fa5, %lo(.LCPI14_0)(a0)
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    vfabs.v v16, v8
; CHECK-NEXT:    vmflt.vf v0, v16, fa5
; CHECK-NEXT:    fsrmi a0, 4
; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT:    fsrm a0
; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
; CHECK-NEXT:    ret
  %a = call <vscale x 8 x double> @llvm.experimental.constrained.round.nxv8f64(<vscale x 8 x double> %x, metadata !"fpexcept.strict")
  ret <vscale x 8 x double> %a
}
declare <vscale x 8 x double> @llvm.experimental.constrained.round.nxv8f64(<vscale x 8 x double>, metadata)