; 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 --check-prefixes=CHECK,RV32 %s
; RUN: llc -mtriple=riscv64 -mattr=+d,+zvfh,+v -target-abi=lp64d \
; RUN:     -verify-machineinstrs < %s | FileCheck --check-prefixes=CHECK,RV64 %s

declare <2 x half> @llvm.experimental.constrained.nearbyint.v2f16(<2 x half>, metadata, metadata)

define <2 x half> @nearbyint_v2f16(<2 x half> %v) strictfp {
; CHECK-LABEL: nearbyint_v2f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    li a0, 25
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    slli a0, a0, 10
; CHECK-NEXT:    vfabs.v v9, v8
; CHECK-NEXT:    fmv.h.x fa5, a0
; CHECK-NEXT:    vmflt.vf v0, v9, fa5
; CHECK-NEXT:    frflags a0
; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; 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:    fsflags a0
; CHECK-NEXT:    ret
  %r = call <2 x half> @llvm.experimental.constrained.nearbyint.v2f16(<2 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
  ret <2 x half> %r
}

declare <4 x half> @llvm.experimental.constrained.nearbyint.v4f16(<4 x half>, metadata, metadata)

define <4 x half> @nearbyint_v4f16(<4 x half> %v) strictfp {
; CHECK-LABEL: nearbyint_v4f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    li a0, 25
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    slli a0, a0, 10
; CHECK-NEXT:    vfabs.v v9, v8
; CHECK-NEXT:    fmv.h.x fa5, a0
; CHECK-NEXT:    vmflt.vf v0, v9, fa5
; CHECK-NEXT:    frflags a0
; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; 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:    fsflags a0
; CHECK-NEXT:    ret
  %r = call <4 x half> @llvm.experimental.constrained.nearbyint.v4f16(<4 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
  ret <4 x half> %r
}

declare <8 x half> @llvm.experimental.constrained.nearbyint.v8f16(<8 x half>, metadata, metadata)

define <8 x half> @nearbyint_v8f16(<8 x half> %v) strictfp {
; CHECK-LABEL: nearbyint_v8f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    li a0, 25
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    slli a0, a0, 10
; CHECK-NEXT:    vfabs.v v9, v8
; CHECK-NEXT:    fmv.h.x fa5, a0
; CHECK-NEXT:    vmflt.vf v0, v9, fa5
; CHECK-NEXT:    frflags a0
; CHECK-NEXT:    vsetvli zero, zero, e16, m1, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; 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:    fsflags a0
; CHECK-NEXT:    ret
  %r = call <8 x half> @llvm.experimental.constrained.nearbyint.v8f16(<8 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
  ret <8 x half> %r
}

declare <16 x half> @llvm.experimental.constrained.nearbyint.v16f16(<16 x half>, metadata, metadata)

define <16 x half> @nearbyint_v16f16(<16 x half> %v) strictfp {
; CHECK-LABEL: nearbyint_v16f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    li a0, 25
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    slli a0, a0, 10
; CHECK-NEXT:    vfabs.v v10, v8
; CHECK-NEXT:    fmv.h.x fa5, a0
; CHECK-NEXT:    vmflt.vf v0, v10, fa5
; CHECK-NEXT:    frflags a0
; CHECK-NEXT:    vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
; 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:    fsflags a0
; CHECK-NEXT:    ret
  %r = call <16 x half> @llvm.experimental.constrained.nearbyint.v16f16(<16 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
  ret <16 x half> %r
}

declare <32 x half> @llvm.experimental.constrained.nearbyint.v32f16(<32 x half>, metadata, metadata)

define <32 x half> @nearbyint_v32f16(<32 x half> %v) strictfp {
; CHECK-LABEL: nearbyint_v32f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    li a0, 32
; CHECK-NEXT:    li a1, 25
; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
; CHECK-NEXT:    vmfne.vv v0, v8, v8
; CHECK-NEXT:    slli a1, a1, 10
; CHECK-NEXT:    vfadd.vv v8, v8, v8, v0.t
; CHECK-NEXT:    fmv.h.x fa5, a1
; CHECK-NEXT:    vfabs.v v12, v8
; CHECK-NEXT:    vmflt.vf v0, v12, fa5
; CHECK-NEXT:    frflags a0
; CHECK-NEXT:    vsetvli zero, zero, e16, m4, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
; 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:    fsflags a0
; CHECK-NEXT:    ret
  %r = call <32 x half> @llvm.experimental.constrained.nearbyint.v32f16(<32 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
  ret <32 x half> %r
}

declare <2 x float> @llvm.experimental.constrained.nearbyint.v2f32(<2 x float>, metadata, metadata)

define <2 x float> @nearbyint_v2f32(<2 x float> %v) strictfp {
; CHECK-LABEL: nearbyint_v2f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 2, 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:    frflags a0
; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; 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:    fsflags a0
; CHECK-NEXT:    ret
  %r = call <2 x float> @llvm.experimental.constrained.nearbyint.v2f32(<2 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
  ret <2 x float> %r
}

declare <4 x float> @llvm.experimental.constrained.nearbyint.v4f32(<4 x float>, metadata, metadata)

define <4 x float> @nearbyint_v4f32(<4 x float> %v) strictfp {
; CHECK-LABEL: nearbyint_v4f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 4, 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:    frflags a0
; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; 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:    fsflags a0
; CHECK-NEXT:    ret
  %r = call <4 x float> @llvm.experimental.constrained.nearbyint.v4f32(<4 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
  ret <4 x float> %r
}

declare <8 x float> @llvm.experimental.constrained.nearbyint.v8f32(<8 x float>, metadata, metadata)

define <8 x float> @nearbyint_v8f32(<8 x float> %v) strictfp {
; CHECK-LABEL: nearbyint_v8f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 8, 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:    frflags a0
; CHECK-NEXT:    vsetvli zero, zero, e32, m2, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v10, v8, v0.t
; 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:    fsflags a0
; CHECK-NEXT:    ret
  %r = call <8 x float> @llvm.experimental.constrained.nearbyint.v8f32(<8 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
  ret <8 x float> %r
}

declare <16 x float> @llvm.experimental.constrained.nearbyint.v16f32(<16 x float>, metadata, metadata)

define <16 x float> @nearbyint_v16f32(<16 x float> %v) strictfp {
; CHECK-LABEL: nearbyint_v16f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetivli zero, 16, 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:    frflags a0
; CHECK-NEXT:    vsetvli zero, zero, e32, m4, ta, ma
; CHECK-NEXT:    vfcvt.x.f.v v12, v8, v0.t
; 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:    fsflags a0
; CHECK-NEXT:    ret
  %r = call <16 x float> @llvm.experimental.constrained.nearbyint.v16f32(<16 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
  ret <16 x float> %r
}

declare <2 x double> @llvm.experimental.constrained.nearbyint.v2f64(<2 x double>, metadata, metadata)

define <2 x double> @nearbyint_v2f64(<2 x double> %v) strictfp {
; RV32-LABEL: nearbyint_v2f64:
; RV32:       # %bb.0:
; RV32-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
; RV32-NEXT:    vmfne.vv v0, v8, v8
; RV32-NEXT:    lui a0, %hi(.LCPI9_0)
; RV32-NEXT:    fld fa5, %lo(.LCPI9_0)(a0)
; RV32-NEXT:    vfadd.vv v8, v8, v8, v0.t
; RV32-NEXT:    vfabs.v v9, v8
; RV32-NEXT:    vmflt.vf v0, v9, fa5
; RV32-NEXT:    frflags a0
; RV32-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
; RV32-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; RV32-NEXT:    vfcvt.f.x.v v9, v9, v0.t
; RV32-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
; RV32-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
; RV32-NEXT:    fsflags a0
; RV32-NEXT:    ret
;
; RV64-LABEL: nearbyint_v2f64:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
; RV64-NEXT:    vmfne.vv v0, v8, v8
; RV64-NEXT:    li a0, 1075
; RV64-NEXT:    vfadd.vv v8, v8, v8, v0.t
; RV64-NEXT:    slli a0, a0, 52
; RV64-NEXT:    vfabs.v v9, v8
; RV64-NEXT:    fmv.d.x fa5, a0
; RV64-NEXT:    vmflt.vf v0, v9, fa5
; RV64-NEXT:    frflags a0
; RV64-NEXT:    vsetvli zero, zero, e64, m1, ta, ma
; RV64-NEXT:    vfcvt.x.f.v v9, v8, v0.t
; RV64-NEXT:    vfcvt.f.x.v v9, v9, v0.t
; RV64-NEXT:    vsetvli zero, zero, e64, m1, ta, mu
; RV64-NEXT:    vfsgnj.vv v8, v9, v8, v0.t
; RV64-NEXT:    fsflags a0
; RV64-NEXT:    ret
  %r = call <2 x double> @llvm.experimental.constrained.nearbyint.v2f64(<2 x double> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
  ret <2 x double> %r
}

declare <4 x double> @llvm.experimental.constrained.nearbyint.v4f64(<4 x double>, metadata, metadata)

define <4 x double> @nearbyint_v4f64(<4 x double> %v) strictfp {
; RV32-LABEL: nearbyint_v4f64:
; RV32:       # %bb.0:
; RV32-NEXT:    vsetivli zero, 4, e64, m2, ta, mu
; RV32-NEXT:    vmfne.vv v0, v8, v8
; RV32-NEXT:    lui a0, %hi(.LCPI10_0)
; RV32-NEXT:    fld fa5, %lo(.LCPI10_0)(a0)
; RV32-NEXT:    vfadd.vv v8, v8, v8, v0.t
; RV32-NEXT:    vfabs.v v10, v8
; RV32-NEXT:    vmflt.vf v0, v10, fa5
; RV32-NEXT:    frflags a0
; RV32-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
; RV32-NEXT:    vfcvt.x.f.v v10, v8, v0.t
; RV32-NEXT:    vfcvt.f.x.v v10, v10, v0.t
; RV32-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
; RV32-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
; RV32-NEXT:    fsflags a0
; RV32-NEXT:    ret
;
; RV64-LABEL: nearbyint_v4f64:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetivli zero, 4, e64, m2, ta, mu
; RV64-NEXT:    vmfne.vv v0, v8, v8
; RV64-NEXT:    li a0, 1075
; RV64-NEXT:    vfadd.vv v8, v8, v8, v0.t
; RV64-NEXT:    slli a0, a0, 52
; RV64-NEXT:    vfabs.v v10, v8
; RV64-NEXT:    fmv.d.x fa5, a0
; RV64-NEXT:    vmflt.vf v0, v10, fa5
; RV64-NEXT:    frflags a0
; RV64-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
; RV64-NEXT:    vfcvt.x.f.v v10, v8, v0.t
; RV64-NEXT:    vfcvt.f.x.v v10, v10, v0.t
; RV64-NEXT:    vsetvli zero, zero, e64, m2, ta, mu
; RV64-NEXT:    vfsgnj.vv v8, v10, v8, v0.t
; RV64-NEXT:    fsflags a0
; RV64-NEXT:    ret
  %r = call <4 x double> @llvm.experimental.constrained.nearbyint.v4f64(<4 x double> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
  ret <4 x double> %r
}

declare <8 x double> @llvm.experimental.constrained.nearbyint.v8f64(<8 x double>, metadata, metadata)

define <8 x double> @nearbyint_v8f64(<8 x double> %v) strictfp {
; RV32-LABEL: nearbyint_v8f64:
; RV32:       # %bb.0:
; RV32-NEXT:    vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT:    vmfne.vv v0, v8, v8
; RV32-NEXT:    lui a0, %hi(.LCPI11_0)
; RV32-NEXT:    fld fa5, %lo(.LCPI11_0)(a0)
; RV32-NEXT:    vfadd.vv v8, v8, v8, v0.t
; RV32-NEXT:    vfabs.v v12, v8
; RV32-NEXT:    vmflt.vf v0, v12, fa5
; RV32-NEXT:    frflags a0
; RV32-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
; RV32-NEXT:    vfcvt.x.f.v v12, v8, v0.t
; RV32-NEXT:    vfcvt.f.x.v v12, v12, v0.t
; RV32-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
; RV32-NEXT:    fsflags a0
; RV32-NEXT:    ret
;
; RV64-LABEL: nearbyint_v8f64:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT:    vmfne.vv v0, v8, v8
; RV64-NEXT:    li a0, 1075
; RV64-NEXT:    vfadd.vv v8, v8, v8, v0.t
; RV64-NEXT:    slli a0, a0, 52
; RV64-NEXT:    vfabs.v v12, v8
; RV64-NEXT:    fmv.d.x fa5, a0
; RV64-NEXT:    vmflt.vf v0, v12, fa5
; RV64-NEXT:    frflags a0
; RV64-NEXT:    vsetvli zero, zero, e64, m4, ta, ma
; RV64-NEXT:    vfcvt.x.f.v v12, v8, v0.t
; RV64-NEXT:    vfcvt.f.x.v v12, v12, v0.t
; RV64-NEXT:    vsetvli zero, zero, e64, m4, ta, mu
; RV64-NEXT:    vfsgnj.vv v8, v12, v8, v0.t
; RV64-NEXT:    fsflags a0
; RV64-NEXT:    ret
  %r = call <8 x double> @llvm.experimental.constrained.nearbyint.v8f64(<8 x double> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
  ret <8 x double> %r
}