xref: /src/external/gpl3/gcc.old/dist/gcc/config/aarch64/aarch64-simd-builtins.def

/* Machine description for AArch64 architecture.
   Copyright (C) 2012-2019 Free Software Foundation, Inc.
   Contributed by ARM Ltd.

   This file is part of GCC.

   GCC is free software; you can redistribute it and/or modify it
   under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 3, or (at your option)
   any later version.

   GCC is distributed in the hope that it will be useful, but
   WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with GCC; see the file COPYING3.  If not see
   <http://www.gnu.org/licenses/>.  */

/* In the list below, the BUILTIN_<ITERATOR> macros expand to create
   builtins for each of the modes described by <ITERATOR>.  When adding
   new builtins to this list, a helpful idiom to follow is to add
   a line for each pattern in the md file.  Thus, ADDP, which has one
   pattern defined for the VD_BHSI iterator, and one for DImode, has two
   entries below.

   Parameter 1 is the 'type' of the intrinsic.  This is used to
   describe the type modifiers (for example; unsigned) applied to
   each of the parameters to the intrinsic function.

   Parameter 2 is the name of the intrinsic.  This is appended
   to `__builtin_aarch64_<name><mode>` to give the intrinsic name
   as exported to the front-ends.

   Parameter 3 describes how to map from the name to the CODE_FOR_
   macro holding the RTL pattern for the intrinsic.  This mapping is:
   0 - CODE_FOR_aarch64_<name><mode>
   1-9 - CODE_FOR_<name><mode><1-9>
   10 - CODE_FOR_<name><mode>.  */

  BUILTIN_VDC (COMBINE, combine, 0)
  VAR1 (COMBINEP, combine, 0, di)
  BUILTIN_VB (BINOP, pmul, 0)
  BUILTIN_VHSDF_HSDF (BINOP, fmulx, 0)
  BUILTIN_VHSDF_DF (UNOP, sqrt, 2)
  BUILTIN_VD_BHSI (BINOP, addp, 0)
  VAR1 (UNOP, addp, 0, di)
  BUILTIN_VDQ_BHSI (UNOP, clrsb, 2)
  BUILTIN_VDQ_BHSI (UNOP, clz, 2)
  BUILTIN_VS (UNOP, ctz, 2)
  BUILTIN_VB (UNOP, popcount, 2)

  /* Implemented by aarch64_<sur>q<r>shl<mode>.  */
  BUILTIN_VSDQ_I (BINOP, sqshl, 0)
  BUILTIN_VSDQ_I (BINOP_UUS, uqshl, 0)
  BUILTIN_VSDQ_I (BINOP, sqrshl, 0)
  BUILTIN_VSDQ_I (BINOP_UUS, uqrshl, 0)
  /* Implemented by aarch64_<su_optab><optab><mode>.  */
  BUILTIN_VSDQ_I (BINOP, sqadd, 0)
  BUILTIN_VSDQ_I (BINOPU, uqadd, 0)
  BUILTIN_VSDQ_I (BINOP, sqsub, 0)
  BUILTIN_VSDQ_I (BINOPU, uqsub, 0)
  /* Implemented by aarch64_<sur>qadd<mode>.  */
  BUILTIN_VSDQ_I (BINOP_SSU, suqadd, 0)
  BUILTIN_VSDQ_I (BINOP_UUS, usqadd, 0)

  /* Implemented by aarch64_get_dreg<VSTRUCT:mode><VDC:mode>.  */
  BUILTIN_VDC (GETREG, get_dregoi, 0)
  BUILTIN_VDC (GETREG, get_dregci, 0)
  BUILTIN_VDC (GETREG, get_dregxi, 0)
  VAR1 (GETREGP, get_dregoi, 0, di)
  VAR1 (GETREGP, get_dregci, 0, di)
  VAR1 (GETREGP, get_dregxi, 0, di)
  /* Implemented by aarch64_get_qreg<VSTRUCT:mode><VQ:mode>.  */
  BUILTIN_VQ (GETREG, get_qregoi, 0)
  BUILTIN_VQ (GETREG, get_qregci, 0)
  BUILTIN_VQ (GETREG, get_qregxi, 0)
  VAR1 (GETREGP, get_qregoi, 0, v2di)
  VAR1 (GETREGP, get_qregci, 0, v2di)
  VAR1 (GETREGP, get_qregxi, 0, v2di)
  /* Implemented by aarch64_set_qreg<VSTRUCT:mode><VQ:mode>.  */
  BUILTIN_VQ (SETREG, set_qregoi, 0)
  BUILTIN_VQ (SETREG, set_qregci, 0)
  BUILTIN_VQ (SETREG, set_qregxi, 0)
  VAR1 (SETREGP, set_qregoi, 0, v2di)
  VAR1 (SETREGP, set_qregci, 0, v2di)
  VAR1 (SETREGP, set_qregxi, 0, v2di)
  /* Implemented by aarch64_ld1x2<VQ:mode>. */
  BUILTIN_VQ (LOADSTRUCT, ld1x2, 0)
  /* Implemented by aarch64_ld1x2<VDC:mode>. */
  BUILTIN_VDC (LOADSTRUCT, ld1x2, 0)
  /* Implemented by aarch64_ld<VSTRUCT:nregs><VDC:mode>.  */
  BUILTIN_VDC (LOADSTRUCT, ld2, 0)
  BUILTIN_VDC (LOADSTRUCT, ld3, 0)
  BUILTIN_VDC (LOADSTRUCT, ld4, 0)
  /* Implemented by aarch64_ld<VSTRUCT:nregs><VQ:mode>.  */
  BUILTIN_VQ (LOADSTRUCT, ld2, 0)
  BUILTIN_VQ (LOADSTRUCT, ld3, 0)
  BUILTIN_VQ (LOADSTRUCT, ld4, 0)
  /* Implemented by aarch64_ld<VSTRUCT:nregs>r<VALLDIF:mode>.  */
  BUILTIN_VALLDIF (LOADSTRUCT, ld2r, 0)
  BUILTIN_VALLDIF (LOADSTRUCT, ld3r, 0)
  BUILTIN_VALLDIF (LOADSTRUCT, ld4r, 0)
  /* Implemented by aarch64_ld<VSTRUCT:nregs>_lane<VQ:mode>.  */
  BUILTIN_VALLDIF (LOADSTRUCT_LANE, ld2_lane, 0)
  BUILTIN_VALLDIF (LOADSTRUCT_LANE, ld3_lane, 0)
  BUILTIN_VALLDIF (LOADSTRUCT_LANE, ld4_lane, 0)
  /* Implemented by aarch64_st<VSTRUCT:nregs><VDC:mode>.  */
  BUILTIN_VDC (STORESTRUCT, st2, 0)
  BUILTIN_VDC (STORESTRUCT, st3, 0)
  BUILTIN_VDC (STORESTRUCT, st4, 0)
  /* Implemented by aarch64_st<VSTRUCT:nregs><VQ:mode>.  */
  BUILTIN_VQ (STORESTRUCT, st2, 0)
  BUILTIN_VQ (STORESTRUCT, st3, 0)
  BUILTIN_VQ (STORESTRUCT, st4, 0)

  BUILTIN_VALLDIF (STORESTRUCT_LANE, st2_lane, 0)
  BUILTIN_VALLDIF (STORESTRUCT_LANE, st3_lane, 0)
  BUILTIN_VALLDIF (STORESTRUCT_LANE, st4_lane, 0)

  BUILTIN_VQW (BINOP, saddl2, 0)
  BUILTIN_VQW (BINOP, uaddl2, 0)
  BUILTIN_VQW (BINOP, ssubl2, 0)
  BUILTIN_VQW (BINOP, usubl2, 0)
  BUILTIN_VQW (BINOP, saddw2, 0)
  BUILTIN_VQW (BINOP, uaddw2, 0)
  BUILTIN_VQW (BINOP, ssubw2, 0)
  BUILTIN_VQW (BINOP, usubw2, 0)
  /* Implemented by aarch64_<ANY_EXTEND:su><ADDSUB:optab>l<mode>.  */
  BUILTIN_VD_BHSI (BINOP, saddl, 0)
  BUILTIN_VD_BHSI (BINOP, uaddl, 0)
  BUILTIN_VD_BHSI (BINOP, ssubl, 0)
  BUILTIN_VD_BHSI (BINOP, usubl, 0)
  /* Implemented by aarch64_<ANY_EXTEND:su><ADDSUB:optab>w<mode>.  */
  BUILTIN_VD_BHSI (BINOP, saddw, 0)
  BUILTIN_VD_BHSI (BINOP, uaddw, 0)
  BUILTIN_VD_BHSI (BINOP, ssubw, 0)
  BUILTIN_VD_BHSI (BINOP, usubw, 0)
  /* Implemented by aarch64_<sur>h<addsub><mode>.  */
  BUILTIN_VDQ_BHSI (BINOP, shadd, 0)
  BUILTIN_VDQ_BHSI (BINOP, shsub, 0)
  BUILTIN_VDQ_BHSI (BINOP, uhadd, 0)
  BUILTIN_VDQ_BHSI (BINOP, uhsub, 0)
  BUILTIN_VDQ_BHSI (BINOP, srhadd, 0)
  BUILTIN_VDQ_BHSI (BINOP, urhadd, 0)
  /* Implemented by aarch64_<sur><addsub>hn<mode>.  */
  BUILTIN_VQN (BINOP, addhn, 0)
  BUILTIN_VQN (BINOP, subhn, 0)
  BUILTIN_VQN (BINOP, raddhn, 0)
  BUILTIN_VQN (BINOP, rsubhn, 0)
  /* Implemented by aarch64_<sur><addsub>hn2<mode>.  */
  BUILTIN_VQN (TERNOP, addhn2, 0)
  BUILTIN_VQN (TERNOP, subhn2, 0)
  BUILTIN_VQN (TERNOP, raddhn2, 0)
  BUILTIN_VQN (TERNOP, rsubhn2, 0)

  BUILTIN_VSQN_HSDI (UNOP, sqmovun, 0)
  /* Implemented by aarch64_<sur>qmovn<mode>.  */
  BUILTIN_VSQN_HSDI (UNOP, sqmovn, 0)
  BUILTIN_VSQN_HSDI (UNOP, uqmovn, 0)
  /* Implemented by aarch64_s<optab><mode>.  */
  BUILTIN_VSDQ_I (UNOP, sqabs, 0)
  BUILTIN_VSDQ_I (UNOP, sqneg, 0)

  /* Implemented by aarch64_sqdml<SBINQOPS:as>l<mode>.  */
  BUILTIN_VSD_HSI (TERNOP, sqdmlal, 0)
  BUILTIN_VSD_HSI (TERNOP, sqdmlsl, 0)
  /* Implemented by aarch64_sqdml<SBINQOPS:as>l_lane<mode>.  */
  BUILTIN_VSD_HSI (QUADOP_LANE, sqdmlal_lane, 0)
  BUILTIN_VSD_HSI (QUADOP_LANE, sqdmlsl_lane, 0)
  /* Implemented by aarch64_sqdml<SBINQOPS:as>l_laneq<mode>.  */
  BUILTIN_VSD_HSI (QUADOP_LANE, sqdmlal_laneq, 0)
  BUILTIN_VSD_HSI (QUADOP_LANE, sqdmlsl_laneq, 0)
  /* Implemented by aarch64_sqdml<SBINQOPS:as>l_n<mode>.  */
  BUILTIN_VD_HSI (TERNOP, sqdmlal_n, 0)
  BUILTIN_VD_HSI (TERNOP, sqdmlsl_n, 0)

  BUILTIN_VQ_HSI (TERNOP, sqdmlal2, 0)
  BUILTIN_VQ_HSI (TERNOP, sqdmlsl2, 0)
  BUILTIN_VQ_HSI (QUADOP_LANE, sqdmlal2_lane, 0)
  BUILTIN_VQ_HSI (QUADOP_LANE, sqdmlsl2_lane, 0)
  BUILTIN_VQ_HSI (QUADOP_LANE, sqdmlal2_laneq, 0)
  BUILTIN_VQ_HSI (QUADOP_LANE, sqdmlsl2_laneq, 0)
  BUILTIN_VQ_HSI (TERNOP, sqdmlal2_n, 0)
  BUILTIN_VQ_HSI (TERNOP, sqdmlsl2_n, 0)

  BUILTIN_VSD_HSI (BINOP, sqdmull, 0)
  BUILTIN_VSD_HSI (TERNOP_LANE, sqdmull_lane, 0)
  BUILTIN_VSD_HSI (TERNOP_LANE, sqdmull_laneq, 0)
  BUILTIN_VD_HSI (BINOP, sqdmull_n, 0)
  BUILTIN_VQ_HSI (BINOP, sqdmull2, 0)
  BUILTIN_VQ_HSI (TERNOP_LANE, sqdmull2_lane, 0)
  BUILTIN_VQ_HSI (TERNOP_LANE, sqdmull2_laneq, 0)
  BUILTIN_VQ_HSI (BINOP, sqdmull2_n, 0)
  /* Implemented by aarch64_sq<r>dmulh<mode>.  */
  BUILTIN_VSDQ_HSI (BINOP, sqdmulh, 0)
  BUILTIN_VSDQ_HSI (BINOP, sqrdmulh, 0)
  /* Implemented by aarch64_sq<r>dmulh_lane<q><mode>.  */
  BUILTIN_VSDQ_HSI (TERNOP_LANE, sqdmulh_lane, 0)
  BUILTIN_VSDQ_HSI (TERNOP_LANE, sqdmulh_laneq, 0)
  BUILTIN_VSDQ_HSI (TERNOP_LANE, sqrdmulh_lane, 0)
  BUILTIN_VSDQ_HSI (TERNOP_LANE, sqrdmulh_laneq, 0)

  BUILTIN_VSDQ_I_DI (BINOP, ashl, 3)
  /* Implemented by aarch64_<sur>shl<mode>.  */
  BUILTIN_VSDQ_I_DI (BINOP, sshl, 0)
  BUILTIN_VSDQ_I_DI (BINOP_UUS, ushl, 0)
  BUILTIN_VSDQ_I_DI (BINOP, srshl, 0)
  BUILTIN_VSDQ_I_DI (BINOP_UUS, urshl, 0)

  /* Implemented by aarch64_<sur><dotprod>{_lane}{q}<dot_mode>.  */
  BUILTIN_VB (TERNOP, sdot, 0)
  BUILTIN_VB (TERNOPU, udot, 0)
  BUILTIN_VB (QUADOP_LANE, sdot_lane, 0)
  BUILTIN_VB (QUADOPU_LANE, udot_lane, 0)
  BUILTIN_VB (QUADOP_LANE, sdot_laneq, 0)
  BUILTIN_VB (QUADOPU_LANE, udot_laneq, 0)

  /* Implemented by aarch64_fcadd<rot><mode>.   */
  BUILTIN_VHSDF (BINOP, fcadd90, 0)
  BUILTIN_VHSDF (BINOP, fcadd270, 0)

  /* Implemented by aarch64_fcmla{_lane}{q}<rot><mode>.   */
  BUILTIN_VHSDF (TERNOP, fcmla0, 0)
  BUILTIN_VHSDF (TERNOP, fcmla90, 0)
  BUILTIN_VHSDF (TERNOP, fcmla180, 0)
  BUILTIN_VHSDF (TERNOP, fcmla270, 0)
  BUILTIN_VHSDF (QUADOP_LANE_PAIR, fcmla_lane0, 0)
  BUILTIN_VHSDF (QUADOP_LANE_PAIR, fcmla_lane90, 0)
  BUILTIN_VHSDF (QUADOP_LANE_PAIR, fcmla_lane180, 0)
  BUILTIN_VHSDF (QUADOP_LANE_PAIR, fcmla_lane270, 0)

  BUILTIN_VQ_HSF (QUADOP_LANE_PAIR, fcmlaq_lane0, 0)
  BUILTIN_VQ_HSF (QUADOP_LANE_PAIR, fcmlaq_lane90, 0)
  BUILTIN_VQ_HSF (QUADOP_LANE_PAIR, fcmlaq_lane180, 0)
  BUILTIN_VQ_HSF (QUADOP_LANE_PAIR, fcmlaq_lane270, 0)

  BUILTIN_VDQ_I (SHIFTIMM, ashr, 3)
  VAR1 (SHIFTIMM, ashr_simd, 0, di)
  BUILTIN_VDQ_I (SHIFTIMM, lshr, 3)
  VAR1 (USHIFTIMM, lshr_simd, 0, di)
  /* Implemented by aarch64_<sur>shr_n<mode>.  */
  BUILTIN_VSDQ_I_DI (SHIFTIMM, srshr_n, 0)
  BUILTIN_VSDQ_I_DI (USHIFTIMM, urshr_n, 0)
  /* Implemented by aarch64_<sur>sra_n<mode>.  */
  BUILTIN_VSDQ_I_DI (SHIFTACC, ssra_n, 0)
  BUILTIN_VSDQ_I_DI (USHIFTACC, usra_n, 0)
  BUILTIN_VSDQ_I_DI (SHIFTACC, srsra_n, 0)
  BUILTIN_VSDQ_I_DI (USHIFTACC, ursra_n, 0)
  /* Implemented by aarch64_<sur>shll_n<mode>.  */
  BUILTIN_VD_BHSI (SHIFTIMM, sshll_n, 0)
  BUILTIN_VD_BHSI (USHIFTIMM, ushll_n, 0)
  /* Implemented by aarch64_<sur>shll2_n<mode>.  */
  BUILTIN_VQW (SHIFTIMM, sshll2_n, 0)
  BUILTIN_VQW (SHIFTIMM, ushll2_n, 0)
  /* Implemented by aarch64_<sur>q<r>shr<u>n_n<mode>.  */
  BUILTIN_VSQN_HSDI (SHIFTIMM, sqshrun_n, 0)
  BUILTIN_VSQN_HSDI (SHIFTIMM, sqrshrun_n, 0)
  BUILTIN_VSQN_HSDI (SHIFTIMM, sqshrn_n, 0)
  BUILTIN_VSQN_HSDI (USHIFTIMM, uqshrn_n, 0)
  BUILTIN_VSQN_HSDI (SHIFTIMM, sqrshrn_n, 0)
  BUILTIN_VSQN_HSDI (USHIFTIMM, uqrshrn_n, 0)
  /* Implemented by aarch64_<sur>s<lr>i_n<mode>.  */
  BUILTIN_VSDQ_I_DI (SHIFTINSERT, ssri_n, 0)
  BUILTIN_VSDQ_I_DI (USHIFTACC, usri_n, 0)
  BUILTIN_VSDQ_I_DI (SHIFTINSERT, ssli_n, 0)
  VAR2 (SHIFTINSERTP, ssli_n, 0, di, v2di)
  BUILTIN_VSDQ_I_DI (USHIFTACC, usli_n, 0)
  /* Implemented by aarch64_<sur>qshl<u>_n<mode>.  */
  BUILTIN_VSDQ_I (SHIFTIMM_USS, sqshlu_n, 0)
  BUILTIN_VSDQ_I (SHIFTIMM, sqshl_n, 0)
  BUILTIN_VSDQ_I (USHIFTIMM, uqshl_n, 0)

  /* Implemented by aarch64_reduc_plus_<mode>.  */
  BUILTIN_VALL (UNOP, reduc_plus_scal_, 10)

  /* Implemented by reduc_<maxmin_uns>_scal_<mode> (producing scalar).  */
  BUILTIN_VDQIF_F16 (UNOP, reduc_smax_scal_, 10)
  BUILTIN_VDQIF_F16 (UNOP, reduc_smin_scal_, 10)
  BUILTIN_VDQ_BHSI (UNOPU, reduc_umax_scal_, 10)
  BUILTIN_VDQ_BHSI (UNOPU, reduc_umin_scal_, 10)
  BUILTIN_VHSDF (UNOP, reduc_smax_nan_scal_, 10)
  BUILTIN_VHSDF (UNOP, reduc_smin_nan_scal_, 10)

  /* Implemented by <maxmin_uns><mode>3.
     smax variants map to fmaxnm,
     smax_nan variants map to fmax.  */
  BUILTIN_VDQ_BHSI (BINOP, smax, 3)
  BUILTIN_VDQ_BHSI (BINOP, smin, 3)
  BUILTIN_VDQ_BHSI (BINOP, umax, 3)
  BUILTIN_VDQ_BHSI (BINOP, umin, 3)
  BUILTIN_VHSDF_DF (BINOP, smax_nan, 3)
  BUILTIN_VHSDF_DF (BINOP, smin_nan, 3)

  /* Implemented by <maxmin_uns><mode>3.  */
  BUILTIN_VHSDF_HSDF (BINOP, fmax, 3)
  BUILTIN_VHSDF_HSDF (BINOP, fmin, 3)

  /* Implemented by aarch64_<maxmin_uns>p<mode>.  */
  BUILTIN_VDQ_BHSI (BINOP, smaxp, 0)
  BUILTIN_VDQ_BHSI (BINOP, sminp, 0)
  BUILTIN_VDQ_BHSI (BINOP, umaxp, 0)
  BUILTIN_VDQ_BHSI (BINOP, uminp, 0)
  BUILTIN_VHSDF (BINOP, smaxp, 0)
  BUILTIN_VHSDF (BINOP, sminp, 0)
  BUILTIN_VHSDF (BINOP, smax_nanp, 0)
  BUILTIN_VHSDF (BINOP, smin_nanp, 0)

  /* Implemented by <frint_pattern><mode>2.  */
  BUILTIN_VHSDF (UNOP, btrunc, 2)
  BUILTIN_VHSDF (UNOP, ceil, 2)
  BUILTIN_VHSDF (UNOP, floor, 2)
  BUILTIN_VHSDF (UNOP, nearbyint, 2)
  BUILTIN_VHSDF (UNOP, rint, 2)
  BUILTIN_VHSDF (UNOP, round, 2)
  BUILTIN_VHSDF_DF (UNOP, frintn, 2)

  VAR1 (UNOP, btrunc, 2, hf)
  VAR1 (UNOP, ceil, 2, hf)
  VAR1 (UNOP, floor, 2, hf)
  VAR1 (UNOP, frintn, 2, hf)
  VAR1 (UNOP, nearbyint, 2, hf)
  VAR1 (UNOP, rint, 2, hf)
  VAR1 (UNOP, round, 2, hf)

  /* Implemented by l<fcvt_pattern><su_optab><VQDF:mode><vcvt_target>2.  */
  VAR1 (UNOP, lbtruncv4hf, 2, v4hi)
  VAR1 (UNOP, lbtruncv8hf, 2, v8hi)
  VAR1 (UNOP, lbtruncv2sf, 2, v2si)
  VAR1 (UNOP, lbtruncv4sf, 2, v4si)
  VAR1 (UNOP, lbtruncv2df, 2, v2di)

  VAR1 (UNOPUS, lbtruncuv4hf, 2, v4hi)
  VAR1 (UNOPUS, lbtruncuv8hf, 2, v8hi)
  VAR1 (UNOPUS, lbtruncuv2sf, 2, v2si)
  VAR1 (UNOPUS, lbtruncuv4sf, 2, v4si)
  VAR1 (UNOPUS, lbtruncuv2df, 2, v2di)

  VAR1 (UNOP, lroundv4hf, 2, v4hi)
  VAR1 (UNOP, lroundv8hf, 2, v8hi)
  VAR1 (UNOP, lroundv2sf, 2, v2si)
  VAR1 (UNOP, lroundv4sf, 2, v4si)
  VAR1 (UNOP, lroundv2df, 2, v2di)
  /* Implemented by l<fcvt_pattern><su_optab><GPF_F16:mode><GPI:mode>2.  */
  BUILTIN_GPI_I16 (UNOP, lroundhf, 2)
  VAR1 (UNOP, lroundsf, 2, si)
  VAR1 (UNOP, lrounddf, 2, di)

  VAR1 (UNOPUS, lrounduv4hf, 2, v4hi)
  VAR1 (UNOPUS, lrounduv8hf, 2, v8hi)
  VAR1 (UNOPUS, lrounduv2sf, 2, v2si)
  VAR1 (UNOPUS, lrounduv4sf, 2, v4si)
  VAR1 (UNOPUS, lrounduv2df, 2, v2di)
  BUILTIN_GPI_I16 (UNOPUS, lrounduhf, 2)
  VAR1 (UNOPUS, lroundusf, 2, si)
  VAR1 (UNOPUS, lroundudf, 2, di)

  VAR1 (UNOP, lceilv4hf, 2, v4hi)
  VAR1 (UNOP, lceilv8hf, 2, v8hi)
  VAR1 (UNOP, lceilv2sf, 2, v2si)
  VAR1 (UNOP, lceilv4sf, 2, v4si)
  VAR1 (UNOP, lceilv2df, 2, v2di)
  BUILTIN_GPI_I16 (UNOP, lceilhf, 2)

  VAR1 (UNOPUS, lceiluv4hf, 2, v4hi)
  VAR1 (UNOPUS, lceiluv8hf, 2, v8hi)
  VAR1 (UNOPUS, lceiluv2sf, 2, v2si)
  VAR1 (UNOPUS, lceiluv4sf, 2, v4si)
  VAR1 (UNOPUS, lceiluv2df, 2, v2di)
  BUILTIN_GPI_I16 (UNOPUS, lceiluhf, 2)
  VAR1 (UNOPUS, lceilusf, 2, si)
  VAR1 (UNOPUS, lceiludf, 2, di)

  VAR1 (UNOP, lfloorv4hf, 2, v4hi)
  VAR1 (UNOP, lfloorv8hf, 2, v8hi)
  VAR1 (UNOP, lfloorv2sf, 2, v2si)
  VAR1 (UNOP, lfloorv4sf, 2, v4si)
  VAR1 (UNOP, lfloorv2df, 2, v2di)
  BUILTIN_GPI_I16 (UNOP, lfloorhf, 2)

  VAR1 (UNOPUS, lflooruv4hf, 2, v4hi)
  VAR1 (UNOPUS, lflooruv8hf, 2, v8hi)
  VAR1 (UNOPUS, lflooruv2sf, 2, v2si)
  VAR1 (UNOPUS, lflooruv4sf, 2, v4si)
  VAR1 (UNOPUS, lflooruv2df, 2, v2di)
  BUILTIN_GPI_I16 (UNOPUS, lflooruhf, 2)
  VAR1 (UNOPUS, lfloorusf, 2, si)
  VAR1 (UNOPUS, lfloorudf, 2, di)

  VAR1 (UNOP, lfrintnv4hf, 2, v4hi)
  VAR1 (UNOP, lfrintnv8hf, 2, v8hi)
  VAR1 (UNOP, lfrintnv2sf, 2, v2si)
  VAR1 (UNOP, lfrintnv4sf, 2, v4si)
  VAR1 (UNOP, lfrintnv2df, 2, v2di)
  BUILTIN_GPI_I16 (UNOP, lfrintnhf, 2)
  VAR1 (UNOP, lfrintnsf, 2, si)
  VAR1 (UNOP, lfrintndf, 2, di)

  VAR1 (UNOPUS, lfrintnuv4hf, 2, v4hi)
  VAR1 (UNOPUS, lfrintnuv8hf, 2, v8hi)
  VAR1 (UNOPUS, lfrintnuv2sf, 2, v2si)
  VAR1 (UNOPUS, lfrintnuv4sf, 2, v4si)
  VAR1 (UNOPUS, lfrintnuv2df, 2, v2di)
  BUILTIN_GPI_I16 (UNOPUS, lfrintnuhf, 2)
  VAR1 (UNOPUS, lfrintnusf, 2, si)
  VAR1 (UNOPUS, lfrintnudf, 2, di)

  /* Implemented by <optab><fcvt_target><VDQF:mode>2.  */
  VAR1 (UNOP, floatv4hi, 2, v4hf)
  VAR1 (UNOP, floatv8hi, 2, v8hf)
  VAR1 (UNOP, floatv2si, 2, v2sf)
  VAR1 (UNOP, floatv4si, 2, v4sf)
  VAR1 (UNOP, floatv2di, 2, v2df)

  VAR1 (UNOP, floatunsv4hi, 2, v4hf)
  VAR1 (UNOP, floatunsv8hi, 2, v8hf)
  VAR1 (UNOP, floatunsv2si, 2, v2sf)
  VAR1 (UNOP, floatunsv4si, 2, v4sf)
  VAR1 (UNOP, floatunsv2di, 2, v2df)

  VAR5 (UNOPU, bswap, 2, v4hi, v8hi, v2si, v4si, v2di)

  BUILTIN_VB (UNOP, rbit, 0)

  /* Implemented by
     aarch64_<PERMUTE:perm_insn><PERMUTE:perm_hilo><mode>.  */
  BUILTIN_VALL (BINOP, zip1, 0)
  BUILTIN_VALL (BINOP, zip2, 0)
  BUILTIN_VALL (BINOP, uzp1, 0)
  BUILTIN_VALL (BINOP, uzp2, 0)
  BUILTIN_VALL (BINOP, trn1, 0)
  BUILTIN_VALL (BINOP, trn2, 0)

  BUILTIN_GPF_F16 (UNOP, frecpe, 0)
  BUILTIN_GPF_F16 (UNOP, frecpx, 0)

  BUILTIN_VDQ_SI (UNOP, urecpe, 0)

  BUILTIN_VHSDF (UNOP, frecpe, 0)
  BUILTIN_VHSDF_HSDF (BINOP, frecps, 0)

  /* Implemented by a mixture of abs2 patterns.  Note the DImode builtin is
     only ever used for the int64x1_t intrinsic, there is no scalar version.  */
  BUILTIN_VSDQ_I_DI (UNOP, abs, 0)
  BUILTIN_VHSDF (UNOP, abs, 2)
  VAR1 (UNOP, abs, 2, hf)

  BUILTIN_VQ_HSF (UNOP, vec_unpacks_hi_, 10)
  VAR1 (BINOP, float_truncate_hi_, 0, v4sf)
  VAR1 (BINOP, float_truncate_hi_, 0, v8hf)

  VAR1 (UNOP, float_extend_lo_, 0, v2df)
  VAR1 (UNOP, float_extend_lo_,  0, v4sf)
  BUILTIN_VDF (UNOP, float_truncate_lo_, 0)

  /* Implemented by aarch64_ld1<VALL_F16:mode>.  */
  BUILTIN_VALL_F16 (LOAD1, ld1, 0)
  VAR1(STORE1P, ld1, 0, v2di)

  /* Implemented by aarch64_st1<VALL_F16:mode>.  */
  BUILTIN_VALL_F16 (STORE1, st1, 0)
  VAR1(STORE1P, st1, 0, v2di)

  /* Implemented by aarch64_ld1x3<VALLDIF:mode>.  */
  BUILTIN_VALLDIF (LOADSTRUCT, ld1x3, 0)

  /* Implemented by aarch64_st1x2<VALLDIF:mode>.  */
  BUILTIN_VALLDIF (STORESTRUCT, st1x2, 0)

  /* Implemented by aarch64_st1x3<VALLDIF:mode>.  */
  BUILTIN_VALLDIF (STORESTRUCT, st1x3, 0)

  /* Implemented by fma<mode>4.  */
  BUILTIN_VHSDF (TERNOP, fma, 4)
  VAR1 (TERNOP, fma, 4, hf)
  /* Implemented by fnma<mode>4.  */
  BUILTIN_VHSDF (TERNOP, fnma, 4)
  VAR1 (TERNOP, fnma, 4, hf)

  /* Implemented by aarch64_simd_bsl<mode>.  */
  BUILTIN_VDQQH (BSL_P, simd_bsl, 0)
  VAR2 (BSL_P, simd_bsl,0, di, v2di)
  BUILTIN_VSDQ_I_DI (BSL_U, simd_bsl, 0)
  BUILTIN_VALLDIF (BSL_S, simd_bsl, 0)

  /* Implemented by aarch64_crypto_aes<op><mode>.  */
  VAR1 (BINOPU, crypto_aese, 0, v16qi)
  VAR1 (BINOPU, crypto_aesd, 0, v16qi)
  VAR1 (UNOPU, crypto_aesmc, 0, v16qi)
  VAR1 (UNOPU, crypto_aesimc, 0, v16qi)

  /* Implemented by aarch64_crypto_sha1<op><mode>.  */
  VAR1 (UNOPU, crypto_sha1h, 0, si)
  VAR1 (BINOPU, crypto_sha1su1, 0, v4si)
  VAR1 (TERNOPU, crypto_sha1c, 0, v4si)
  VAR1 (TERNOPU, crypto_sha1m, 0, v4si)
  VAR1 (TERNOPU, crypto_sha1p, 0, v4si)
  VAR1 (TERNOPU, crypto_sha1su0, 0, v4si)

  /* Implemented by aarch64_crypto_sha256<op><mode>.  */
  VAR1 (TERNOPU, crypto_sha256h, 0, v4si)
  VAR1 (TERNOPU, crypto_sha256h2, 0, v4si)
  VAR1 (BINOPU, crypto_sha256su0, 0, v4si)
  VAR1 (TERNOPU, crypto_sha256su1, 0, v4si)

  /* Implemented by aarch64_crypto_pmull<mode>.  */
  VAR1 (BINOPP, crypto_pmull, 0, di)
  VAR1 (BINOPP, crypto_pmull, 0, v2di)

  /* Implemented by aarch64_tbl3<mode>.  */
  VAR1 (BINOP, tbl3, 0, v8qi)
  VAR1 (BINOP, tbl3, 0, v16qi)

  /* Implemented by aarch64_qtbl3<mode>.  */
  VAR1 (BINOP, qtbl3, 0, v8qi)
  VAR1 (BINOP, qtbl3, 0, v16qi)

  /* Implemented by aarch64_qtbl4<mode>.  */
  VAR1 (BINOP, qtbl4, 0, v8qi)
  VAR1 (BINOP, qtbl4, 0, v16qi)

  /* Implemented by aarch64_tbx4<mode>.  */
  VAR1 (TERNOP, tbx4, 0, v8qi)
  VAR1 (TERNOP, tbx4, 0, v16qi)

  /* Implemented by aarch64_qtbx3<mode>.  */
  VAR1 (TERNOP, qtbx3, 0, v8qi)
  VAR1 (TERNOP, qtbx3, 0, v16qi)

  /* Implemented by aarch64_qtbx4<mode>.  */
  VAR1 (TERNOP, qtbx4, 0, v8qi)
  VAR1 (TERNOP, qtbx4, 0, v16qi)

  /* Builtins for ARMv8.1-A Adv.SIMD instructions.  */

  /* Implemented by aarch64_sqrdml<SQRDMLH_AS:rdma_as>h<mode>.  */
  BUILTIN_VSDQ_HSI (TERNOP, sqrdmlah, 0)
  BUILTIN_VSDQ_HSI (TERNOP, sqrdmlsh, 0)

  /* Implemented by aarch64_sqrdml<SQRDMLH_AS:rdma_as>h_lane<mode>.  */
  BUILTIN_VSDQ_HSI (QUADOP_LANE, sqrdmlah_lane, 0)
  BUILTIN_VSDQ_HSI (QUADOP_LANE, sqrdmlsh_lane, 0)

  /* Implemented by aarch64_sqrdml<SQRDMLH_AS:rdma_as>h_laneq<mode>.  */
  BUILTIN_VSDQ_HSI (QUADOP_LANE, sqrdmlah_laneq, 0)
  BUILTIN_VSDQ_HSI (QUADOP_LANE, sqrdmlsh_laneq, 0)

  /* Implemented by <FCVT_F2FIXED/FIXED2F:fcvt_fixed_insn><*><*>3.  */
  BUILTIN_VSDQ_HSDI (SHIFTIMM, scvtf, 3)
  BUILTIN_VSDQ_HSDI (FCVTIMM_SUS, ucvtf, 3)
  BUILTIN_VHSDF_HSDF (SHIFTIMM, fcvtzs, 3)
  BUILTIN_VHSDF_HSDF (SHIFTIMM_USS, fcvtzu, 3)
  VAR1 (SHIFTIMM, scvtfsi, 3, hf)
  VAR1 (SHIFTIMM, scvtfdi, 3, hf)
  VAR1 (FCVTIMM_SUS, ucvtfsi, 3, hf)
  VAR1 (FCVTIMM_SUS, ucvtfdi, 3, hf)
  BUILTIN_GPI (SHIFTIMM, fcvtzshf, 3)
  BUILTIN_GPI (SHIFTIMM_USS, fcvtzuhf, 3)

  /* Implemented by aarch64_rsqrte<mode>.  */
  BUILTIN_VHSDF_HSDF (UNOP, rsqrte, 0)

  /* Implemented by aarch64_rsqrts<mode>.  */
  BUILTIN_VHSDF_HSDF (BINOP, rsqrts, 0)

  /* Implemented by fabd<mode>3.  */
  BUILTIN_VHSDF_HSDF (BINOP, fabd, 3)

  /* Implemented by aarch64_faddp<mode>.  */
  BUILTIN_VHSDF (BINOP, faddp, 0)

  /* Implemented by aarch64_cm<optab><mode>.  */
  BUILTIN_VHSDF_HSDF (BINOP_USS, cmeq, 0)
  BUILTIN_VHSDF_HSDF (BINOP_USS, cmge, 0)
  BUILTIN_VHSDF_HSDF (BINOP_USS, cmgt, 0)
  BUILTIN_VHSDF_HSDF (BINOP_USS, cmle, 0)
  BUILTIN_VHSDF_HSDF (BINOP_USS, cmlt, 0)

  /* Implemented by neg<mode>2.  */
  BUILTIN_VHSDF_HSDF (UNOP, neg, 2)

  /* Implemented by aarch64_fac<optab><mode>.  */
  BUILTIN_VHSDF_HSDF (BINOP_USS, faclt, 0)
  BUILTIN_VHSDF_HSDF (BINOP_USS, facle, 0)
  BUILTIN_VHSDF_HSDF (BINOP_USS, facgt, 0)
  BUILTIN_VHSDF_HSDF (BINOP_USS, facge, 0)

  /* Implemented by sqrt<mode>2.  */
  VAR1 (UNOP, sqrt, 2, hf)

  /* Implemented by <optab><mode>hf2.  */
  VAR1 (UNOP, floatdi, 2, hf)
  VAR1 (UNOP, floatsi, 2, hf)
  VAR1 (UNOP, floathi, 2, hf)
  VAR1 (UNOPUS, floatunsdi, 2, hf)
  VAR1 (UNOPUS, floatunssi, 2, hf)
  VAR1 (UNOPUS, floatunshi, 2, hf)
  BUILTIN_GPI_I16 (UNOP, fix_trunchf, 2)
  BUILTIN_GPI (UNOP, fix_truncsf, 2)
  BUILTIN_GPI (UNOP, fix_truncdf, 2)
  BUILTIN_GPI_I16 (UNOPUS, fixuns_trunchf, 2)
  BUILTIN_GPI (UNOPUS, fixuns_truncsf, 2)
  BUILTIN_GPI (UNOPUS, fixuns_truncdf, 2)

  /* Implemented by aarch64_sm3ss1qv4si.  */
  VAR1 (TERNOPU, sm3ss1q, 0, v4si)
  /* Implemented by aarch64_sm3tt<sm3tt_op>qv4si.  */
  VAR1 (QUADOPUI, sm3tt1aq, 0, v4si)
  VAR1 (QUADOPUI, sm3tt1bq, 0, v4si)
  VAR1 (QUADOPUI, sm3tt2aq, 0, v4si)
  VAR1 (QUADOPUI, sm3tt2bq, 0, v4si)
  /* Implemented by aarch64_sm3partw<sm3part_op>qv4si.  */
  VAR1 (TERNOPU, sm3partw1q, 0, v4si)
  VAR1 (TERNOPU, sm3partw2q, 0, v4si)
  /* Implemented by aarch64_sm4eqv4si.  */
  VAR1 (BINOPU, sm4eq, 0, v4si)
  /* Implemented by aarch64_sm4ekeyqv4si.  */
  VAR1 (BINOPU, sm4ekeyq, 0, v4si)
  /* Implemented by aarch64_crypto_sha512hqv2di.  */
  VAR1 (TERNOPU, crypto_sha512hq, 0, v2di)
  /* Implemented by aarch64_sha512h2qv2di.  */
  VAR1 (TERNOPU, crypto_sha512h2q, 0, v2di)
  /* Implemented by aarch64_crypto_sha512su0qv2di.  */
  VAR1 (BINOPU, crypto_sha512su0q, 0, v2di)
  /* Implemented by aarch64_crypto_sha512su1qv2di.  */
  VAR1 (TERNOPU, crypto_sha512su1q, 0, v2di)
  /* Implemented by eor3q<mode>4.  */
  BUILTIN_VQ_I (TERNOPU, eor3q, 4)
  BUILTIN_VQ_I (TERNOP, eor3q, 4)
  /* Implemented by aarch64_rax1qv2di.  */
  VAR1 (BINOPU, rax1q, 0, v2di)
  /* Implemented by aarch64_xarqv2di.  */
  VAR1 (TERNOPUI, xarq, 0, v2di)
  /* Implemented by bcaxq<mode>4.  */
  BUILTIN_VQ_I (TERNOPU, bcaxq, 4)
  BUILTIN_VQ_I (TERNOP, bcaxq, 4)

  /* Implemented by aarch64_fml<f16mac1>l<f16quad>_low<mode>.  */
  VAR1 (TERNOP, fmlal_low, 0, v2sf)
  VAR1 (TERNOP, fmlsl_low, 0, v2sf)
  VAR1 (TERNOP, fmlalq_low, 0, v4sf)
  VAR1 (TERNOP, fmlslq_low, 0, v4sf)
  /* Implemented by aarch64_fml<f16mac1>l<f16quad>_high<mode>.  */
  VAR1 (TERNOP, fmlal_high, 0, v2sf)
  VAR1 (TERNOP, fmlsl_high, 0, v2sf)
  VAR1 (TERNOP, fmlalq_high, 0, v4sf)
  VAR1 (TERNOP, fmlslq_high, 0, v4sf)
  /* Implemented by aarch64_fml<f16mac1>l_lane_lowv2sf.  */
  VAR1 (QUADOP_LANE, fmlal_lane_low, 0, v2sf)
  VAR1 (QUADOP_LANE, fmlsl_lane_low, 0, v2sf)
  /* Implemented by aarch64_fml<f16mac1>l_laneq_lowv2sf.  */
  VAR1 (QUADOP_LANE, fmlal_laneq_low, 0, v2sf)
  VAR1 (QUADOP_LANE, fmlsl_laneq_low, 0, v2sf)
  /* Implemented by aarch64_fml<f16mac1>lq_lane_lowv4sf.  */
  VAR1 (QUADOP_LANE, fmlalq_lane_low, 0, v4sf)
  VAR1 (QUADOP_LANE, fmlslq_lane_low, 0, v4sf)
  /* Implemented by aarch64_fml<f16mac1>lq_laneq_lowv4sf.  */
  VAR1 (QUADOP_LANE, fmlalq_laneq_low, 0, v4sf)
  VAR1 (QUADOP_LANE, fmlslq_laneq_low, 0, v4sf)
  /* Implemented by aarch64_fml<f16mac1>l_lane_highv2sf.  */
  VAR1 (QUADOP_LANE, fmlal_lane_high, 0, v2sf)
  VAR1 (QUADOP_LANE, fmlsl_lane_high, 0, v2sf)
  /* Implemented by aarch64_fml<f16mac1>l_laneq_highv2sf.  */
  VAR1 (QUADOP_LANE, fmlal_laneq_high, 0, v2sf)
  VAR1 (QUADOP_LANE, fmlsl_laneq_high, 0, v2sf)
  /* Implemented by aarch64_fml<f16mac1>lq_lane_highv4sf.  */
  VAR1 (QUADOP_LANE, fmlalq_lane_high, 0, v4sf)
  VAR1 (QUADOP_LANE, fmlslq_lane_high, 0, v4sf)
  /* Implemented by aarch64_fml<f16mac1>lq_laneq_highv4sf.  */
  VAR1 (QUADOP_LANE, fmlalq_laneq_high, 0, v4sf)
  VAR1 (QUADOP_LANE, fmlslq_laneq_high, 0, v4sf)