source/libs/gmp/gmp-src/mpn/pa32/add_n.asm

   1 dnl  HP-PA mpn_add_n -- Add two limb vectors of the same length > 0 and store
   2 dnl  sum in a third limb vector.
   3
   4 dnl  Copyright 1992, 1994, 2000-2002 Free Software Foundation, Inc.
   5
   6 dnl  This file is part of the GNU MP Library.
   7 dnl
   8 dnl  The GNU MP Library is free software; you can redistribute it and/or modify
   9 dnl  it under the terms of either:
  10 dnl
  11 dnl    * the GNU Lesser General Public License as published by the Free
  12 dnl      Software Foundation; either version 3 of the License, or (at your
  13 dnl      option) any later version.
  14 dnl
  15 dnl  or
  16 dnl
  17 dnl    * the GNU General Public License as published by the Free Software
  18 dnl      Foundation; either version 2 of the License, or (at your option) any
  19 dnl      later version.
  20 dnl
  21 dnl  or both in parallel, as here.
  22 dnl
  23 dnl  The GNU MP Library is distributed in the hope that it will be useful, but
  24 dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
  25 dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  26 dnl  for more details.
  27 dnl
  28 dnl  You should have received copies of the GNU General Public License and the
  29 dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
  30 dnl  see https://www.gnu.org/licenses/.
  31
  32 include(`../config.m4')
  33
  34 C INPUT PARAMETERS
  35 C res_ptr       gr26
  36 C s1_ptr        gr25
  37 C s2_ptr        gr24
  38 C size          gr23
  39
  40 C One might want to unroll this as for other processors, but it turns out that
  41 C the data cache contention after a store makes such unrolling useless.  We
  42 C can't come under 5 cycles/limb anyway.
  43
  44 ASM_START()
  45 PROLOGUE(mpn_add_n)
  46         ldws,ma         4(0,%r25),%r20
  47         ldws,ma         4(0,%r24),%r19
  48
  49         addib,=         -1,%r23,L(end)  C check for (SIZE == 1)
  50          add            %r20,%r19,%r28  C add first limbs ignoring cy
  51
  52 LDEF(loop)
  53         ldws,ma         4(0,%r25),%r20
  54         ldws,ma         4(0,%r24),%r19
  55         stws,ma         %r28,4(0,%r26)
  56         addib,<>        -1,%r23,L(loop)
  57          addc           %r20,%r19,%r28
  58
  59 LDEF(end)
  60         stws            %r28,0(0,%r26)
  61         bv              0(%r2)
  62          addc           %r0,%r0,%r28
  63 EPILOGUE()