source/libs/gmp/gmp-src/mpn/pa32/hppa1_1/sqr_diagonal.asm

   1 dnl  HP-PA 1.1 32-bit mpn_sqr_diagonal.
   2
   3 dnl  Copyright 2001, 2002 Free Software Foundation, Inc.
   4
   5 dnl  This file is part of the GNU MP Library.
   6 dnl
   7 dnl  The GNU MP Library is free software; you can redistribute it and/or modify
   8 dnl  it under the terms of either:
   9 dnl
  10 dnl    * the GNU Lesser General Public License as published by the Free
  11 dnl      Software Foundation; either version 3 of the License, or (at your
  12 dnl      option) any later version.
  13 dnl
  14 dnl  or
  15 dnl
  16 dnl    * the GNU General Public License as published by the Free Software
  17 dnl      Foundation; either version 2 of the License, or (at your option) any
  18 dnl      later version.
  19 dnl
  20 dnl  or both in parallel, as here.
  21 dnl
  22 dnl  The GNU MP Library is distributed in the hope that it will be useful, but
  23 dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
  24 dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  25 dnl  for more details.
  26 dnl
  27 dnl  You should have received copies of the GNU General Public License and the
  28 dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
  29 dnl  see https://www.gnu.org/licenses/.
  30
  31 include(`../config.m4')
  32
  33 C This code runs at 6 cycles/limb on the PA7100 and 2.5 cycles/limb on PA8x00.
  34 C 2-way unrolling wouldn't help the PA7100; it could however bring times down
  35 C to 2.0 cycles/limb for the PA8x00.
  36
  37 C INPUT PARAMETERS
  38 define(`rp',`%r26')
  39 define(`up',`%r25')
  40 define(`n',`%r24')
  41
  42 ASM_START()
  43 PROLOGUE(mpn_sqr_diagonal)
  44         ldo             4(rp),rp
  45         fldws,ma        4(up),%fr4r
  46         addib,=         -1,n,L(exit)
  47         xmpyu           %fr4r,%fr4r,%fr5
  48
  49 LDEF(loop)
  50         fldws,ma        4(up),%fr4r
  51         fstws           %fr5r,-4(rp)
  52         fstws,ma        %fr5l,8(rp)
  53         addib,<>        -1,n,L(loop)
  54         xmpyu           %fr4r,%fr4r,%fr5
  55
  56 LDEF(exit)
  57         fstws           %fr5r,-4(rp)
  58         bv              0(%r2)
  59         fstws           %fr5l,0(rp)
  60 EPILOGUE(mpn_sqr_diagonal)