source/libs/gmp/gmp-src/mpn/powerpc32/750/com.asm

   1 dnl  PowerPC 750 mpn_com -- mpn bitwise one's complement
   2
   3 dnl  Copyright 2002, 2003 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
  34 C                cycles/limb
  35 C 603e:            ?
  36 C 604e:            3.0
  37 C 75x (G3):        2.0
  38 C 7400,7410 (G4):  2.0
  39 C 744x,745x (G4+): 3.0
  40
  41 C void mpn_com (mp_ptr dst, mp_srcptr src, mp_size_t size);
  42 C
  43 C This loop form is necessary for the claimed speed.
  44
  45 ASM_START()
  46 PROLOGUE(mpn_com)
  47
  48         C r3    dst
  49         C r4    src
  50         C r5    size
  51
  52         mtctr   r5              C size
  53         lwz     r5, 0(r4)       C src low limb
  54
  55         sub     r4, r4, r3      C src-dst
  56         subi    r3, r3, 4       C dst-4
  57
  58         addi    r4, r4, 8       C src-dst+8
  59         bdz     L(one)
  60
  61 L(top):
  62         C r3    &dst[i-1]
  63         C r4    src-dst
  64         C r5    src[i]
  65         C r6    scratch
  66
  67         not     r6, r5          C ~src[i]
  68         lwzx    r5, r4,r3       C src[i+1]
  69
  70         stwu    r6, 4(r3)       C dst[i]
  71         bdnz    L(top)
  72
  73 L(one):
  74         not     r6, r5
  75
  76         stw     r6, 4(r3)       C dst[size-1]
  77         blr
  78
  79 EPILOGUE()