source/libs/gmp/gmp-src/mpn/x86/copyi.asm

   1 dnl  x86 mpn_copyi -- copy limb vector, incrementing.
   2
   3 dnl  Copyright 1999-2002 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
  34 C     cycles/limb  startup (approx)
  35 C P5      1.0         35
  36 C P6      0.75        45
  37 C K6      1.0         30
  38 C K7      1.3         65
  39 C P4      1.0        120
  40 C
  41 C (Startup time includes some function call overheads.)
  42
  43
  44 C void mpn_copyi (mp_ptr dst, mp_srcptr src, mp_size_t size);
  45 C
  46 C Copy src,size to dst,size, working from low to high addresses.
  47 C
  48 C The code here is very generic and can be expected to be reasonable on all
  49 C the x86 family.
  50 C
  51 C P6 -  An MMX based copy was tried, but was found to be slower than a rep
  52 C       movs in all cases.  The fastest MMX found was 0.8 cycles/limb (when
  53 C       fully aligned).  A rep movs seems to have a startup time of about 15
  54 C       cycles, but doing something special for small sizes could lead to a
  55 C       branch misprediction that would destroy any saving.  For now a plain
  56 C       rep movs seems ok.
  57 C
  58 C K62 - We used to have a big chunk of code doing an MMX copy at 0.56 c/l if
  59 C       aligned or a 1.0 rep movs if not.  But that seemed excessive since
  60 C       it only got an advantage half the time, and even then only showed it
  61 C       above 50 limbs or so.
  62
  63 defframe(PARAM_SIZE,12)
  64 defframe(PARAM_SRC, 8)
  65 defframe(PARAM_DST, 4)
  66 deflit(`FRAME',0)
  67
  68         TEXT
  69         ALIGN(32)
  70
  71         C eax   saved esi
  72         C ebx
  73         C ecx   counter
  74         C edx   saved edi
  75         C esi   src
  76         C edi   dst
  77         C ebp
  78
  79 PROLOGUE(mpn_copyi)
  80
  81         movl    PARAM_SIZE, %ecx
  82         movl    %esi, %eax
  83
  84         movl    PARAM_SRC, %esi
  85         movl    %edi, %edx
  86
  87         movl    PARAM_DST, %edi
  88
  89         cld     C better safe than sorry, see mpn/x86/README
  90
  91         rep
  92         movsl
  93
  94         movl    %eax, %esi
  95         movl    %edx, %edi
  96
  97         ret
  98
  99 EPILOGUE()