diff options
Diffstat (limited to 'rts/gmp/mpn/x86/copyd.asm')
| -rw-r--r-- | rts/gmp/mpn/x86/copyd.asm | 80 |
1 files changed, 80 insertions, 0 deletions
diff --git a/rts/gmp/mpn/x86/copyd.asm b/rts/gmp/mpn/x86/copyd.asm new file mode 100644 index 0000000000..439640e836 --- /dev/null +++ b/rts/gmp/mpn/x86/copyd.asm @@ -0,0 +1,80 @@ +dnl x86 mpn_copyd -- copy limb vector, decrementing. +dnl +dnl Future: On P6 an MMX loop should be able to go faster than this code. + + +dnl Copyright (C) 1999, 2000 Free Software Foundation, Inc. +dnl +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or +dnl modify it under the terms of the GNU Lesser General Public License as +dnl published by the Free Software Foundation; either version 2.1 of the +dnl License, or (at your option) any later version. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, +dnl but WITHOUT ANY WARRANTY; without even the implied warranty of +dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +dnl Lesser General Public License for more details. +dnl +dnl You should have received a copy of the GNU Lesser General Public +dnl License along with the GNU MP Library; see the file COPYING.LIB. If +dnl not, write to the Free Software Foundation, Inc., 59 Temple Place - +dnl Suite 330, Boston, MA 02111-1307, USA. + + +include(`../config.m4') + + +C void mpn_copyd (mp_ptr dst, mp_srcptr src, mp_size_t size); +C +C Copy src,size to dst,size, working from high to low addresses. +C +C The code here is very generic and can be expected to be reasonable on all +C the x86 family. +C +C P5 - 1.0 cycles/limb. +C +C P6 - 2.4 cycles/limb, approx 40 cycles startup. + +defframe(PARAM_SIZE,12) +defframe(PARAM_SRC, 8) +defframe(PARAM_DST, 4) +deflit(`FRAME',0) + + .text + ALIGN(32) + +PROLOGUE(mpn_copyd) + C eax saved esi + C ebx + C ecx counter + C edx saved edi + C esi src + C edi dst + C ebp + + movl PARAM_SIZE, %ecx + movl %esi, %eax + + movl PARAM_SRC, %esi + movl %edi, %edx + + movl PARAM_DST, %edi + leal -4(%esi,%ecx,4), %esi + + leal -4(%edi,%ecx,4), %edi + + std + + rep + movsl + + cld + + movl %eax, %esi + movl %edx, %edi + + ret + +EPILOGUE() |