diff options
author | Roland McGrath <roland@gnu.org> | 1995-02-18 01:27:10 +0000 |
---|---|---|
committer | Roland McGrath <roland@gnu.org> | 1995-02-18 01:27:10 +0000 |
commit | 28f540f45bbacd939bfd07f213bcad2bf730b1bf (patch) | |
tree | 15f07c4c43d635959c6afee96bde71fb1b3614ee /sysdeps/i386/add_n.S | |
download | glibc-28f540f45bbacd939bfd07f213bcad2bf730b1bf.tar.gz glibc-28f540f45bbacd939bfd07f213bcad2bf730b1bf.tar.bz2 glibc-28f540f45bbacd939bfd07f213bcad2bf730b1bf.zip |
initial import
Diffstat (limited to 'sysdeps/i386/add_n.S')
-rw-r--r-- | sysdeps/i386/add_n.S | 94 |
1 files changed, 94 insertions, 0 deletions
diff --git a/sysdeps/i386/add_n.S b/sysdeps/i386/add_n.S new file mode 100644 index 0000000000..f528976866 --- /dev/null +++ b/sysdeps/i386/add_n.S @@ -0,0 +1,94 @@ +/* i80386 __mpn_add_n -- Add two limb vectors of the same length > 0 and store +sum in a third limb vector. + +Copyright (C) 1992, 1994 Free Software Foundation, Inc. + +This file is part of the GNU MP Library. + +The GNU MP Library is free software; you can redistribute it and/or modify +it under the terms of the GNU Library General Public License as published by +the Free Software Foundation; either version 2 of the License, or (at your +option) any later version. + +The GNU MP Library is distributed in the hope that it will be useful, but +WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Library General Public +License for more details. + +You should have received a copy of the GNU Library General Public License +along with the GNU MP Library; see the file COPYING.LIB. If not, write to +the Free Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ + +/* + INPUT PARAMETERS + res_ptr (sp + 4) + s1_ptr (sp + 8) + s2_ptr (sp + 12) + size (sp + 16) +*/ + +#include "sysdep.h" +#include "asm-syntax.h" + +.text + ALIGN (3) + .globl C_SYMBOL_NAME(__mpn_add_n) +C_SYMBOL_NAME(__mpn_add_n:) + pushl %edi + pushl %esi + + movl 12(%esp),%edi /* res_ptr */ + movl 16(%esp),%esi /* s1_ptr */ + movl 20(%esp),%edx /* s2_ptr */ + movl 24(%esp),%ecx /* size */ + + movl %ecx,%eax + shrl $3,%ecx /* compute count for unrolled loop */ + negl %eax + andl $7,%eax /* get index where to start loop */ + jz Loop /* necessary special case for 0 */ + incl %ecx /* adjust loop count */ + shll $2,%eax /* adjustment for pointers... */ + subl %eax,%edi /* ... since they are offset ... */ + subl %eax,%esi /* ... by a constant when we ... */ + subl %eax,%edx /* ... enter the loop */ + shrl $2,%eax /* restore previous value */ + leal (Loop - 3)(%eax,%eax,8),%eax /* calc start addr in loop */ + jmp *%eax /* jump into loop */ + ALIGN (3) +Loop: movl (%esi),%eax + adcl (%edx),%eax + movl %eax,(%edi) + movl 4(%esi),%eax + adcl 4(%edx),%eax + movl %eax,4(%edi) + movl 8(%esi),%eax + adcl 8(%edx),%eax + movl %eax,8(%edi) + movl 12(%esi),%eax + adcl 12(%edx),%eax + movl %eax,12(%edi) + movl 16(%esi),%eax + adcl 16(%edx),%eax + movl %eax,16(%edi) + movl 20(%esi),%eax + adcl 20(%edx),%eax + movl %eax,20(%edi) + movl 24(%esi),%eax + adcl 24(%edx),%eax + movl %eax,24(%edi) + movl 28(%esi),%eax + adcl 28(%edx),%eax + movl %eax,28(%edi) + leal 32(%edi),%edi + leal 32(%esi),%esi + leal 32(%edx),%edx + decl %ecx + jnz Loop + + sbbl %eax,%eax + negl %eax + + popl %esi + popl %edi + ret |