/* Pentium __mpn_sub_n -- Subtract two limb vectors of the same length > 0
   and store difference in a third limb vector.
   Copyright (C) 1992, 94, 95, 96, 97, 98, 2000 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 Lesser General Public License as published by
   the Free Software Foundation; either version 2.1 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 Lesser General Public
   License for more details.

   You should have received a copy of the GNU Lesser General Public License
   along with the GNU MP Library; see the file COPYING.LIB.  If not, write to
   the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
   MA 02111-1307, USA. */

#include "sysdep.h"
#include "asm-syntax.h"
#include "bp-sym.h"
#include "bp-asm.h"

#define PARMS   LINKAGE+16              /* space for 4 saved regs */
#define RES     PARMS
#define S1      RES+PTR_SIZE
#define S2      S1+PTR_SIZE
#define SIZE    S2+PTR_SIZE

        .text
ENTRY (BP_SYM (__mpn_sub_n))
        ENTER

        pushl   %edi
        pushl   %esi
        pushl   %ebp
        pushl   %ebx

        movl    RES(%esp),%edi
        movl    S1(%esp),%esi
        movl    S2(%esp),%ebx
        movl    SIZE(%esp),%ecx
#if __BOUNDED_POINTERS__
        shll    $2, %ecx        /* convert limbs to bytes */
        CHECK_BOUNDS_BOTH_WIDE (%edi, RES(%esp), %ecx)
        CHECK_BOUNDS_BOTH_WIDE (%esi, S1(%esp), %ecx)
        CHECK_BOUNDS_BOTH_WIDE (%ebx, S2(%esp), %ecx)
        shrl    $2, %ecx
#endif
        movl    (%ebx),%ebp

        decl    %ecx
        movl    %ecx,%edx
        shrl    $3,%ecx
        andl    $7,%edx
        testl   %ecx,%ecx               /* zero carry flag */
        jz      L(end)
        pushl   %edx

        ALIGN (3)
L(oop): movl    28(%edi),%eax           /* fetch destination cache line */
        leal    32(%edi),%edi

L(1):   movl    (%esi),%eax
        movl    4(%esi),%edx
        sbbl    %ebp,%eax
        movl    4(%ebx),%ebp
        sbbl    %ebp,%edx
        movl    8(%ebx),%ebp
        movl    %eax,-32(%edi)
        movl    %edx,-28(%edi)

L(2):   movl    8(%esi),%eax
        movl    12(%esi),%edx
        sbbl    %ebp,%eax
        movl    12(%ebx),%ebp
        sbbl    %ebp,%edx
        movl    16(%ebx),%ebp
        movl    %eax,-24(%edi)
        movl    %edx,-20(%edi)

L(3):   movl    16(%esi),%eax
        movl    20(%esi),%edx
        sbbl    %ebp,%eax
        movl    20(%ebx),%ebp
        sbbl    %ebp,%edx
        movl    24(%ebx),%ebp
        movl    %eax,-16(%edi)
        movl    %edx,-12(%edi)

L(4):   movl    24(%esi),%eax
        movl    28(%esi),%edx
        sbbl    %ebp,%eax
        movl    28(%ebx),%ebp
        sbbl    %ebp,%edx
        movl    32(%ebx),%ebp
        movl    %eax,-8(%edi)
        movl    %edx,-4(%edi)

        leal    32(%esi),%esi
        leal    32(%ebx),%ebx
        decl    %ecx
        jnz     L(oop)

        popl    %edx
L(end):
        decl    %edx                    /* test %edx w/o clobbering carry */
        js      L(end2)
        incl    %edx
L(oop2):
        leal    4(%edi),%edi
        movl    (%esi),%eax
        sbbl    %ebp,%eax
        movl    4(%ebx),%ebp
        movl    %eax,-4(%edi)
        leal    4(%esi),%esi
        leal    4(%ebx),%ebx
        decl    %edx
        jnz     L(oop2)
L(end2):
        movl    (%esi),%eax
        sbbl    %ebp,%eax
        movl    %eax,(%edi)

        sbbl    %eax,%eax
        negl    %eax

        popl    %ebx
        popl    %ebp
        popl    %esi
        popl    %edi

        LEAVE
        ret
END (BP_SYM (__mpn_sub_n))