/* i80586 sub_n -- Sub two limb vectors of the same length > 0 and store
 *		   sum in a third limb vector.
 *
 *      Copyright (C) 1992, 1994, 1995, 1998, 
 *                    2001, 2002 Free Software Foundation, Inc.
 *
 * This file is part of Libgcrypt.
 *
 * Libgcrypt 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.
 *
 * Libgcrypt 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 this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
 *
 * Note: This code is heavily based on the GNU MP Library.
 *	 Actually it's the same code with only minor changes in the
 *	 way the data is stored; this is to support the abstraction
 *	 of an optional secure memory allocation which may be used
 *	 to avoid revealing of sensitive data due to paging etc.
 */


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


/*******************
 *  mpi_limb_t
 *  _gcry_mpih_sub_n( mpi_ptr_t res_ptr,	(sp + 4)
 *		   mpi_ptr_t s1_ptr,	(sp + 8)
 *		   mpi_ptr_t s2_ptr,	(sp + 12)
 *		   mpi_size_t size)	(sp + 16)
 */


.text
	ALIGN (3)
	.globl C_SYMBOL_NAME(_gcry_mpih_sub_n)
C_SYMBOL_NAME(_gcry_mpih_sub_n:)

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

	movl	20(%esp),%edi		/* res_ptr */
	movl	24(%esp),%esi		/* s1_ptr */
	movl	28(%esp),%ebp		/* s2_ptr */
	movl	32(%esp),%ecx		/* size */

	movl	(%ebp),%ebx

	decl	%ecx
	movl	%ecx,%edx
	shrl	$3,%ecx
	andl	$7,%edx
	testl	%ecx,%ecx		/* zero carry flag */
	jz	Lend
	pushl	%edx

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

L1:	movl	(%esi),%eax
	movl	4(%esi),%edx
	sbbl	%ebx,%eax
	movl	4(%ebp),%ebx
	sbbl	%ebx,%edx
	movl	8(%ebp),%ebx
	movl	%eax,-32(%edi)
	movl	%edx,-28(%edi)

L2:	movl	8(%esi),%eax
	movl	12(%esi),%edx
	sbbl	%ebx,%eax
	movl	12(%ebp),%ebx
	sbbl	%ebx,%edx
	movl	16(%ebp),%ebx
	movl	%eax,-24(%edi)
	movl	%edx,-20(%edi)

L3:	movl	16(%esi),%eax
	movl	20(%esi),%edx
	sbbl	%ebx,%eax
	movl	20(%ebp),%ebx
	sbbl	%ebx,%edx
	movl	24(%ebp),%ebx
	movl	%eax,-16(%edi)
	movl	%edx,-12(%edi)

L4:	movl	24(%esi),%eax
	movl	28(%esi),%edx
	sbbl	%ebx,%eax
	movl	28(%ebp),%ebx
	sbbl	%ebx,%edx
	movl	32(%ebp),%ebx
	movl	%eax,-8(%edi)
	movl	%edx,-4(%edi)

	leal	32(%esi),%esi
	leal	32(%ebp),%ebp
	decl	%ecx
	jnz	Loop

	popl	%edx
Lend:
	decl	%edx			/* test %edx w/o clobbering carry */
	js	Lend2
	incl	%edx
Loop2:
	leal	4(%edi),%edi
	movl	(%esi),%eax
	sbbl	%ebx,%eax
	movl	4(%ebp),%ebx
	movl	%eax,-4(%edi)
	leal	4(%esi),%esi
	leal	4(%ebp),%ebp
	decl	%edx
	jnz	Loop2
Lend2:
	movl	(%esi),%eax
	sbbl	%ebx,%eax
	movl	%eax,(%edi)

	sbbl	%eax,%eax
	negl	%eax

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