/* Pentium optimized __mpn_rshift --
   Copyright (C) 1992, 1994, 1995, 1996, 1997 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., 59 Temple Place - Suite 330, Boston,
   MA 02111-1307, USA. */

/*
  INPUT PARAMETERS
  res_ptr	(sp + 4)
  s_ptr		(sp + 8)
  size		(sp + 12)
  cnt		(sp + 16)
*/

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

.text
	ALIGN (3)
	.globl C_SYMBOL_NAME(__mpn_rshift)
C_SYMBOL_NAME(__mpn_rshift:)
	pushl	%edi
	pushl	%esi
	pushl	%ebx
	pushl	%ebp

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

/* We can use faster code for shift-by-1 under certain conditions.  */
	cmp	$1,%ecx
	jne	L(normal)
	leal	4(%edi),%eax
	cmpl	%esi,%eax
	jnc	L(special)		/* jump if res_ptr + 1 >= s_ptr */
	leal	(%edi,%ebp,4),%eax
	cmpl	%eax,%esi
	jnc	L(special)		/* jump if s_ptr >= res_ptr + size */

L(normal):
	movl	(%esi),%edx
	addl	$4,%esi
	xorl	%eax,%eax
	shrdl	%cl,%edx,%eax		/* compute carry limb */
	pushl	%eax			/* push carry limb onto stack */

	decl	%ebp
	pushl	%ebp
	shrl	$3,%ebp
	jz	L(end)

	movl	(%edi),%eax		/* fetch destination cache line */

	ALIGN	(2)
L(oop):	movl	28(%edi),%eax		/* fetch destination cache line */
	movl	%edx,%ebx

	movl	(%esi),%eax
	movl	4(%esi),%edx
	shrdl	%cl,%eax,%ebx
	shrdl	%cl,%edx,%eax
	movl	%ebx,(%edi)
	movl	%eax,4(%edi)

	movl	8(%esi),%ebx
	movl	12(%esi),%eax
	shrdl	%cl,%ebx,%edx
	shrdl	%cl,%eax,%ebx
	movl	%edx,8(%edi)
	movl	%ebx,12(%edi)

	movl	16(%esi),%edx
	movl	20(%esi),%ebx
	shrdl	%cl,%edx,%eax
	shrdl	%cl,%ebx,%edx
	movl	%eax,16(%edi)
	movl	%edx,20(%edi)

	movl	24(%esi),%eax
	movl	28(%esi),%edx
	shrdl	%cl,%eax,%ebx
	shrdl	%cl,%edx,%eax
	movl	%ebx,24(%edi)
	movl	%eax,28(%edi)

	addl	$32,%esi
	addl	$32,%edi
	decl	%ebp
	jnz	L(oop)

L(end):	popl	%ebp
	andl	$7,%ebp
	jz	L(end2)
L(oop2):
	movl	(%esi),%eax
	shrdl	%cl,%eax,%edx		/* compute result limb */
	movl	%edx,(%edi)
	movl	%eax,%edx
	addl	$4,%esi
	addl	$4,%edi
	decl	%ebp
	jnz	L(oop2)

L(end2):
	shrl	%cl,%edx		/* compute most significant limb */
	movl	%edx,(%edi)		/* store it */

	popl	%eax			/* pop carry limb */

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

/* We loop from least significant end of the arrays, which is only
   permissible if the source and destination don't overlap, since the
   function is documented to work for overlapping source and destination.
*/

L(special):
	leal	-4(%edi,%ebp,4),%edi
	leal	-4(%esi,%ebp,4),%esi

	movl	(%esi),%edx
	subl	$4,%esi

	decl	%ebp
	pushl	%ebp
	shrl	$3,%ebp

	shrl	$1,%edx
	incl	%ebp
	decl	%ebp
	jz	L(Lend)

	movl	(%edi),%eax		/* fetch destination cache line */

	ALIGN	(2)
L(Loop):
	movl	-28(%edi),%eax		/* fetch destination cache line */
	movl	%edx,%ebx

	movl	(%esi),%eax
	movl	-4(%esi),%edx
	rcrl	$1,%eax
	movl	%ebx,(%edi)
	rcrl	$1,%edx
	movl	%eax,-4(%edi)

	movl	-8(%esi),%ebx
	movl	-12(%esi),%eax
	rcrl	$1,%ebx
	movl	%edx,-8(%edi)
	rcrl	$1,%eax
	movl	%ebx,-12(%edi)

	movl	-16(%esi),%edx
	movl	-20(%esi),%ebx
	rcrl	$1,%edx
	movl	%eax,-16(%edi)
	rcrl	$1,%ebx
	movl	%edx,-20(%edi)

	movl	-24(%esi),%eax
	movl	-28(%esi),%edx
	rcrl	$1,%eax
	movl	%ebx,-24(%edi)
	rcrl	$1,%edx
	movl	%eax,-28(%edi)

	leal	-32(%esi),%esi		/* use leal not to clobber carry */
	leal	-32(%edi),%edi
	decl	%ebp
	jnz	L(Loop)

L(Lend):
	popl	%ebp
	sbbl	%eax,%eax		/* save carry in %eax */
	andl	$7,%ebp
	jz	L(Lend2)
	addl	%eax,%eax		/* restore carry from eax */
L(Loop2):
	movl	%edx,%ebx
	movl	(%esi),%edx
	rcrl	$1,%edx
	movl	%ebx,(%edi)

	leal	-4(%esi),%esi		/* use leal not to clobber carry */
	leal	-4(%edi),%edi
	decl	%ebp
	jnz	L(Loop2)

	jmp	L(L1)
L(Lend2):
	addl	%eax,%eax		/* restore carry from eax */
L(L1):	movl	%edx,(%edi)		/* store last limb */

	movl	$0,%eax
	rcrl	$1,%eax

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