/* HP-PA  __udiv_qrnnd division support, used from longlong.h.
 *	  This version runs fast on pre-PA7000 CPUs.
 *
 *      Copyright (C) 1993, 1994, 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.
 */


/* INPUT PARAMETERS
 *   rem_ptr	   gr26
 *   n1 	   gr25
 *   n0 	   gr24
 *   d		   gr23
 *
 *   The code size is a bit excessive.	We could merge the last two ds;addc
 *   sequences by simply moving the "bb,< Odd" instruction down.  The only
 *   trouble is the FFFFFFFF code that would need some hacking.
 */

	.code
	.export 	__udiv_qrnnd
	.label		__udiv_qrnnd
	.proc
	.callinfo	frame=0,no_calls
	.entry

	comb,<		%r23,0,L$largedivisor
	 sub		%r0,%r23,%r1		; clear cy as side-effect
	ds		%r0,%r1,%r0
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r23,%r25
	addc		%r24,%r24,%r28
	ds		%r25,%r23,%r25
	comclr,>=	%r25,%r0,%r0
	addl		%r25,%r23,%r25
	stws		%r25,0(0,%r26)
	bv		0(%r2)
	 addc		%r28,%r28,%r28

	.label	L$largedivisor
	extru		%r24,31,1,%r19		; r19 = n0 & 1
	bb,<		%r23,31,L$odd
	 extru		%r23,30,31,%r22 	; r22 = d >> 1
	shd		%r25,%r24,1,%r24	; r24 = new n0
	extru		%r25,30,31,%r25 	; r25 = new n1
	sub		%r0,%r22,%r21
	ds		%r0,%r21,%r0
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	comclr,>=	%r25,%r0,%r0
	addl		%r25,%r22,%r25
	sh1addl 	%r25,%r19,%r25
	stws		%r25,0(0,%r26)
	bv		0(%r2)
	 addc		%r24,%r24,%r28

	.label	L$odd
	addib,sv,n	1,%r22,L$FF..		; r22 = (d / 2 + 1)
	shd		%r25,%r24,1,%r24	; r24 = new n0
	extru		%r25,30,31,%r25 	; r25 = new n1
	sub		%r0,%r22,%r21
	ds		%r0,%r21,%r0
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r24
	ds		%r25,%r22,%r25
	addc		%r24,%r24,%r28
	comclr,>=	%r25,%r0,%r0
	addl		%r25,%r22,%r25
	sh1addl 	%r25,%r19,%r25
; We have computed (n1,,n0) / (d + 1), q' = r28, r' = r25
	add,nuv 	%r28,%r25,%r25
	addl		%r25,%r1,%r25
	addc		%r0,%r28,%r28
	sub,<<		%r25,%r23,%r0
	addl		%r25,%r1,%r25
	stws		%r25,0(0,%r26)
	bv		0(%r2)
	 addc		%r0,%r28,%r28

; This is just a special case of the code above.
; We come here when d == 0xFFFFFFFF
	.label	L$FF..
	add,uv		%r25,%r24,%r24
	sub,<<		%r24,%r23,%r0
	ldo		1(%r24),%r24
	stws		%r24,0(0,%r26)
	bv		0(%r2)
	 addc		%r0,%r25,%r28

	.exit
	.procend