summary refs log tree commit diff stats
path: root/libotr/libgcrypt-1.8.7/mpi/pentium4/sse2/mpih-add1.S
blob: 55ed6630326e9f62588bccd220e7dd6a462a6bab (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
/* Intel Pentium-4 mpn_add_n -- mpn addition.
 *
 * Copyright 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_add_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)
 *
 * P4 Willamette, Northwood: 4.0 cycles/limb if dst!=src1 and dst!=src2
 *			    6.0 cycles/limb if dst==src1 or dst==src2
 * P4 Prescott:		    >= 5 cycles/limb
 *
 * The 4 c/l achieved here isn't particularly good, but is better than 9 c/l
 * for a basic adc loop.
 */

	TEXT
	ALIGN (3)
	GLOBL C_SYMBOL_NAME(_gcry_mpih_add_n)
C_SYMBOL_NAME(_gcry_mpih_add_n:)

	pxor	%mm0, %mm0
	
	movl	8(%esp), %eax		/* s1_ptr */
	movl	%ebx, 8(%esp)		/* re-use parameter space */
	movl	12(%esp), %ebx		/* res_ptr */
	movl	4(%esp), %edx		/* s2_ptr */
	movl	16(%esp), %ecx		/* size */

	leal	(%eax,%ecx,4), %eax	/* src1 end */
	leal	(%ebx,%ecx,4), %ebx	/* src2 end */
	leal	(%edx,%ecx,4), %edx	/* dst end */
	negl	%ecx			/* -size */

Ltop:
/*
	C eax	src1 end
	C ebx	src2 end
	C ecx	counter, limbs, negative
	C edx	dst end
	C mm0	carry bit
*/

	movd	(%eax,%ecx,4), %mm1
	movd	(%ebx,%ecx,4), %mm2
	paddq	%mm2, %mm1

	paddq	%mm1, %mm0
	movd	%mm0, (%edx,%ecx,4)

	psrlq	$32, %mm0

	addl	$1, %ecx
	jnz	Ltop


	movd	%mm0, %eax
	movl	8(%esp), %ebx	/* restore saved EBX */
	emms
	ret