Annotation of OpenXM_contrib/gmp/mpn/hppa/hppa2_0/add_n.s, Revision 1.1.1.1
1.1 maekawa 1: ; HP-PA 2.0 32-bit __gmpn_add_n -- Add two limb vectors of the same length > 0
2: ; and store sum in a third limb vector.
3:
4: ; Copyright (C) 1997, 1998, 2000 Free Software Foundation, Inc.
5:
6: ; This file is part of the GNU MP Library.
7:
8: ; The GNU MP Library is free software; you can redistribute it and/or modify
9: ; it under the terms of the GNU Lesser General Public License as published by
10: ; the Free Software Foundation; either version 2.1 of the License, or (at your
11: ; option) any later version.
12:
13: ; The GNU MP Library is distributed in the hope that it will be useful, but
14: ; WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
15: ; or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
16: ; License for more details.
17:
18: ; You should have received a copy of the GNU Lesser General Public License
19: ; along with the GNU MP Library; see the file COPYING.LIB. If not, write to
20: ; the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
21: ; MA 02111-1307, USA.
22:
23:
24: ; INPUT PARAMETERS
25: ; res_ptr gr26
26: ; s1_ptr gr25
27: ; s2_ptr gr24
28: ; size gr23
29:
30: ; This runs at 2 cycles/limb on PA8000.
31:
32: .code
33: .export __gmpn_add_n
34: __gmpn_add_n
35: .proc
36: .callinfo frame=0,no_calls
37: .entry
38:
39: sub %r0,%r23,%r22
40: zdep %r22,30,3,%r28 ; r28 = 2 * (-n & 7)
41: zdep %r22,29,3,%r22 ; r22 = 4 * (-n & 7)
42: sub %r25,%r22,%r25 ; offset s1_ptr
43: sub %r24,%r22,%r24 ; offset s2_ptr
44: sub %r26,%r22,%r26 ; offset res_ptr
45: blr %r28,%r0 ; branch into loop
46: add %r0,%r0,%r0 ; reset carry
47:
48: L$loop ldw 0(%r25),%r20
49: ldw 0(%r24),%r31
50: addc %r20,%r31,%r20
51: stw %r20,0(%r26)
52: L$7 ldw 4(%r25),%r21
53: ldw 4(%r24),%r19
54: addc %r21,%r19,%r21
55: stw %r21,4(%r26)
56: L$6 ldw 8(%r25),%r20
57: ldw 8(%r24),%r31
58: addc %r20,%r31,%r20
59: stw %r20,8(%r26)
60: L$5 ldw 12(%r25),%r21
61: ldw 12(%r24),%r19
62: addc %r21,%r19,%r21
63: stw %r21,12(%r26)
64: L$4 ldw 16(%r25),%r20
65: ldw 16(%r24),%r31
66: addc %r20,%r31,%r20
67: stw %r20,16(%r26)
68: L$3 ldw 20(%r25),%r21
69: ldw 20(%r24),%r19
70: addc %r21,%r19,%r21
71: stw %r21,20(%r26)
72: L$2 ldw 24(%r25),%r20
73: ldw 24(%r24),%r31
74: addc %r20,%r31,%r20
75: stw %r20,24(%r26)
76: L$1 ldw 28(%r25),%r21
77: ldo 32(%r25),%r25
78: ldw 28(%r24),%r19
79: addc %r21,%r19,%r21
80: stw %r21,28(%r26)
81: ldo 32(%r24),%r24
82: addib,> -8,%r23,L$loop
83: ldo 32(%r26),%r26
84:
85: bv (%r2)
86: .exit
87: addc %r0,%r0,%r28
88: .procend
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>