Annotation of OpenXM_contrib/gmp/mpn/pa32/add_n.asm, Revision 1.1.1.1
1.1 ohara 1: dnl HP-PA mpn_add_n -- Add two limb vectors of the same length > 0 and store
2: dnl sum in a third limb vector.
3:
4: dnl Copyright 1992, 1994, 2000, 2001, 2002 Free Software Foundation, Inc.
5:
6: dnl This file is part of the GNU MP Library.
7:
8: dnl The GNU MP Library is free software; you can redistribute it and/or modify
9: dnl it under the terms of the GNU Lesser General Public License as published
10: dnl by the Free Software Foundation; either version 2.1 of the License, or (at
11: dnl your option) any later version.
12:
13: dnl The GNU MP Library is distributed in the hope that it will be useful, but
14: dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
15: dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
16: dnl License for more details.
17:
18: dnl You should have received a copy of the GNU Lesser General Public License
19: dnl along with the GNU MP Library; see the file COPYING.LIB. If not, write to
20: dnl the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
21: dnl MA 02111-1307, USA.
22:
23: include(`../config.m4')
24:
25: C INPUT PARAMETERS
26: C res_ptr gr26
27: C s1_ptr gr25
28: C s2_ptr gr24
29: C size gr23
30:
31: C One might want to unroll this as for other processors, but it turns out that
32: C the data cache contention after a store makes such unrolling useless. We
33: C can't come under 5 cycles/limb anyway.
34:
35: ASM_START()
36: PROLOGUE(mpn_add_n)
37: ldws,ma 4(0,%r25),%r20
38: ldws,ma 4(0,%r24),%r19
39:
40: addib,= -1,%r23,L(end) C check for (SIZE == 1)
41: add %r20,%r19,%r28 C add first limbs ignoring cy
42:
43: .label L(loop)
44: ldws,ma 4(0,%r25),%r20
45: ldws,ma 4(0,%r24),%r19
46: stws,ma %r28,4(0,%r26)
47: addib,<> -1,%r23,L(loop)
48: addc %r20,%r19,%r28
49:
50: .label L(end)
51: stws %r28,0(0,%r26)
52: bv 0(%r2)
53: addc %r0,%r0,%r28
54: EPILOGUE()
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>