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.
4 dnl Copyright
1992, 1994, 2000-2002 Free Software Foundation
, Inc.
6 dnl
This file is part of the GNU MP Library.
8 dnl The GNU MP Library is free software
; you can redistribute it and/or modify
9 dnl it under the terms of
either:
11 dnl
* the GNU Lesser General
Public License as published by the Free
12 dnl Software Foundation
; either version 3 of the License, or (at your
13 dnl option
) any later version.
17 dnl
* the GNU General
Public License as published by the Free Software
18 dnl Foundation
; either version 2 of the License, or (at your option) any
21 dnl
or both
in parallel
, as here.
23 dnl The GNU MP Library is distributed
in the hope that it will be useful
, but
24 dnl WITHOUT ANY WARRANTY
; without even the implied warranty of MERCHANTABILITY
25 dnl
or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General
Public License
28 dnl You should have received copies of the GNU General
Public License
and the
29 dnl GNU Lesser General
Public License along with the GNU MP Library. If
not,
30 dnl see
https://www.gnu.
org/licenses
/.
32 include(`..
/config.m4
')
40 C One might want to unroll this as for other processors, but it turns out that
41 C the data cache contention after a store makes such unrolling useless. We
42 C can't come under
5 cycles
/limb anyway.
46 ldws
,ma
4(0,%r25
),%r20
47 ldws
,ma
4(0,%r24
),%r19
49 addib
,= -1,%r23
,L
(end) C check for
(SIZE == 1)
50 add %r20
,%r19
,%r28 C
add first limbs ignoring cy
53 ldws
,ma
4(0,%r25
),%r20
54 ldws
,ma
4(0,%r24
),%r19
55 stws
,ma
%r28
,4(0,%r26
)
56 addib
,<> -1,%r23
,L
(loop)