1 ; mc88100 mpn_add_n
-- Add two limb vectors of the same length
> 0 and store
2 ; sum in
a third limb vector.
4 ; Copyright
1992, 1994, 1995, 2000 Free Software Foundation
, Inc.
6 ; This file is part of the GNU MP Library.
8 ; The GNU MP Library is free software; you can redistribute it
and/or modify
9 ; it under the terms of either
:
11 ;
* the GNU Lesser General Public License as published by the Free
12 ; Software Foundation; either version
3 of the License
, or (at your
13 ; option
) any later version.
17 ;
* the GNU General Public License as published by the Free Software
18 ; Foundation; either version
2 of the License
, or (at your option
) any
21 ;
or both in parallel
, as here.
23 ; The GNU MP Library is distributed in the hope that it will
be useful
, but
24 ; WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
25 ;
or FITNESS FOR
A PARTICULAR PURPOSE. See the GNU General Public License
28 ; You should have received copies of the GNU General Public License
and the
29 ; GNU Lesser General Public License along with the GNU MP Library. If
not,
30 ; see https
://www.gnu.org
/licenses
/.
39 ; This code has been optimized to run one instruction per clock
, avoiding
40 ; load stalls
and writeback contention. As
a result
, the instruction
41 ; order is
not always natural.
43 ; The speed is about
4.6 clocks
/limb
+ 18 clocks
/limb-vector on an
88100,
44 ; but on the
88110, it seems to run much slower
, 6.6 clocks
/limb.
50 ld r6,r3,0 ; read first limb from s1_ptr
52 ld r7,r4,0 ; read first limb from s2_ptr
54 subu.co
r5,r0,r5 ;
(clear carry as side effect
)
59 or.u
r12,r12,hi16
(Lbase
)
60 addu
r12,r12,r5 ;
r12 is address for entering in loop
62 extu
r5,r5,2 ; divide by
4
63 subu
r2,r2,r5 ; adjust res_ptr
64 subu
r3,r3,r5 ; adjust s1_ptr
65 subu
r4,r4,r5 ; adjust s2_ptr
78 Lzero
: subu
r10,r10,1 ;
add 0 + 8r limbs
(adj loop cnt
)
83 ld r6,r3,8 ;
add 7 + 8r limbs
87 ld r8,r3,12 ;
add 6 + 8r limbs
91 ld r6,r3,16 ;
add 5 + 8r limbs
95 ld r8,r3,20 ;
add 4 + 8r limbs
99 ld r6,r3,24 ;
add 3 + 8r limbs
103 ld r8,r3,28 ;
add 2 + 8r limbs
107 bcnd.n ne0
,r10,Loop ;
add 1 + 8r limbs
110 st r8,r2,28 ; store most significant limb
113 addu.ci
r2,r0,r0 ; return carry-out from most sign. limb