1
; mc88100 __mpn_add -- Add two limb vectors of the same length > 0 and store
2
; sum in a third limb vector.
4
; Copyright (C) 1992, 1994 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 the GNU General Public License as published by
10
; the Free Software Foundation; either version 2, or (at your option)
13
; The GNU MP Library is distributed in the hope that it will be useful,
14
; but WITHOUT ANY WARRANTY; without even the implied warranty of
15
; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16
; GNU General Public License for more details.
18
; You should have received a copy of the GNU General Public License
19
; along with the GNU MP Library; see the file COPYING. If not, write to
20
; the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
29
; This code has been optimized to run one instruction per clock, avoiding
30
; load stalls and writeback contention. As a result, the instruction
31
; order is not always natural.
33
; The speed is approximately 4.3 clocks/limb + 18 clocks/limb-vector.
38
ld r6,r3,0 ; read first limb from s1_ptr
40
ld r7,r4,0 ; read first limb from s2_ptr
42
subu.co r5,r0,r5 ; (clear carry as side effect)
47
or.u r12,r12,hi16(Lbase)
48
addu r12,r12,r5 ; r12 is address for entering in loop
50
extu r5,r5,2 ; divide by 4
51
subu r2,r2,r5 ; adjust res_ptr
52
subu r3,r3,r5 ; adjust s1_ptr
53
subu r4,r4,r5 ; adjust s2_ptr
66
Lzero: subu r10,r10,1 ; add 0 + 16r limbs (adjust loop counter)
71
ld r6,r3,8 ; add 15 + 16r limbs
75
ld r8,r3,12 ; add 14 + 16r limbs
79
ld r6,r3,16 ; add 13 + 16r limbs
83
ld r8,r3,20 ; add 12 + 16r limbs
87
ld r6,r3,24 ; add 11 + 16r limbs
91
ld r8,r3,28 ; add 10 + 16r limbs
95
ld r6,r3,32 ; add 9 + 16r limbs
99
ld r8,r3,36 ; add 8 + 16r limbs
103
ld r6,r3,40 ; add 7 + 16r limbs
107
ld r8,r3,44 ; add 6 + 16r limbs
111
ld r6,r3,48 ; add 5 + 16r limbs
115
ld r8,r3,52 ; add 4 + 16r limbs
119
ld r6,r3,56 ; add 3 + 16r limbs
123
ld r8,r3,60 ; add 2 + 16r limbs
127
bcnd.n ne0,r10,Loop ; add 1 + 16r limbs
130
st r8,r2,60 ; store most significant limb
133
addu.ci r2,r0,r0 ; return carry-out from most sign. limb