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 the GNU Lesser General Public License as published by
10 ; the Free Software Foundation; either version 3 of the License, or (at your
11 ; option) any later version.
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.
18 ; You should have received a copy of the GNU Lesser General Public License
19 ; along with the GNU MP Library. If not, see http://www.gnu.org/licenses/.
28 ; This code has been optimized to run one instruction per clock, avoiding
29 ; load stalls and writeback contention. As a result, the instruction
30 ; order is not always natural.
32 ; The speed is about 4.6 clocks/limb + 18 clocks/limb-vector on an 88100,
33 ; but on the 88110, it seems to run much slower, 6.6 clocks/limb.
39 ld r6,r3,0 ; read first limb from s1_ptr
41 ld r7,r4,0 ; read first limb from s2_ptr
43 subu.co r5,r0,r5 ; (clear carry as side effect)
48 or.u r12,r12,hi16(Lbase)
49 addu r12,r12,r5 ; r12 is address for entering in loop
51 extu r5,r5,2 ; divide by 4
52 subu r2,r2,r5 ; adjust res_ptr
53 subu r3,r3,r5 ; adjust s1_ptr
54 subu r4,r4,r5 ; adjust s2_ptr
67 Lzero: subu r10,r10,1 ; add 0 + 8r limbs (adj loop cnt)
72 ld r6,r3,8 ; add 7 + 8r limbs
76 ld r8,r3,12 ; add 6 + 8r limbs
80 ld r6,r3,16 ; add 5 + 8r limbs
84 ld r8,r3,20 ; add 4 + 8r limbs
88 ld r6,r3,24 ; add 3 + 8r limbs
92 ld r8,r3,28 ; add 2 + 8r limbs
96 bcnd.n ne0,r10,Loop ; add 1 + 8r limbs
99 st r8,r2,28 ; store most significant limb
102 addu.ci r2,r0,r0 ; return carry-out from most sign. limb