]>
Commit | Line | Data |
---|---|---|
a334319f UD |
1 | /* MIPS __mpn_addmul_1 -- Multiply a limb vector with a single limb and |
2 | add the product to a second limb vector. | |
3 | ||
4 | Copyright (C) 1995, 2000, 2002, 2003 Free Software Foundation, Inc. | |
5 | ||
6 | This file is part of the GNU MP Library. | |
7 | ||
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 2.1 of the License, or (at your | |
11 | option) any later version. | |
12 | ||
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. | |
17 | ||
18 | You should have received a copy of the GNU Lesser General Public License | |
19 | along with the GNU MP Library; see the file COPYING.LIB. If not, write to | |
20 | the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, | |
21 | MA 02111-1307, USA. */ | |
22 | ||
23 | #include <sysdep.h> | |
24 | ||
25 | /* INPUT PARAMETERS | |
26 | res_ptr $4 | |
27 | s1_ptr $5 | |
28 | size $6 | |
29 | s2_limb $7 | |
30 | */ | |
31 | #ifdef __PIC__ | |
32 | .option pic2 | |
33 | #endif | |
34 | ENTRY (__mpn_addmul_1) | |
35 | .set noreorder | |
36 | #ifdef __PIC__ | |
37 | .cpload t9 | |
38 | #endif | |
39 | .set nomacro | |
40 | ||
41 | /* warm up phase 0 */ | |
42 | lw $8,0($5) | |
43 | ||
44 | /* warm up phase 1 */ | |
45 | addiu $5,$5,4 | |
46 | multu $8,$7 | |
47 | ||
48 | addiu $6,$6,-1 | |
49 | beq $6,$0,L(LC0) | |
50 | move $2,$0 /* zero cy2 */ | |
51 | ||
52 | addiu $6,$6,-1 | |
53 | beq $6,$0,L(LC1) | |
54 | lw $8,0($5) /* load new s1 limb as early as possible */ | |
55 | ||
56 | L(Loop): lw $10,0($4) | |
57 | mflo $3 | |
58 | mfhi $9 | |
59 | addiu $5,$5,4 | |
60 | addu $3,$3,$2 /* add old carry limb to low product limb */ | |
61 | multu $8,$7 | |
62 | lw $8,0($5) /* load new s1 limb as early as possible */ | |
63 | addiu $6,$6,-1 /* decrement loop counter */ | |
64 | sltu $2,$3,$2 /* carry from previous addition -> $2 */ | |
65 | addu $3,$10,$3 | |
66 | sltu $10,$3,$10 | |
67 | addu $2,$2,$10 | |
68 | sw $3,0($4) | |
69 | addiu $4,$4,4 | |
70 | bne $6,$0,L(Loop) /* should be "bnel" */ | |
71 | addu $2,$9,$2 /* add high product limb and carry from addition */ | |
72 | ||
73 | /* cool down phase 1 */ | |
74 | L(LC1): lw $10,0($4) | |
75 | mflo $3 | |
76 | mfhi $9 | |
77 | addu $3,$3,$2 | |
78 | sltu $2,$3,$2 | |
79 | multu $8,$7 | |
80 | addu $3,$10,$3 | |
81 | sltu $10,$3,$10 | |
82 | addu $2,$2,$10 | |
83 | sw $3,0($4) | |
84 | addiu $4,$4,4 | |
85 | addu $2,$9,$2 /* add high product limb and carry from addition */ | |
86 | ||
87 | /* cool down phase 0 */ | |
88 | L(LC0): lw $10,0($4) | |
89 | mflo $3 | |
90 | mfhi $9 | |
91 | addu $3,$3,$2 | |
92 | sltu $2,$3,$2 | |
93 | addu $3,$10,$3 | |
94 | sltu $10,$3,$10 | |
95 | addu $2,$2,$10 | |
96 | sw $3,0($4) | |
97 | j $31 | |
98 | addu $2,$9,$2 /* add high product limb and carry from addition */ | |
99 | END (__mpn_addmul_1) |