1 | /* SPARC v9 __mpn_lshift -- |
2 | |
3 | Copyright (C) 1996-2024 Free Software Foundation, Inc. |
4 | |
5 | This file is part of the GNU MP Library. |
6 | |
7 | The GNU MP Library is free software; you can redistribute it and/or modify |
8 | it under the terms of the GNU Lesser General Public License as published by |
9 | the Free Software Foundation; either version 2.1 of the License, or (at your |
10 | option) any later version. |
11 | |
12 | The GNU MP Library is distributed in the hope that it will be useful, but |
13 | WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY |
14 | or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public |
15 | License for more details. |
16 | |
17 | You should have received a copy of the GNU Lesser General Public License |
18 | along with the GNU MP Library; see the file COPYING.LIB. If not, |
19 | see <https://www.gnu.org/licenses/>. */ |
20 | |
21 | #include <sysdep.h> |
22 | |
23 | /* INPUT PARAMETERS |
24 | res_ptr %o0 |
25 | src_ptr %o1 |
26 | size %o2 |
27 | cnt %o3 */ |
28 | |
29 | .register %g2, #scratch |
30 | .register %g3, #scratch |
31 | |
32 | ENTRY(__mpn_lshift) |
33 | sllx %o2,3,%g1 |
34 | add %o1,%g1,%o1 ! make %o1 point at end of src |
35 | ldx [%o1-8],%g2 ! load first limb |
36 | sub %g0,%o3,%o5 ! negate shift count |
37 | add %o0,%g1,%o0 ! make %o0 point at end of res |
38 | add %o2,-1,%o2 |
39 | andcc %o2,4-1,%g4 ! number of limbs in first loop |
40 | srlx %g2,%o5,%g1 ! compute function result |
41 | be,pn %xcc,.L0 ! if multiple of 4 limbs, skip first loop |
42 | mov %g1,%g5 |
43 | |
44 | sub %o2,%g4,%o2 ! adjust count for main loop |
45 | |
46 | .Loop0: ldx [%o1-16],%g3 |
47 | add %o0,-8,%o0 |
48 | add %o1,-8,%o1 |
49 | sllx %g2,%o3,%o4 |
50 | addcc %g4,-1,%g4 |
51 | srlx %g3,%o5,%g1 |
52 | mov %g3,%g2 |
53 | or %o4,%g1,%o4 |
54 | bne,pt %xcc,.Loop0 |
55 | stx %o4,[%o0+0] |
56 | |
57 | .L0: brz,pn %o2,.Lend |
58 | nop |
59 | |
60 | .Loop: ldx [%o1-16],%g3 |
61 | add %o0,-32,%o0 |
62 | sllx %g2,%o3,%o4 |
63 | addcc %o2,-4,%o2 |
64 | srlx %g3,%o5,%g1 |
65 | |
66 | ldx [%o1-24],%g2 |
67 | sllx %g3,%o3,%g4 |
68 | or %o4,%g1,%o4 |
69 | stx %o4,[%o0+24] |
70 | srlx %g2,%o5,%g1 |
71 | |
72 | ldx [%o1-32],%g3 |
73 | sllx %g2,%o3,%o4 |
74 | or %g4,%g1,%g4 |
75 | stx %g4,[%o0+16] |
76 | srlx %g3,%o5,%g1 |
77 | |
78 | ldx [%o1-40],%g2 |
79 | sllx %g3,%o3,%g4 |
80 | or %o4,%g1,%o4 |
81 | stx %o4,[%o0+8] |
82 | srlx %g2,%o5,%g1 |
83 | |
84 | add %o1,-32,%o1 |
85 | or %g4,%g1,%g4 |
86 | bne,pt %xcc,.Loop |
87 | stx %g4,[%o0+0] |
88 | |
89 | .Lend: sllx %g2,%o3,%g2 |
90 | stx %g2,[%o0-8] |
91 | |
92 | jmpl %o7+8, %g0 |
93 | mov %g5,%o0 |
94 | |
95 | END(__mpn_lshift) |
96 | |