Go to most recent revision | Details | Last modification | View Log | RSS feed
Rev | Author | Line No. | Line |
---|---|---|---|
4349 | Serge | 1 | /* |
2 | * Copyright (c) 2008 Siarhei Siamashka |
||
3 | * |
||
4 | * This file is part of FFmpeg. |
||
5 | * |
||
6 | * FFmpeg is free software; you can redistribute it and/or |
||
7 | * modify it under the terms of the GNU Lesser General Public |
||
8 | * License as published by the Free Software Foundation; either |
||
9 | * version 2.1 of the License, or (at your option) any later version. |
||
10 | * |
||
11 | * FFmpeg is distributed in the hope that it will be useful, |
||
12 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
||
13 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
||
14 | * Lesser General Public License for more details. |
||
15 | * |
||
16 | * You should have received a copy of the GNU Lesser General Public |
||
17 | * License along with FFmpeg; if not, write to the Free Software |
||
18 | * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA |
||
19 | */ |
||
20 | |||
21 | #include "config.h" |
||
22 | #include "libavutil/arm/asm.S" |
||
23 | |||
24 | /** |
||
25 | * ARM VFP optimized float to int16 conversion. |
||
26 | * Assume that len is a positive number and is multiple of 8, destination |
||
27 | * buffer is at least 4 bytes aligned (8 bytes alignment is better for |
||
28 | * performance), little-endian byte sex. |
||
29 | */ |
||
30 | @ void ff_float_to_int16_vfp(int16_t *dst, const float *src, int len) |
||
31 | function ff_float_to_int16_vfp, export=1 |
||
32 | push {r4-r8,lr} |
||
33 | vpush {d8-d11} |
||
34 | vldmia r1!, {s16-s23} |
||
35 | vcvt.s32.f32 s0, s16 |
||
36 | vcvt.s32.f32 s1, s17 |
||
37 | vcvt.s32.f32 s2, s18 |
||
38 | vcvt.s32.f32 s3, s19 |
||
39 | vcvt.s32.f32 s4, s20 |
||
40 | vcvt.s32.f32 s5, s21 |
||
41 | vcvt.s32.f32 s6, s22 |
||
42 | vcvt.s32.f32 s7, s23 |
||
43 | 1: |
||
44 | subs r2, r2, #8 |
||
45 | vmov r3, r4, s0, s1 |
||
46 | vmov r5, r6, s2, s3 |
||
47 | vmov r7, r8, s4, s5 |
||
48 | vmov ip, lr, s6, s7 |
||
49 | it gt |
||
50 | vldmiagt r1!, {s16-s23} |
||
51 | ssat r4, #16, r4 |
||
52 | ssat r3, #16, r3 |
||
53 | ssat r6, #16, r6 |
||
54 | ssat r5, #16, r5 |
||
55 | pkhbt r3, r3, r4, lsl #16 |
||
56 | pkhbt r4, r5, r6, lsl #16 |
||
57 | itttt gt |
||
58 | vcvtgt.s32.f32 s0, s16 |
||
59 | vcvtgt.s32.f32 s1, s17 |
||
60 | vcvtgt.s32.f32 s2, s18 |
||
61 | vcvtgt.s32.f32 s3, s19 |
||
62 | itttt gt |
||
63 | vcvtgt.s32.f32 s4, s20 |
||
64 | vcvtgt.s32.f32 s5, s21 |
||
65 | vcvtgt.s32.f32 s6, s22 |
||
66 | vcvtgt.s32.f32 s7, s23 |
||
67 | ssat r8, #16, r8 |
||
68 | ssat r7, #16, r7 |
||
69 | ssat lr, #16, lr |
||
70 | ssat ip, #16, ip |
||
71 | pkhbt r5, r7, r8, lsl #16 |
||
72 | pkhbt r6, ip, lr, lsl #16 |
||
73 | stmia r0!, {r3-r6} |
||
74 | bgt 1b |
||
75 | |||
76 | vpop {d8-d11} |
||
77 | pop {r4-r8,pc} |
||
78 | endfunc |