| 4349 |
Serge |
1 |
/* |
|
|
2 |
* simple math operations |
|
|
3 |
* Copyright (c) 2006 Michael Niedermayer et al |
|
|
4 |
* |
|
|
5 |
* This file is part of FFmpeg. |
|
|
6 |
* |
|
|
7 |
* FFmpeg is free software; you can redistribute it and/or |
|
|
8 |
* modify it under the terms of the GNU Lesser General Public |
|
|
9 |
* License as published by the Free Software Foundation; either |
|
|
10 |
* version 2.1 of the License, or (at your option) any later version. |
|
|
11 |
* |
|
|
12 |
* FFmpeg is distributed in the hope that it will be useful, |
|
|
13 |
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
|
14 |
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
|
|
15 |
* Lesser General Public License for more details. |
|
|
16 |
* |
|
|
17 |
* You should have received a copy of the GNU Lesser General Public |
|
|
18 |
* License along with FFmpeg; if not, write to the Free Software |
|
|
19 |
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA |
|
|
20 |
*/ |
|
|
21 |
|
|
|
22 |
#ifndef AVCODEC_X86_MATHOPS_H |
|
|
23 |
#define AVCODEC_X86_MATHOPS_H |
|
|
24 |
|
|
|
25 |
#include "config.h" |
|
|
26 |
#include "libavutil/common.h" |
|
|
27 |
|
|
|
28 |
#if HAVE_INLINE_ASM |
|
|
29 |
|
|
|
30 |
#if ARCH_X86_32 |
|
|
31 |
|
|
|
32 |
#define MULL MULL |
|
|
33 |
static av_always_inline av_const int MULL(int a, int b, unsigned shift) |
|
|
34 |
{ |
|
|
35 |
int rt, dummy; |
|
|
36 |
__asm__ ( |
|
|
37 |
"imull %3 \n\t" |
|
|
38 |
"shrdl %4, %%edx, %%eax \n\t" |
|
|
39 |
:"=a"(rt), "=d"(dummy) |
|
|
40 |
:"a"(a), "rm"(b), "ci"((uint8_t)shift) |
|
|
41 |
); |
|
|
42 |
return rt; |
|
|
43 |
} |
|
|
44 |
|
|
|
45 |
#define MULH MULH |
|
|
46 |
static av_always_inline av_const int MULH(int a, int b) |
|
|
47 |
{ |
|
|
48 |
int rt, dummy; |
|
|
49 |
__asm__ ( |
|
|
50 |
"imull %3" |
|
|
51 |
:"=d"(rt), "=a"(dummy) |
|
|
52 |
:"a"(a), "rm"(b) |
|
|
53 |
); |
|
|
54 |
return rt; |
|
|
55 |
} |
|
|
56 |
|
|
|
57 |
#define MUL64 MUL64 |
|
|
58 |
static av_always_inline av_const int64_t MUL64(int a, int b) |
|
|
59 |
{ |
|
|
60 |
int64_t rt; |
|
|
61 |
__asm__ ( |
|
|
62 |
"imull %2" |
|
|
63 |
:"=A"(rt) |
|
|
64 |
:"a"(a), "rm"(b) |
|
|
65 |
); |
|
|
66 |
return rt; |
|
|
67 |
} |
|
|
68 |
|
|
|
69 |
#endif /* ARCH_X86_32 */ |
|
|
70 |
|
|
|
71 |
#if HAVE_I686 |
|
|
72 |
/* median of 3 */ |
|
|
73 |
#define mid_pred mid_pred |
|
|
74 |
static inline av_const int mid_pred(int a, int b, int c) |
|
|
75 |
{ |
|
|
76 |
int i=b; |
|
|
77 |
__asm__ ( |
|
|
78 |
"cmp %2, %1 \n\t" |
|
|
79 |
"cmovg %1, %0 \n\t" |
|
|
80 |
"cmovg %2, %1 \n\t" |
|
|
81 |
"cmp %3, %1 \n\t" |
|
|
82 |
"cmovl %3, %1 \n\t" |
|
|
83 |
"cmp %1, %0 \n\t" |
|
|
84 |
"cmovg %1, %0 \n\t" |
|
|
85 |
:"+&r"(i), "+&r"(a) |
|
|
86 |
:"r"(b), "r"(c) |
|
|
87 |
); |
|
|
88 |
return i; |
|
|
89 |
} |
|
|
90 |
|
|
|
91 |
#define COPY3_IF_LT(x, y, a, b, c, d)\ |
|
|
92 |
__asm__ volatile(\ |
|
|
93 |
"cmpl %0, %3 \n\t"\ |
|
|
94 |
"cmovl %3, %0 \n\t"\ |
|
|
95 |
"cmovl %4, %1 \n\t"\ |
|
|
96 |
"cmovl %5, %2 \n\t"\ |
|
|
97 |
: "+&r" (x), "+&r" (a), "+r" (c)\ |
|
|
98 |
: "r" (y), "r" (b), "r" (d)\ |
|
|
99 |
); |
|
|
100 |
#endif /* HAVE_I686 */ |
|
|
101 |
|
|
|
102 |
#define MASK_ABS(mask, level) \ |
|
|
103 |
__asm__ ("cltd \n\t" \ |
|
|
104 |
"xorl %1, %0 \n\t" \ |
|
|
105 |
"subl %1, %0 \n\t" \ |
|
|
106 |
: "+a"(level), "=&d"(mask)) |
|
|
107 |
|
|
|
108 |
// avoid +32 for shift optimization (gcc should do that ...) |
|
|
109 |
#define NEG_SSR32 NEG_SSR32 |
|
|
110 |
static inline int32_t NEG_SSR32( int32_t a, int8_t s){ |
|
|
111 |
__asm__ ("sarl %1, %0\n\t" |
|
|
112 |
: "+r" (a) |
|
|
113 |
: "ic" ((uint8_t)(-s)) |
|
|
114 |
); |
|
|
115 |
return a; |
|
|
116 |
} |
|
|
117 |
|
|
|
118 |
#define NEG_USR32 NEG_USR32 |
|
|
119 |
static inline uint32_t NEG_USR32(uint32_t a, int8_t s){ |
|
|
120 |
__asm__ ("shrl %1, %0\n\t" |
|
|
121 |
: "+r" (a) |
|
|
122 |
: "ic" ((uint8_t)(-s)) |
|
|
123 |
); |
|
|
124 |
return a; |
|
|
125 |
} |
|
|
126 |
|
|
|
127 |
#endif /* HAVE_INLINE_ASM */ |
|
|
128 |
#endif /* AVCODEC_X86_MATHOPS_H */ |