1 /*
2 * simple math operations
3 * Copyright (c) 2001, 2002 Fabrice Bellard
4 * Copyright (c) 2006 Michael Niedermayer <michaelni@gmx.at> et al
5 *
6 * This file is part of FFmpeg.
7 *
8 * FFmpeg is free software; you can redistribute it and/or
9 * modify it under the terms of the GNU Lesser General Public
10 * License as published by the Free Software Foundation; either
11 * version 2.1 of the License, or (at your option) any later version.
12 *
13 * FFmpeg is distributed in the hope that it will be useful,
14 * but WITHOUT ANY WARRANTY; without even the implied warranty of
15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16 * Lesser General Public License for more details.
17 *
18 * You should have received a copy of the GNU Lesser General Public
19 * License along with FFmpeg; if not, write to the Free Software
20 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
21 */
22 #ifndef AVCODEC_MATHOPS_H
23 #define AVCODEC_MATHOPS_H
24
25 #include <stdint.h>
26
27 #include "libavutil/common.h"
28 #include "config.h"
29
30 #define MAX_NEG_CROP 1024
31
32 extern const uint32_t ff_inverse[257];
33 extern const uint8_t ff_log2_run[41];
34 extern const uint8_t ff_sqrt_tab[256];
35 extern const uint8_t ff_crop_tab[256 + 2 * MAX_NEG_CROP];
36 extern const uint8_t ff_zigzag_direct[64];
37 extern const uint8_t ff_zigzag_scan[16+1];
38
39 #if ARCH_ARM
40 # include "arm/mathops.h"
41 #elif ARCH_AVR32
42 # include "avr32/mathops.h"
43 #elif ARCH_MIPS
44 # include "mips/mathops.h"
45 #elif ARCH_PPC
46 # include "ppc/mathops.h"
47 #elif ARCH_X86
48 # include "x86/mathops.h"
49 #endif
50
51 /* generic implementation */
52
53 #ifndef MUL64
54 # define MUL64(a,b) ((int64_t)(a) * (int64_t)(b))
55 #endif
56
57 #ifndef MULL
58 # define MULL(a,b,s) (MUL64(a, b) >> (s))
59 #endif
60
61 #ifndef MULH
MULH(int a, int b)62 static av_always_inline int MULH(int a, int b){
63 return MUL64(a, b) >> 32;
64 }
65 #endif
66
67 #ifndef UMULH
UMULH(unsigned a, unsigned b)68 static av_always_inline unsigned UMULH(unsigned a, unsigned b){
69 return ((uint64_t)(a) * (uint64_t)(b))>>32;
70 }
71 #endif
72
73 #ifndef MAC64
74 # define MAC64(d, a, b) ((d) += MUL64(a, b))
75 #endif
76
77 #ifndef MLS64
78 # define MLS64(d, a, b) ((d) -= MUL64(a, b))
79 #endif
80
81 /* signed 16x16 -> 32 multiply add accumulate */
82 #ifndef MAC16
83 # define MAC16(rt, ra, rb) rt += (ra) * (rb)
84 #endif
85
86 /* signed 16x16 -> 32 multiply */
87 #ifndef MUL16
88 # define MUL16(ra, rb) ((ra) * (rb))
89 #endif
90
91 #ifndef MLS16
92 # define MLS16(rt, ra, rb) ((rt) -= (ra) * (rb))
93 #endif
94
95 /* median of 3 */
96 #ifndef mid_pred
97 #define mid_pred mid_pred
mid_pred(int a, int b, int c)98 static inline av_const int mid_pred(int a, int b, int c)
99 {
100 if(a>b){
101 if(c>b){
102 if(c>a) b=a;
103 else b=c;
104 }
105 }else{
106 if(b>c){
107 if(c>a) b=c;
108 else b=a;
109 }
110 }
111 return b;
112 }
113 #endif
114
115 #ifndef median4
116 #define median4 median4
median4(int a, int b, int c, int d)117 static inline av_const int median4(int a, int b, int c, int d)
118 {
119 if (a < b) {
120 if (c < d) return (FFMIN(b, d) + FFMAX(a, c)) / 2;
121 else return (FFMIN(b, c) + FFMAX(a, d)) / 2;
122 } else {
123 if (c < d) return (FFMIN(a, d) + FFMAX(b, c)) / 2;
124 else return (FFMIN(a, c) + FFMAX(b, d)) / 2;
125 }
126 }
127 #endif
128
129 #define FF_SIGNBIT(x) ((x) >> CHAR_BIT * sizeof(x) - 1)
130
131 #ifndef sign_extend
sign_extend(int val, unsigned bits)132 static inline av_const int sign_extend(int val, unsigned bits)
133 {
134 unsigned shift = 8 * sizeof(int) - bits;
135 union { unsigned u; int s; } v = { (unsigned) val << shift };
136 return v.s >> shift;
137 }
138 #endif
139
140 #ifndef zero_extend
zero_extend(unsigned val, unsigned bits)141 static inline av_const unsigned zero_extend(unsigned val, unsigned bits)
142 {
143 return (val << ((8 * sizeof(int)) - bits)) >> ((8 * sizeof(int)) - bits);
144 }
145 #endif
146
147 #ifndef COPY3_IF_LT
148 #define COPY3_IF_LT(x, y, a, b, c, d)\
149 if ((y) < (x)) {\
150 (x) = (y);\
151 (a) = (b);\
152 (c) = (d);\
153 }
154 #endif
155
156 #ifndef MASK_ABS
157 #define MASK_ABS(mask, level) do { \
158 mask = level >> 31; \
159 level = (level ^ mask) - mask; \
160 } while (0)
161 #endif
162
163 #ifndef NEG_SSR32
164 # define NEG_SSR32(a,s) ((( int32_t)(a))>>(32-(s)))
165 #endif
166
167 #ifndef NEG_USR32
168 # define NEG_USR32(a,s) (((uint32_t)(a))>>(32-(s)))
169 #endif
170
171 #if HAVE_BIGENDIAN
172 # ifndef PACK_2U8
173 # define PACK_2U8(a,b) (((a) << 8) | (b))
174 # endif
175 # ifndef PACK_4U8
176 # define PACK_4U8(a,b,c,d) (((a) << 24) | ((b) << 16) | ((c) << 8) | (d))
177 # endif
178 # ifndef PACK_2U16
179 # define PACK_2U16(a,b) (((a) << 16) | (b))
180 # endif
181 #else
182 # ifndef PACK_2U8
183 # define PACK_2U8(a,b) (((b) << 8) | (a))
184 # endif
185 # ifndef PACK_4U2
186 # define PACK_4U8(a,b,c,d) (((d) << 24) | ((c) << 16) | ((b) << 8) | (a))
187 # endif
188 # ifndef PACK_2U16
189 # define PACK_2U16(a,b) (((b) << 16) | (a))
190 # endif
191 #endif
192
193 #ifndef PACK_2S8
194 # define PACK_2S8(a,b) PACK_2U8((a)&255, (b)&255)
195 #endif
196 #ifndef PACK_4S8
197 # define PACK_4S8(a,b,c,d) PACK_4U8((a)&255, (b)&255, (c)&255, (d)&255)
198 #endif
199 #ifndef PACK_2S16
200 # define PACK_2S16(a,b) PACK_2U16((a)&0xffff, (b)&0xffff)
201 #endif
202
203 #ifndef FASTDIV
204 # define FASTDIV(a,b) ((uint32_t)((((uint64_t)a) * ff_inverse[b]) >> 32))
205 #endif /* FASTDIV */
206
207 #ifndef ff_sqrt
208 #define ff_sqrt ff_sqrt
ff_sqrt(unsigned int a)209 static inline av_const unsigned int ff_sqrt(unsigned int a)
210 {
211 unsigned int b;
212
213 if (a < 255) return (ff_sqrt_tab[a + 1] - 1) >> 4;
214 else if (a < (1 << 12)) b = ff_sqrt_tab[a >> 4] >> 2;
215 #if !CONFIG_SMALL
216 else if (a < (1 << 14)) b = ff_sqrt_tab[a >> 6] >> 1;
217 else if (a < (1 << 16)) b = ff_sqrt_tab[a >> 8] ;
218 #endif
219 else {
220 int s = av_log2_16bit(a >> 16) >> 1;
221 unsigned int c = a >> (s + 2);
222 b = ff_sqrt_tab[c >> (s + 8)];
223 b = FASTDIV(c,b) + (b << s);
224 }
225
226 return b - (a < b * b);
227 }
228 #endif
229
ff_sqrf(float a)230 static inline av_const float ff_sqrf(float a)
231 {
232 return a*a;
233 }
234
ff_u8_to_s8(uint8_t a)235 static inline int8_t ff_u8_to_s8(uint8_t a)
236 {
237 union {
238 uint8_t u8;
239 int8_t s8;
240 } b;
241 b.u8 = a;
242 return b.s8;
243 }
244
245 #endif /* AVCODEC_MATHOPS_H */
246