1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
|
/*
* Copyright (c) 2010 The WebM project authors. All Rights Reserved.
*
* Use of this source code is governed by a BSD-style license
* that can be found in the LICENSE file in the root of the source
* tree. An additional intellectual property rights grant can be found
* in the file PATENTS. All contributing project authors may
* be found in the AUTHORS file in the root of the source tree.
*/
#include "./vp8_rtcd.h"
/****************************************************************************
* Notes:
*
* This implementation makes use of 16 bit fixed point verio of two multiply
* constants:
* 1. sqrt(2) * cos (pi/8)
* 2. sqrt(2) * sin (pi/8)
* Becuase the first constant is bigger than 1, to maintain the same 16 bit
* fixed point precision as the second one, we use a trick of
* x * a = x + x*(a-1)
* so
* x * sqrt(2) * cos (pi/8) = x + x * (sqrt(2) *cos(pi/8)-1).
**************************************************************************/
static const int cospi8sqrt2minus1 = 20091;
static const int sinpi8sqrt2 = 35468;
void vp8_short_idct4x4llm_c(short *input, unsigned char *pred_ptr,
int pred_stride, unsigned char *dst_ptr,
int dst_stride)
{
int i;
int r, c;
int a1, b1, c1, d1;
short output[16];
short *ip = input;
short *op = output;
int temp1, temp2;
int shortpitch = 4;
for (i = 0; i < 4; i++)
{
a1 = ip[0] + ip[8];
b1 = ip[0] - ip[8];
temp1 = (ip[4] * sinpi8sqrt2) >> 16;
temp2 = ip[12] + ((ip[12] * cospi8sqrt2minus1) >> 16);
c1 = temp1 - temp2;
temp1 = ip[4] + ((ip[4] * cospi8sqrt2minus1) >> 16);
temp2 = (ip[12] * sinpi8sqrt2) >> 16;
d1 = temp1 + temp2;
op[shortpitch*0] = a1 + d1;
op[shortpitch*3] = a1 - d1;
op[shortpitch*1] = b1 + c1;
op[shortpitch*2] = b1 - c1;
ip++;
op++;
}
ip = output;
op = output;
for (i = 0; i < 4; i++)
{
a1 = ip[0] + ip[2];
b1 = ip[0] - ip[2];
temp1 = (ip[1] * sinpi8sqrt2) >> 16;
temp2 = ip[3] + ((ip[3] * cospi8sqrt2minus1) >> 16);
c1 = temp1 - temp2;
temp1 = ip[1] + ((ip[1] * cospi8sqrt2minus1) >> 16);
temp2 = (ip[3] * sinpi8sqrt2) >> 16;
d1 = temp1 + temp2;
op[0] = (a1 + d1 + 4) >> 3;
op[3] = (a1 - d1 + 4) >> 3;
op[1] = (b1 + c1 + 4) >> 3;
op[2] = (b1 - c1 + 4) >> 3;
ip += shortpitch;
op += shortpitch;
}
ip = output;
for (r = 0; r < 4; r++)
{
for (c = 0; c < 4; c++)
{
int a = ip[c] + pred_ptr[c] ;
if (a < 0)
a = 0;
if (a > 255)
a = 255;
dst_ptr[c] = (unsigned char) a ;
}
ip += 4;
dst_ptr += dst_stride;
pred_ptr += pred_stride;
}
}
void vp8_dc_only_idct_add_c(short input_dc, unsigned char *pred_ptr,
int pred_stride, unsigned char *dst_ptr,
int dst_stride)
{
int a1 = ((input_dc + 4) >> 3);
int r, c;
for (r = 0; r < 4; r++)
{
for (c = 0; c < 4; c++)
{
int a = a1 + pred_ptr[c] ;
if (a < 0)
a = 0;
if (a > 255)
a = 255;
dst_ptr[c] = (unsigned char) a ;
}
dst_ptr += dst_stride;
pred_ptr += pred_stride;
}
}
void vp8_short_inv_walsh4x4_c(short *input, short *mb_dqcoeff)
{
short output[16];
int i;
int a1, b1, c1, d1;
int a2, b2, c2, d2;
short *ip = input;
short *op = output;
for (i = 0; i < 4; i++)
{
a1 = ip[0] + ip[12];
b1 = ip[4] + ip[8];
c1 = ip[4] - ip[8];
d1 = ip[0] - ip[12];
op[0] = a1 + b1;
op[4] = c1 + d1;
op[8] = a1 - b1;
op[12] = d1 - c1;
ip++;
op++;
}
ip = output;
op = output;
for (i = 0; i < 4; i++)
{
a1 = ip[0] + ip[3];
b1 = ip[1] + ip[2];
c1 = ip[1] - ip[2];
d1 = ip[0] - ip[3];
a2 = a1 + b1;
b2 = c1 + d1;
c2 = a1 - b1;
d2 = d1 - c1;
op[0] = (a2 + 3) >> 3;
op[1] = (b2 + 3) >> 3;
op[2] = (c2 + 3) >> 3;
op[3] = (d2 + 3) >> 3;
ip += 4;
op += 4;
}
for(i = 0; i < 16; i++)
{
mb_dqcoeff[i * 16] = output[i];
}
}
void vp8_short_inv_walsh4x4_1_c(short *input, short *mb_dqcoeff)
{
int i;
int a1;
a1 = ((input[0] + 3) >> 3);
for(i = 0; i < 16; i++)
{
mb_dqcoeff[i * 16] = a1;
}
}
|
