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
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
|
/*
* Copyright (c) 2010 The VP8 project authors. All Rights Reserved.
*
* Use of this source code is governed by a BSD-style license and patent
* grant that can be found in the LICENSE file in the root of the source
* tree. All contributing project authors may be found in the AUTHORS
* file in the root of the source tree.
*/
#include "vpx_ports/config.h"
#include "vpx_ports/x86.h"
#include "variance.h"
#include "onyx_int.h"
#if HAVE_MMX
void vp8_short_fdct8x4_mmx(short *input, short *output, int pitch)
{
vp8_short_fdct4x4_mmx(input, output, pitch);
vp8_short_fdct4x4_mmx(input + 4, output + 16, pitch);
}
void vp8_fast_fdct8x4_mmx(short *input, short *output, int pitch)
{
vp8_fast_fdct4x4_mmx(input, output , pitch);
vp8_fast_fdct4x4_mmx(input + 4, output + 16, pitch);
}
int vp8_fast_quantize_b_impl_mmx(short *coeff_ptr, short *zbin_ptr,
short *qcoeff_ptr, short *dequant_ptr,
short *scan_mask, short *round_ptr,
short *quant_ptr, short *dqcoeff_ptr);
void vp8_fast_quantize_b_mmx(BLOCK *b, BLOCKD *d)
{
short *scan_mask = vp8_default_zig_zag_mask;//d->scan_order_mask_ptr;
short *coeff_ptr = &b->coeff[0];
short *zbin_ptr = &b->zbin[0][0];
short *round_ptr = &b->round[0][0];
short *quant_ptr = &b->quant[0][0];
short *qcoeff_ptr = d->qcoeff;
short *dqcoeff_ptr = d->dqcoeff;
short *dequant_ptr = &d->dequant[0][0];
d->eob = vp8_fast_quantize_b_impl_mmx(
coeff_ptr,
zbin_ptr,
qcoeff_ptr,
dequant_ptr,
scan_mask,
round_ptr,
quant_ptr,
dqcoeff_ptr
);
}
int vp8_mbblock_error_mmx_impl(short *coeff_ptr, short *dcoef_ptr, int dc);
int vp8_mbblock_error_mmx(MACROBLOCK *mb, int dc)
{
short *coeff_ptr = mb->block[0].coeff;
short *dcoef_ptr = mb->e_mbd.block[0].dqcoeff;
return vp8_mbblock_error_mmx_impl(coeff_ptr, dcoef_ptr, dc);
}
int vp8_mbuverror_mmx_impl(short *s_ptr, short *d_ptr);
int vp8_mbuverror_mmx(MACROBLOCK *mb)
{
short *s_ptr = &mb->coeff[256];
short *d_ptr = &mb->e_mbd.dqcoeff[256];
return vp8_mbuverror_mmx_impl(s_ptr, d_ptr);
}
void vp8_subtract_b_mmx_impl(unsigned char *z, int src_stride,
short *diff, unsigned char *predictor,
int pitch);
void vp8_subtract_b_mmx(BLOCK *be, BLOCKD *bd, int pitch)
{
unsigned char *z = *(be->base_src) + be->src;
unsigned int src_stride = be->src_stride;
short *diff = &be->src_diff[0];
unsigned char *predictor = &bd->predictor[0];
vp8_subtract_b_mmx_impl(z, src_stride, diff, predictor, pitch);
}
#endif
#if HAVE_SSE2
void vp8_short_fdct8x4_wmt(short *input, short *output, int pitch)
{
vp8_short_fdct4x4_wmt(input, output, pitch);
vp8_short_fdct4x4_wmt(input + 4, output + 16, pitch);
}
int vp8_fast_quantize_b_impl_sse(short *coeff_ptr, short *zbin_ptr,
short *qcoeff_ptr, short *dequant_ptr,
short *scan_mask, short *round_ptr,
short *quant_ptr, short *dqcoeff_ptr);
void vp8_fast_quantize_b_sse(BLOCK *b, BLOCKD *d)
{
short *scan_mask = vp8_default_zig_zag_mask;//d->scan_order_mask_ptr;
short *coeff_ptr = &b->coeff[0];
short *zbin_ptr = &b->zbin[0][0];
short *round_ptr = &b->round[0][0];
short *quant_ptr = &b->quant[0][0];
short *qcoeff_ptr = d->qcoeff;
short *dqcoeff_ptr = d->dqcoeff;
short *dequant_ptr = &d->dequant[0][0];
d->eob = vp8_fast_quantize_b_impl_sse(
coeff_ptr,
zbin_ptr,
qcoeff_ptr,
dequant_ptr,
scan_mask,
round_ptr,
quant_ptr,
dqcoeff_ptr
);
}
int vp8_mbblock_error_xmm_impl(short *coeff_ptr, short *dcoef_ptr, int dc);
int vp8_mbblock_error_xmm(MACROBLOCK *mb, int dc)
{
short *coeff_ptr = mb->block[0].coeff;
short *dcoef_ptr = mb->e_mbd.block[0].dqcoeff;
return vp8_mbblock_error_xmm_impl(coeff_ptr, dcoef_ptr, dc);
}
int vp8_mbuverror_xmm_impl(short *s_ptr, short *d_ptr);
int vp8_mbuverror_xmm(MACROBLOCK *mb)
{
short *s_ptr = &mb->coeff[256];
short *d_ptr = &mb->e_mbd.dqcoeff[256];
return vp8_mbuverror_xmm_impl(s_ptr, d_ptr);
}
#endif
void vp8_arch_x86_encoder_init(VP8_COMP *cpi)
{
#if CONFIG_RUNTIME_CPU_DETECT
int flags = x86_simd_caps();
int mmx_enabled = flags & HAS_MMX;
int xmm_enabled = flags & HAS_SSE;
int wmt_enabled = flags & HAS_SSE2;
int SSE3Enabled = flags & HAS_SSE3;
int SSSE3Enabled = flags & HAS_SSSE3;
/* Note:
*
* This platform can be built without runtime CPU detection as well. If
* you modify any of the function mappings present in this file, be sure
* to also update them in static mapings (<arch>/filename_<arch>.h)
*/
/* Override default functions with fastest ones for this CPU. */
#if HAVE_MMX
if (mmx_enabled)
{
cpi->rtcd.variance.sad16x16 = vp8_sad16x16_mmx;
cpi->rtcd.variance.sad16x8 = vp8_sad16x8_mmx;
cpi->rtcd.variance.sad8x16 = vp8_sad8x16_mmx;
cpi->rtcd.variance.sad8x8 = vp8_sad8x8_mmx;
cpi->rtcd.variance.sad4x4 = vp8_sad4x4_mmx;
cpi->rtcd.variance.var4x4 = vp8_variance4x4_mmx;
cpi->rtcd.variance.var8x8 = vp8_variance8x8_mmx;
cpi->rtcd.variance.var8x16 = vp8_variance8x16_mmx;
cpi->rtcd.variance.var16x8 = vp8_variance16x8_mmx;
cpi->rtcd.variance.var16x16 = vp8_variance16x16_mmx;
cpi->rtcd.variance.subpixvar4x4 = vp8_sub_pixel_variance4x4_mmx;
cpi->rtcd.variance.subpixvar8x8 = vp8_sub_pixel_variance8x8_mmx;
cpi->rtcd.variance.subpixvar8x16 = vp8_sub_pixel_variance8x16_mmx;
cpi->rtcd.variance.subpixvar16x8 = vp8_sub_pixel_variance16x8_mmx;
cpi->rtcd.variance.subpixvar16x16 = vp8_sub_pixel_variance16x16_mmx;
cpi->rtcd.variance.subpixmse16x16 = vp8_sub_pixel_mse16x16_mmx;
cpi->rtcd.variance.mse16x16 = vp8_mse16x16_mmx;
cpi->rtcd.variance.getmbss = vp8_get_mb_ss_mmx;
cpi->rtcd.variance.get16x16prederror = vp8_get16x16pred_error_mmx;
cpi->rtcd.variance.get8x8var = vp8_get8x8var_mmx;
cpi->rtcd.variance.get16x16var = vp8_get16x16var_mmx;
cpi->rtcd.variance.get4x4sse_cs = vp8_get4x4sse_cs_mmx;
cpi->rtcd.fdct.short4x4 = vp8_short_fdct4x4_mmx;
cpi->rtcd.fdct.short8x4 = vp8_short_fdct8x4_mmx;
cpi->rtcd.fdct.fast4x4 = vp8_fast_fdct4x4_mmx;
cpi->rtcd.fdct.fast8x4 = vp8_fast_fdct8x4_mmx;
cpi->rtcd.fdct.walsh_short4x4 = vp8_short_walsh4x4_c;
cpi->rtcd.encodemb.berr = vp8_block_error_mmx;
cpi->rtcd.encodemb.mberr = vp8_mbblock_error_mmx;
cpi->rtcd.encodemb.mbuverr = vp8_mbuverror_mmx;
cpi->rtcd.encodemb.subb = vp8_subtract_b_mmx;
cpi->rtcd.encodemb.submby = vp8_subtract_mby_mmx;
cpi->rtcd.encodemb.submbuv = vp8_subtract_mbuv_mmx;
cpi->rtcd.quantize.fastquantb = vp8_fast_quantize_b_mmx;
}
#endif
#if HAVE_SSE2
if (wmt_enabled)
{
cpi->rtcd.variance.sad16x16 = vp8_sad16x16_wmt;
cpi->rtcd.variance.sad16x8 = vp8_sad16x8_wmt;
cpi->rtcd.variance.sad8x16 = vp8_sad8x16_wmt;
cpi->rtcd.variance.sad8x8 = vp8_sad8x8_wmt;
cpi->rtcd.variance.sad4x4 = vp8_sad4x4_wmt;
cpi->rtcd.variance.var4x4 = vp8_variance4x4_wmt;
cpi->rtcd.variance.var8x8 = vp8_variance8x8_wmt;
cpi->rtcd.variance.var8x16 = vp8_variance8x16_wmt;
cpi->rtcd.variance.var16x8 = vp8_variance16x8_wmt;
cpi->rtcd.variance.var16x16 = vp8_variance16x16_wmt;
cpi->rtcd.variance.subpixvar4x4 = vp8_sub_pixel_variance4x4_wmt;
cpi->rtcd.variance.subpixvar8x8 = vp8_sub_pixel_variance8x8_wmt;
cpi->rtcd.variance.subpixvar8x16 = vp8_sub_pixel_variance8x16_wmt;
cpi->rtcd.variance.subpixvar16x8 = vp8_sub_pixel_variance16x8_wmt;
cpi->rtcd.variance.subpixvar16x16 = vp8_sub_pixel_variance16x16_wmt;
cpi->rtcd.variance.subpixmse16x16 = vp8_sub_pixel_mse16x16_wmt;
cpi->rtcd.variance.mse16x16 = vp8_mse16x16_wmt;
cpi->rtcd.variance.getmbss = vp8_get_mb_ss_sse2;
cpi->rtcd.variance.get16x16prederror = vp8_get16x16pred_error_sse2;
cpi->rtcd.variance.get8x8var = vp8_get8x8var_sse2;
cpi->rtcd.variance.get16x16var = vp8_get16x16var_sse2;
/* cpi->rtcd.variance.get4x4sse_cs not implemented for wmt */;
#if 0
/* short SSE2 DCT currently disabled, does not match the MMX version */
cpi->rtcd.fdct.short4x4 = vp8_short_fdct4x4_wmt;
cpi->rtcd.fdct.short8x4 = vp8_short_fdct8x4_wmt;
#endif
/* cpi->rtcd.fdct.fast4x4 not implemented for wmt */;
cpi->rtcd.fdct.fast8x4 = vp8_fast_fdct8x4_wmt;
cpi->rtcd.fdct.walsh_short4x4 = vp8_short_walsh4x4_sse2;
cpi->rtcd.encodemb.berr = vp8_block_error_xmm;
cpi->rtcd.encodemb.mberr = vp8_mbblock_error_xmm;
cpi->rtcd.encodemb.mbuverr = vp8_mbuverror_xmm;
/* cpi->rtcd.encodemb.sub* not implemented for wmt */
cpi->rtcd.quantize.fastquantb = vp8_fast_quantize_b_sse;
}
#endif
#if HAVE_SSE3
if (SSE3Enabled)
{
cpi->rtcd.variance.sad16x16 = vp8_sad16x16_sse3;
cpi->rtcd.variance.sad16x16x3 = vp8_sad16x16x3_sse3;
cpi->rtcd.variance.sad16x8x3 = vp8_sad16x8x3_sse3;
cpi->rtcd.variance.sad8x16x3 = vp8_sad8x16x3_sse3;
cpi->rtcd.variance.sad8x8x3 = vp8_sad8x8x3_sse3;
cpi->rtcd.variance.sad4x4x3 = vp8_sad4x4x3_sse3;
cpi->rtcd.search.full_search = vp8_full_search_sadx3;
cpi->rtcd.variance.sad16x16x4d = vp8_sad16x16x4d_sse3;
cpi->rtcd.variance.sad16x8x4d = vp8_sad16x8x4d_sse3;
cpi->rtcd.variance.sad8x16x4d = vp8_sad8x16x4d_sse3;
cpi->rtcd.variance.sad8x8x4d = vp8_sad8x8x4d_sse3;
cpi->rtcd.variance.sad4x4x4d = vp8_sad4x4x4d_sse3;
cpi->rtcd.search.diamond_search = vp8_diamond_search_sadx4;
}
#endif
#if HAVE_SSSE3
if (SSSE3Enabled)
{
cpi->rtcd.variance.sad16x16x3 = vp8_sad16x16x3_ssse3;
cpi->rtcd.variance.sad16x8x3 = vp8_sad16x8x3_ssse3;
}
#endif
#endif
}
|
