forked from mpc-hc/mpc-hc
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathvd_asm.cpp
More file actions
432 lines (333 loc) · 10.8 KB
/
vd_asm.cpp
File metadata and controls
432 lines (333 loc) · 10.8 KB
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
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
// VirtualDub - Video processing and capture application
// Graphics support library
// Copyright (C) 1998-2007 Avery Lee
//
// This program is free software; you can redistribute it and/or modify
// it under the terms of the GNU General Public License as published by
// the Free Software Foundation; either version 2 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
//
// You should have received a copy of the GNU General Public License
// along with this program; if not, write to the Free Software
// Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
//
// Notes:
// - VDPixmapBlt is from VirtualDub
// - sse2 yv12 to yuy2 conversion by Haali
// (- vd.cpp/h should be renamed to something more sensible already :)
#include "stdafx.h"
#include "vd_asm.h"
#pragma warning(disable : 4799) // no emms... blahblahblah
#ifndef _WIN64
void __declspec(naked) yuvtoyuy2row_MMX(BYTE* dst, BYTE* srcy, BYTE* srcu, BYTE* srcv, DWORD width)
{
__asm {
push ebp
push edi
push esi
push ebx
mov edi, [esp+20] // dst
mov ebp, [esp+24] // srcy
mov ebx, [esp+28] // srcu
mov esi, [esp+32] // srcv
mov ecx, [esp+36] // width
shr ecx, 3
yuvtoyuy2row_loop:
movd mm0, [ebx]
punpcklbw mm0, [esi]
movq mm1, [ebp]
movq mm2, mm1
punpcklbw mm1, mm0
punpckhbw mm2, mm0
movq [edi], mm1
movq [edi+8], mm2
add ebp, 8
add ebx, 4
add esi, 4
add edi, 16
dec ecx
jnz yuvtoyuy2row_loop
pop ebx
pop esi
pop edi
pop ebp
ret
};
}
void __declspec(naked) yuvtoyuy2row_avg_MMX(BYTE* dst, BYTE* srcy, BYTE* srcu, BYTE* srcv, DWORD width, DWORD pitchuv)
{
static const __int64 mask = 0x7f7f7f7f7f7f7f7fi64;
__asm {
push ebp
push edi
push esi
push ebx
movq mm7, mask
mov edi, [esp+20] // dst
mov ebp, [esp+24] // srcy
mov ebx, [esp+28] // srcu
mov esi, [esp+32] // srcv
mov ecx, [esp+36] // width
mov eax, [esp+40] // pitchuv
shr ecx, 3
yuvtoyuy2row_avg_loop:
movd mm0, [ebx]
punpcklbw mm0, [esi]
movq mm1, mm0
movd mm2, [ebx + eax]
punpcklbw mm2, [esi + eax]
movq mm3, mm2
// (x+y)>>1 == (x&y)+((x^y)>>1)
pand mm0, mm2
pxor mm1, mm3
psrlq mm1, 1
pand mm1, mm7
paddb mm0, mm1
movq mm1, [ebp]
movq mm2, mm1
punpcklbw mm1, mm0
punpckhbw mm2, mm0
movq [edi], mm1
movq [edi+8], mm2
add ebp, 8
add ebx, 4
add esi, 4
add edi, 16
dec ecx
jnz yuvtoyuy2row_avg_loop
pop ebx
pop esi
pop edi
pop ebp
ret
};
}
void __declspec(naked) yv12_yuy2_row_sse2() {
__asm {
// ebx - Y
// edx - U
// esi - V
// edi - dest
// ecx - halfwidth
xor eax, eax
one:
movdqa xmm0, [ebx + eax*2] // YYYYYYYY
movdqa xmm1, [ebx + eax*2 + 16] // YYYYYYYY
movdqa xmm2, [edx + eax] // UUUUUUUU
movdqa xmm3, [esi + eax] // VVVVVVVV
movdqa xmm4, xmm2
movdqa xmm5, xmm0
movdqa xmm6, xmm1
punpcklbw xmm2, xmm3 // VUVUVUVU
punpckhbw xmm4, xmm3 // VUVUVUVU
punpcklbw xmm0, xmm2 // VYUYVYUY
punpcklbw xmm1, xmm4
punpckhbw xmm5, xmm2
punpckhbw xmm6, xmm4
movntdq [edi + eax*4], xmm0
movntdq [edi + eax*4 + 16], xmm5
movntdq [edi + eax*4 + 32], xmm1
movntdq [edi + eax*4 + 48], xmm6
add eax, 16
cmp eax, ecx
jb one
ret
};
}
void __declspec(naked) yv12_yuy2_row_sse2_linear() {
__asm {
// ebx - Y
// edx - U
// esi - V
// edi - dest
// ecx - width
// ebp - uv_stride
xor eax, eax
one:
movdqa xmm0, [ebx + eax*2] // YYYYYYYY
movdqa xmm1, [ebx + eax*2 + 16] // YYYYYYYY
movdqa xmm2, [edx]
movdqa xmm3, [esi]
pavgb xmm2, [edx + ebp] // UUUUUUUU
pavgb xmm3, [esi + ebp] // VVVVVVVV
movdqa xmm4, xmm2
movdqa xmm5, xmm0
movdqa xmm6, xmm1
punpcklbw xmm2, xmm3 // VUVUVUVU
punpckhbw xmm4, xmm3 // VUVUVUVU
punpcklbw xmm0, xmm2 // VYUYVYUY
punpcklbw xmm1, xmm4
punpckhbw xmm5, xmm2
punpckhbw xmm6, xmm4
movntdq [edi + eax*4], xmm0
movntdq [edi + eax*4 + 16], xmm5
movntdq [edi + eax*4 + 32], xmm1
movntdq [edi + eax*4 + 48], xmm6
add eax, 16
add edx, 16
add esi, 16
cmp eax, ecx
jb one
ret
};
}
void __declspec(naked) yv12_yuy2_row_sse2_linear_interlaced() {
__asm {
// ebx - Y
// edx - U
// esi - V
// edi - dest
// ecx - width
// ebp - uv_stride
xor eax, eax
one:
movdqa xmm0, [ebx + eax*2] // YYYYYYYY
movdqa xmm1, [ebx + eax*2 + 16] // YYYYYYYY
movdqa xmm2, [edx]
movdqa xmm3, [esi]
pavgb xmm2, [edx + ebp*2] // UUUUUUUU
pavgb xmm3, [esi + ebp*2] // VVVVVVVV
movdqa xmm4, xmm2
movdqa xmm5, xmm0
movdqa xmm6, xmm1
punpcklbw xmm2, xmm3 // VUVUVUVU
punpckhbw xmm4, xmm3 // VUVUVUVU
punpcklbw xmm0, xmm2 // VYUYVYUY
punpcklbw xmm1, xmm4
punpckhbw xmm5, xmm2
punpckhbw xmm6, xmm4
movntdq [edi + eax*4], xmm0
movntdq [edi + eax*4 + 16], xmm5
movntdq [edi + eax*4 + 32], xmm1
movntdq [edi + eax*4 + 48], xmm6
add eax, 16
add edx, 16
add esi, 16
cmp eax, ecx
jb one
ret
};
}
void __declspec(naked) yv12_yuy2_sse2(const BYTE *Y, const BYTE *U, const BYTE *V,
int halfstride, unsigned halfwidth, unsigned height,
BYTE *YUY2, int d_stride)
{
__asm {
push ebx
push esi
push edi
push ebp
mov ebx, [esp + 20] // Y
mov edx, [esp + 24] // U
mov esi, [esp + 28] // V
mov edi, [esp + 44] // D
mov ebp, [esp + 32] // uv_stride
mov ecx, [esp + 36] // uv_width
mov eax, ecx
add eax, 15
and eax, 0xfffffff0
sub [esp + 32], eax
cmp dword ptr [esp + 40], 2
jbe last2
row:
sub dword ptr [esp + 40], 2
call yv12_yuy2_row_sse2
lea ebx, [ebx + ebp*2]
add edi, [esp + 48]
call yv12_yuy2_row_sse2_linear
add edx, [esp + 32]
add esi, [esp + 32]
lea ebx, [ebx + ebp*2]
add edi, [esp + 48]
cmp dword ptr [esp + 40], 2
ja row
last2:
call yv12_yuy2_row_sse2
dec dword ptr [esp + 40]
jz done
lea ebx, [ebx + ebp*2]
add edi, [esp + 48]
call yv12_yuy2_row_sse2
done:
pop ebp
pop edi
pop esi
pop ebx
ret
};
}
void __declspec(naked) yv12_yuy2_sse2_interlaced(const BYTE *Y, const BYTE *U, const BYTE *V,
int halfstride, unsigned halfwidth, unsigned height,
BYTE *YUY2, int d_stride)
{
__asm {
push ebx
push esi
push edi
push ebp
mov ebx, [esp + 20] // Y
mov edx, [esp + 24] // U
mov esi, [esp + 28] // V
mov edi, [esp + 44] // D
mov ebp, [esp + 32] // uv_stride
mov ecx, [esp + 36] // uv_width
mov eax, ecx
add eax, 15
and eax, 0xfffffff0
sub [esp + 32], eax
cmp dword ptr [esp + 40], 4
jbe last4
row:
sub dword ptr [esp + 40], 4
call yv12_yuy2_row_sse2 // first row, first field
lea ebx, [ebx + ebp*2]
add edi, [esp + 48]
add edx, ebp
add esi, ebp
call yv12_yuy2_row_sse2 // first row, second field
lea ebx, [ebx + ebp*2]
add edi, [esp + 48]
sub edx, ebp
sub esi, ebp
call yv12_yuy2_row_sse2_linear_interlaced // second row, first field
add edx, [esp + 32]
add esi, [esp + 32]
lea ebx, [ebx + ebp*2]
add edi, [esp + 48]
call yv12_yuy2_row_sse2_linear_interlaced // second row, second field
add edx, [esp + 32]
add esi, [esp + 32]
lea ebx, [ebx + ebp*2]
add edi, [esp + 48]
cmp dword ptr [esp + 40], 4
ja row
last4:
call yv12_yuy2_row_sse2
lea ebx, [ebx + ebp*2]
add edi, [esp + 48]
add edx, ebp
add esi, ebp
call yv12_yuy2_row_sse2
lea ebx, [ebx + ebp*2]
add edi, [esp + 48]
sub edx, ebp
sub esi, ebp
call yv12_yuy2_row_sse2
lea ebx, [ebx + ebp*2]
add edi, [esp + 48]
add edx, ebp
add esi, ebp
call yv12_yuy2_row_sse2
pop ebp
pop edi
pop esi
pop ebx
ret
};
}
#endif