vp8/decoder/x86/dequantize_mmx.asm


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

;
;  Copyright (c) 2010 The VP8 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 "vpx_ports/x86_abi_support.asm"


;void vp8_dequantize_b_impl_mmx(short *sq, short *dq, short *q)
global sym(vp8_dequantize_b_impl_mmx)
sym(vp8_dequantize_b_impl_mmx):
    push        rbp
    mov         rbp, rsp
    SHADOW_ARGS_TO_STACK 3
    push        rsi
    push        rdi
    ; end prolog

        mov       rsi, arg(0) ;sq
        mov       rdi, arg(1) ;dq
        mov       rax, arg(2) ;q

        movq      mm1, [rsi]
        pmullw    mm1, [rax+0]            ; mm4 *= kernel 0 modifiers.
        movq      [rdi], mm1

        movq      mm1, [rsi+8]
        pmullw    mm1, [rax+8]            ; mm4 *= kernel 0 modifiers.
        movq      [rdi+8], mm1

        movq      mm1, [rsi+16]
        pmullw    mm1, [rax+16]            ; mm4 *= kernel 0 modifiers.
        movq      [rdi+16], mm1

        movq      mm1, [rsi+24]
        pmullw    mm1, [rax+24]            ; mm4 *= kernel 0 modifiers.
        movq      [rdi+24], mm1

    ; begin epilog
    pop rdi
    pop rsi
    UNSHADOW_ARGS
    pop         rbp
    ret


;void dequant_idct_mmx(short *input, short *dq, short *output, int pitch)
global sym(vp8_dequant_idct_mmx)
sym(vp8_dequant_idct_mmx):
    push        rbp
    mov         rbp, rsp
    SHADOW_ARGS_TO_STACK 4
    GET_GOT     rbx
    push        rsi
    push        rdi
    ; end prolog

        mov         rax,    arg(0) ;input
        mov         rdx,    arg(1) ;dq


        movq        mm0,    [rax   ]
        pmullw      mm0,    [rdx]

        movq        mm1,    [rax +8]
        pmullw      mm1,    [rdx +8]

        movq        mm2,    [rax+16]
        pmullw      mm2,    [rdx+16]

        movq        mm3,    [rax+24]
        pmullw      mm3,    [rdx+24]

        mov         rdx,    arg(2) ;output
        pxor        mm7,    mm7


        movq        [rax],   mm7
        movq        [rax+8], mm7

        movq        [rax+16],mm7
        movq        [rax+24],mm7


        movsxd      rax,            dword ptr arg(3) ;pitch

        psubw       mm0,            mm2             ; b1= 0-2
        paddw       mm2,            mm2             ;

        movq        mm5,            mm1
        paddw       mm2,            mm0             ; a1 =0+2

        pmulhw      mm5,            [x_s1sqr2 GLOBAL];
        paddw       mm5,            mm1             ; ip1 * sin(pi/8) * sqrt(2)

        movq        mm7,            mm3             ;
        pmulhw      mm7,            [x_c1sqr2less1 GLOBAL];

        paddw       mm7,            mm3             ; ip3 * cos(pi/8) * sqrt(2)
        psubw       mm7,            mm5             ; c1

        movq        mm5,            mm1
        movq        mm4,            mm3

        pmulhw      mm5,            [x_c1sqr2less1 GLOBAL]
        paddw       mm5,            mm1

        pmulhw      mm3,            [x_s1sqr2 GLOBAL]
        paddw       mm3,            mm4

        paddw       mm3,            mm5             ; d1
        movq        mm6,            mm2             ; a1

        movq        mm4,            mm0             ; b1
        paddw       mm2,            mm3             ;0

        paddw       mm4,            mm7             ;1
        psubw       mm0,            mm7             ;2

        psubw       mm6,            mm3             ;3

        movq        mm1,            mm2             ; 03 02 01 00
        movq        mm3,            mm4             ; 23 22 21 20

        punpcklwd   mm1,            mm0             ; 11 01 10 00
        punpckhwd   mm2,            mm0             ; 13 03 12 02

        punpcklwd   mm3,            mm6             ; 31 21 30 20
        punpckhwd   mm4,            mm6             ; 33 23 32 22

        movq        mm0,            mm1             ; 11 01 10 00
        movq        mm5,            mm2             ; 13 03 12 02

        punpckldq   mm0,            mm3             ; 30 20 10 00
        punpckhdq   mm1,            mm3             ; 31 21 11 01

        punpckldq   mm2,            mm4             ; 32 22 12 02
        punpckhdq   mm5,            mm4             ; 33 23 13 03

        movq        mm3,            mm5             ; 33 23 13 03

        psubw       mm0,            mm2             ; b1= 0-2
        paddw       mm2,            mm2             ;

        movq        mm5,            mm1
        paddw       mm2,            mm0             ; a1 =0+2

        pmulhw      mm5,            [x_s1sqr2 GLOBAL];
        paddw       mm5,            mm1             ; ip1 * sin(pi/8) * sqrt(2)

        movq        mm7,            mm3             ;
        pmulhw      mm7,            [x_c1sqr2less1 GLOBAL];

        paddw       mm7,            mm3             ; ip3 * cos(pi/8) * sqrt(2)
        psubw       mm7,            mm5             ; c1

        movq        mm5,            mm1
        movq        mm4,            mm3

        pmulhw      mm5,            [x_c1sqr2less1 GLOBAL]
        paddw       mm5,            mm1

        pmulhw      mm3,            [x_s1sqr2 GLOBAL]
        paddw       mm3,            mm4

        paddw       mm3,            mm5             ; d1
        paddw       mm0,            [fours GLOBAL]

        paddw       mm2,            [fours GLOBAL]
        movq        mm6,            mm2             ; a1

        movq        mm4,            mm0             ; b1
        paddw       mm2,            mm3             ;0

        paddw       mm4,            mm7             ;1
        psubw       mm0,            mm7             ;2

        psubw       mm6,            mm3             ;3
        psraw       mm2,            3

        psraw       mm0,            3
        psraw       mm4,            3

        psraw       mm6,            3

        movq        mm1,            mm2             ; 03 02 01 00
        movq        mm3,            mm4             ; 23 22 21 20

        punpcklwd   mm1,            mm0             ; 11 01 10 00
        punpckhwd   mm2,            mm0             ; 13 03 12 02

        punpcklwd   mm3,            mm6             ; 31 21 30 20
        punpckhwd   mm4,            mm6             ; 33 23 32 22

        movq        mm0,            mm1             ; 11 01 10 00
        movq        mm5,            mm2             ; 13 03 12 02

        punpckldq   mm0,            mm3             ; 30 20 10 00
        punpckhdq   mm1,            mm3             ; 31 21 11 01

        punpckldq   mm2,            mm4             ; 32 22 12 02
        punpckhdq   mm5,            mm4             ; 33 23 13 03

        movq        [rdx],          mm0

        movq        [rdx+rax],      mm1
        movq        [rdx+rax*2],    mm2

        add         rdx,            rax
        movq        [rdx+rax*2],    mm5

    ; begin epilog
    pop rdi
    pop rsi
    RESTORE_GOT
    UNSHADOW_ARGS
    pop         rbp
    ret


;void dequant_dc_idct_mmx(short *input, short *dq, short *output, int pitch, int Dc)
global sym(vp8_dequant_dc_idct_mmx)
sym(vp8_dequant_dc_idct_mmx):
    push        rbp
    mov         rbp, rsp
    SHADOW_ARGS_TO_STACK 5
    GET_GOT     rbx
    push        rsi
    push        rdi
    ; end prolog

        mov         rax,    arg(0) ;input
        mov         rdx,    arg(1) ;dq

        movsxd      rcx,    dword ptr arg(4) ;Dc

        movq        mm0,    [rax   ]
        pmullw      mm0,    [rdx]

        movq        mm1,    [rax +8]
        pmullw      mm1,    [rdx +8]

        movq        mm2,    [rax+16]
        pmullw      mm2,    [rdx+16]

        movq        mm3,    [rax+24]
        pmullw      mm3,    [rdx+24]

        mov         rdx,    arg(2) ;output
        pxor        mm7,    mm7


        movq        [rax],   mm7
        movq        [rax+8], mm7

        movq        [rax+16],mm7
        movq        [rax+24],mm7

        pinsrw      mm0,    rcx,  0
        movsxd      rax,            dword ptr arg(3) ;pitch

        psubw       mm0,            mm2             ; b1= 0-2
        paddw       mm2,            mm2             ;

        movq        mm5,            mm1
        paddw       mm2,            mm0             ; a1 =0+2

        pmulhw      mm5,            [x_s1sqr2 GLOBAL];
        paddw       mm5,            mm1             ; ip1 * sin(pi/8) * sqrt(2)

        movq        mm7,            mm3             ;
        pmulhw      mm7,            [x_c1sqr2less1 GLOBAL];

        paddw       mm7,            mm3             ; ip3 * cos(pi/8) * sqrt(2)
        psubw       mm7,            mm5             ; c1

        movq        mm5,            mm1
        movq        mm4,            mm3

        pmulhw      mm5,            [x_c1sqr2less1 GLOBAL]
        paddw       mm5,            mm1

        pmulhw      mm3,            [x_s1sqr2 GLOBAL]
        paddw       mm3,            mm4

        paddw       mm3,            mm5             ; d1
        movq        mm6,            mm2             ; a1

        movq        mm4,            mm0             ; b1
        paddw       mm2,            mm3             ;0

        paddw       mm4,            mm7             ;1
        psubw       mm0,            mm7             ;2

        psubw       mm6,            mm3             ;3

        movq        mm1,            mm2             ; 03 02 01 00
        movq        mm3,            mm4             ; 23 22 21 20

        punpcklwd   mm1,            mm0             ; 11 01 10 00
        punpckhwd   mm2,            mm0             ; 13 03 12 02

        punpcklwd   mm3,            mm6             ; 31 21 30 20
        punpckhwd   mm4,            mm6             ; 33 23 32 22

        movq        mm0,            mm1             ; 11 01 10 00
        movq        mm5,            mm2             ; 13 03 12 02

        punpckldq   mm0,            mm3             ; 30 20 10 00
        punpckhdq   mm1,            mm3             ; 31 21 11 01

        punpckldq   mm2,            mm4             ; 32 22 12 02
        punpckhdq   mm5,            mm4             ; 33 23 13 03

        movq        mm3,            mm5             ; 33 23 13 03

        psubw       mm0,            mm2             ; b1= 0-2
        paddw       mm2,            mm2             ;

        movq        mm5,            mm1
        paddw       mm2,            mm0             ; a1 =0+2

        pmulhw      mm5,            [x_s1sqr2 GLOBAL];
        paddw       mm5,            mm1             ; ip1 * sin(pi/8) * sqrt(2)

        movq        mm7,            mm3             ;
        pmulhw      mm7,            [x_c1sqr2less1 GLOBAL];

        paddw       mm7,            mm3             ; ip3 * cos(pi/8) * sqrt(2)
        psubw       mm7,            mm5             ; c1

        movq        mm5,            mm1
        movq        mm4,            mm3

        pmulhw      mm5,            [x_c1sqr2less1 GLOBAL]
        paddw       mm5,            mm1

        pmulhw      mm3,            [x_s1sqr2 GLOBAL]
        paddw       mm3,            mm4

        paddw       mm3,            mm5             ; d1
        paddw       mm0,            [fours GLOBAL]

        paddw       mm2,            [fours GLOBAL]
        movq        mm6,            mm2             ; a1

        movq        mm4,            mm0             ; b1
        paddw       mm2,            mm3             ;0

        paddw       mm4,            mm7             ;1
        psubw       mm0,            mm7             ;2

        psubw       mm6,            mm3             ;3
        psraw       mm2,            3

        psraw       mm0,            3
        psraw       mm4,            3

        psraw       mm6,            3

        movq        mm1,            mm2             ; 03 02 01 00
        movq        mm3,            mm4             ; 23 22 21 20

        punpcklwd   mm1,            mm0             ; 11 01 10 00
        punpckhwd   mm2,            mm0             ; 13 03 12 02

        punpcklwd   mm3,            mm6             ; 31 21 30 20
        punpckhwd   mm4,            mm6             ; 33 23 32 22

        movq        mm0,            mm1             ; 11 01 10 00
        movq        mm5,            mm2             ; 13 03 12 02

        punpckldq   mm0,            mm3             ; 30 20 10 00
        punpckhdq   mm1,            mm3             ; 31 21 11 01

        punpckldq   mm2,            mm4             ; 32 22 12 02
        punpckhdq   mm5,            mm4             ; 33 23 13 03

        movq        [rdx],          mm0

        movq        [rdx+rax],      mm1
        movq        [rdx+rax*2],    mm2

        add         rdx,            rax
        movq        [rdx+rax*2],    mm5

    ; begin epilog
    pop rdi
    pop rsi
    RESTORE_GOT
    UNSHADOW_ARGS
    pop         rbp
    ret


SECTION_RODATA
align 16
x_s1sqr2:
    times 4 dw 0x8A8C
align 16
x_c1sqr2less1:
    times 4 dw 0x4E7B
align 16
fours:
    times 4 dw 0x0004