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
|
;
; 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 "vpx_ports/x86_abi_support.asm"
;int vp8_block_error_xmm(short *coeff_ptr, short *dcoef_ptr)
global sym(vp8_block_error_xmm) PRIVATE
sym(vp8_block_error_xmm):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 2
push rsi
push rdi
; end prologue
mov rsi, arg(0) ;coeff_ptr
mov rdi, arg(1) ;dcoef_ptr
movdqa xmm0, [rsi]
movdqa xmm1, [rdi]
movdqa xmm2, [rsi+16]
movdqa xmm3, [rdi+16]
psubw xmm0, xmm1
psubw xmm2, xmm3
pmaddwd xmm0, xmm0
pmaddwd xmm2, xmm2
paddd xmm0, xmm2
pxor xmm5, xmm5
movdqa xmm1, xmm0
punpckldq xmm0, xmm5
punpckhdq xmm1, xmm5
paddd xmm0, xmm1
movdqa xmm1, xmm0
psrldq xmm0, 8
paddd xmm0, xmm1
movq rax, xmm0
pop rdi
pop rsi
; begin epilog
UNSHADOW_ARGS
pop rbp
ret
;int vp8_block_error_mmx(short *coeff_ptr, short *dcoef_ptr)
global sym(vp8_block_error_mmx) PRIVATE
sym(vp8_block_error_mmx):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 2
push rsi
push rdi
; end prolog
mov rsi, arg(0) ;coeff_ptr
pxor mm7, mm7
mov rdi, arg(1) ;dcoef_ptr
movq mm3, [rsi]
movq mm4, [rdi]
movq mm5, [rsi+8]
movq mm6, [rdi+8]
pxor mm1, mm1 ; from movd mm1, dc ; dc =0
movq mm2, mm7
psubw mm5, mm6
por mm1, mm2
pmaddwd mm5, mm5
pcmpeqw mm1, mm7
psubw mm3, mm4
pand mm1, mm3
pmaddwd mm1, mm1
paddd mm1, mm5
movq mm3, [rsi+16]
movq mm4, [rdi+16]
movq mm5, [rsi+24]
movq mm6, [rdi+24]
psubw mm5, mm6
pmaddwd mm5, mm5
psubw mm3, mm4
pmaddwd mm3, mm3
paddd mm3, mm5
paddd mm1, mm3
movq mm0, mm1
psrlq mm1, 32
paddd mm0, mm1
movq rax, mm0
pop rdi
pop rsi
; begin epilog
UNSHADOW_ARGS
pop rbp
ret
;int vp8_mbblock_error_mmx_impl(short *coeff_ptr, short *dcoef_ptr, int dc);
global sym(vp8_mbblock_error_mmx_impl) PRIVATE
sym(vp8_mbblock_error_mmx_impl):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 3
push rsi
push rdi
; end prolog
mov rsi, arg(0) ;coeff_ptr
pxor mm7, mm7
mov rdi, arg(1) ;dcoef_ptr
pxor mm2, mm2
movd mm1, dword ptr arg(2) ;dc
por mm1, mm2
pcmpeqw mm1, mm7
mov rcx, 16
.mberror_loop_mmx:
movq mm3, [rsi]
movq mm4, [rdi]
movq mm5, [rsi+8]
movq mm6, [rdi+8]
psubw mm5, mm6
pmaddwd mm5, mm5
psubw mm3, mm4
pand mm3, mm1
pmaddwd mm3, mm3
paddd mm2, mm5
paddd mm2, mm3
movq mm3, [rsi+16]
movq mm4, [rdi+16]
movq mm5, [rsi+24]
movq mm6, [rdi+24]
psubw mm5, mm6
pmaddwd mm5, mm5
psubw mm3, mm4
pmaddwd mm3, mm3
paddd mm2, mm5
paddd mm2, mm3
add rsi, 32
add rdi, 32
sub rcx, 1
jnz .mberror_loop_mmx
movq mm0, mm2
psrlq mm2, 32
paddd mm0, mm2
movq rax, mm0
pop rdi
pop rsi
; begin epilog
UNSHADOW_ARGS
pop rbp
ret
;int vp8_mbblock_error_xmm_impl(short *coeff_ptr, short *dcoef_ptr, int dc);
global sym(vp8_mbblock_error_xmm_impl) PRIVATE
sym(vp8_mbblock_error_xmm_impl):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 3
SAVE_XMM 6
push rsi
push rdi
; end prolog
mov rsi, arg(0) ;coeff_ptr
pxor xmm6, xmm6
mov rdi, arg(1) ;dcoef_ptr
pxor xmm4, xmm4
movd xmm5, dword ptr arg(2) ;dc
por xmm5, xmm4
pcmpeqw xmm5, xmm6
mov rcx, 16
.mberror_loop:
movdqa xmm0, [rsi]
movdqa xmm1, [rdi]
movdqa xmm2, [rsi+16]
movdqa xmm3, [rdi+16]
psubw xmm2, xmm3
pmaddwd xmm2, xmm2
psubw xmm0, xmm1
pand xmm0, xmm5
pmaddwd xmm0, xmm0
add rsi, 32
add rdi, 32
sub rcx, 1
paddd xmm4, xmm2
paddd xmm4, xmm0
jnz .mberror_loop
movdqa xmm0, xmm4
punpckldq xmm0, xmm6
punpckhdq xmm4, xmm6
paddd xmm0, xmm4
movdqa xmm1, xmm0
psrldq xmm0, 8
paddd xmm0, xmm1
movq rax, xmm0
pop rdi
pop rsi
; begin epilog
RESTORE_XMM
UNSHADOW_ARGS
pop rbp
ret
;int vp8_mbuverror_mmx_impl(short *s_ptr, short *d_ptr);
global sym(vp8_mbuverror_mmx_impl) PRIVATE
sym(vp8_mbuverror_mmx_impl):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 2
push rsi
push rdi
; end prolog
mov rsi, arg(0) ;s_ptr
mov rdi, arg(1) ;d_ptr
mov rcx, 16
pxor mm7, mm7
.mbuverror_loop_mmx:
movq mm1, [rsi]
movq mm2, [rdi]
psubw mm1, mm2
pmaddwd mm1, mm1
movq mm3, [rsi+8]
movq mm4, [rdi+8]
psubw mm3, mm4
pmaddwd mm3, mm3
paddd mm7, mm1
paddd mm7, mm3
add rsi, 16
add rdi, 16
dec rcx
jnz .mbuverror_loop_mmx
movq mm0, mm7
psrlq mm7, 32
paddd mm0, mm7
movq rax, mm0
pop rdi
pop rsi
; begin epilog
UNSHADOW_ARGS
pop rbp
ret
;int vp8_mbuverror_xmm_impl(short *s_ptr, short *d_ptr);
global sym(vp8_mbuverror_xmm_impl) PRIVATE
sym(vp8_mbuverror_xmm_impl):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 2
push rsi
push rdi
; end prolog
mov rsi, arg(0) ;s_ptr
mov rdi, arg(1) ;d_ptr
mov rcx, 16
pxor xmm3, xmm3
.mbuverror_loop:
movdqa xmm1, [rsi]
movdqa xmm2, [rdi]
psubw xmm1, xmm2
pmaddwd xmm1, xmm1
paddd xmm3, xmm1
add rsi, 16
add rdi, 16
dec rcx
jnz .mbuverror_loop
pxor xmm0, xmm0
movdqa xmm1, xmm3
movdqa xmm2, xmm1
punpckldq xmm1, xmm0
punpckhdq xmm2, xmm0
paddd xmm1, xmm2
movdqa xmm2, xmm1
psrldq xmm1, 8
paddd xmm1, xmm2
movq rax, xmm1
pop rdi
pop rsi
; begin epilog
UNSHADOW_ARGS
pop rbp
ret
|
