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
|
;
; 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/x86_abi_support.asm"
;void vp8_recon_b_mmx(unsigned char *s, short *q, unsigned char *d, int stride)
global sym(vp8_recon_b_mmx)
sym(vp8_recon_b_mmx):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 4
push rsi
push rdi
; end prolog
mov rsi, arg(0) ;s
mov rdi, arg(2) ;d
mov rdx, arg(1) ;q
movsxd rax, dword ptr arg(3) ;stride
pxor mm0, mm0
movd mm1, [rsi]
punpcklbw mm1, mm0
paddsw mm1, [rdx]
packuswb mm1, mm0 ; pack and unpack to saturate
movd [rdi], mm1
movd mm2, [rsi+16]
punpcklbw mm2, mm0
paddsw mm2, [rdx+32]
packuswb mm2, mm0 ; pack and unpack to saturate
movd [rdi+rax], mm2
movd mm3, [rsi+32]
punpcklbw mm3, mm0
paddsw mm3, [rdx+64]
packuswb mm3, mm0 ; pack and unpack to saturate
movd [rdi+2*rax], mm3
add rdi, rax
movd mm4, [rsi+48]
punpcklbw mm4, mm0
paddsw mm4, [rdx+96]
packuswb mm4, mm0 ; pack and unpack to saturate
movd [rdi+2*rax], mm4
; begin epilog
pop rdi
pop rsi
UNSHADOW_ARGS
pop rbp
ret
;void copy_mem8x8_mmx(
; unsigned char *src,
; int src_stride,
; unsigned char *dst,
; int dst_stride
; )
global sym(vp8_copy_mem8x8_mmx)
sym(vp8_copy_mem8x8_mmx):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 4
push rsi
push rdi
; end prolog
mov rsi, arg(0) ;src;
movq mm0, [rsi]
movsxd rax, dword ptr arg(1) ;src_stride;
mov rdi, arg(2) ;dst;
movq mm1, [rsi+rax]
movq mm2, [rsi+rax*2]
movsxd rcx, dword ptr arg(3) ;dst_stride
lea rsi, [rsi+rax*2]
movq [rdi], mm0
add rsi, rax
movq [rdi+rcx], mm1
movq [rdi+rcx*2], mm2
lea rdi, [rdi+rcx*2]
movq mm3, [rsi]
add rdi, rcx
movq mm4, [rsi+rax]
movq mm5, [rsi+rax*2]
movq [rdi], mm3
lea rsi, [rsi+rax*2]
movq [rdi+rcx], mm4
movq [rdi+rcx*2], mm5
lea rdi, [rdi+rcx*2]
movq mm0, [rsi+rax]
movq mm1, [rsi+rax*2]
movq [rdi+rcx], mm0
movq [rdi+rcx*2],mm1
; begin epilog
pop rdi
pop rsi
UNSHADOW_ARGS
pop rbp
ret
;void copy_mem8x4_mmx(
; unsigned char *src,
; int src_stride,
; unsigned char *dst,
; int dst_stride
; )
global sym(vp8_copy_mem8x4_mmx)
sym(vp8_copy_mem8x4_mmx):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 4
push rsi
push rdi
; end prolog
mov rsi, arg(0) ;src;
movq mm0, [rsi]
movsxd rax, dword ptr arg(1) ;src_stride;
mov rdi, arg(2) ;dst;
movq mm1, [rsi+rax]
movq mm2, [rsi+rax*2]
movsxd rcx, dword ptr arg(3) ;dst_stride
lea rsi, [rsi+rax*2]
movq [rdi], mm0
movq [rdi+rcx], mm1
movq [rdi+rcx*2], mm2
lea rdi, [rdi+rcx*2]
movq mm3, [rsi+rax]
movq [rdi+rcx], mm3
; begin epilog
pop rdi
pop rsi
UNSHADOW_ARGS
pop rbp
ret
;void copy_mem16x16_mmx(
; unsigned char *src,
; int src_stride,
; unsigned char *dst,
; int dst_stride
; )
global sym(vp8_copy_mem16x16_mmx)
sym(vp8_copy_mem16x16_mmx):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 4
push rsi
push rdi
; end prolog
mov rsi, arg(0) ;src;
movsxd rax, dword ptr arg(1) ;src_stride;
mov rdi, arg(2) ;dst;
movsxd rcx, dword ptr arg(3) ;dst_stride
movq mm0, [rsi]
movq mm3, [rsi+8];
movq mm1, [rsi+rax]
movq mm4, [rsi+rax+8]
movq mm2, [rsi+rax*2]
movq mm5, [rsi+rax*2+8]
lea rsi, [rsi+rax*2]
add rsi, rax
movq [rdi], mm0
movq [rdi+8], mm3
movq [rdi+rcx], mm1
movq [rdi+rcx+8], mm4
movq [rdi+rcx*2], mm2
movq [rdi+rcx*2+8], mm5
lea rdi, [rdi+rcx*2]
add rdi, rcx
movq mm0, [rsi]
movq mm3, [rsi+8];
movq mm1, [rsi+rax]
movq mm4, [rsi+rax+8]
movq mm2, [rsi+rax*2]
movq mm5, [rsi+rax*2+8]
lea rsi, [rsi+rax*2]
add rsi, rax
movq [rdi], mm0
movq [rdi+8], mm3
movq [rdi+rcx], mm1
movq [rdi+rcx+8], mm4
movq [rdi+rcx*2], mm2
movq [rdi+rcx*2+8], mm5
lea rdi, [rdi+rcx*2]
add rdi, rcx
movq mm0, [rsi]
movq mm3, [rsi+8];
movq mm1, [rsi+rax]
movq mm4, [rsi+rax+8]
movq mm2, [rsi+rax*2]
movq mm5, [rsi+rax*2+8]
lea rsi, [rsi+rax*2]
add rsi, rax
movq [rdi], mm0
movq [rdi+8], mm3
movq [rdi+rcx], mm1
movq [rdi+rcx+8], mm4
movq [rdi+rcx*2], mm2
movq [rdi+rcx*2+8], mm5
lea rdi, [rdi+rcx*2]
add rdi, rcx
movq mm0, [rsi]
movq mm3, [rsi+8];
movq mm1, [rsi+rax]
movq mm4, [rsi+rax+8]
movq mm2, [rsi+rax*2]
movq mm5, [rsi+rax*2+8]
lea rsi, [rsi+rax*2]
add rsi, rax
movq [rdi], mm0
movq [rdi+8], mm3
movq [rdi+rcx], mm1
movq [rdi+rcx+8], mm4
movq [rdi+rcx*2], mm2
movq [rdi+rcx*2+8], mm5
lea rdi, [rdi+rcx*2]
add rdi, rcx
movq mm0, [rsi]
movq mm3, [rsi+8];
movq mm1, [rsi+rax]
movq mm4, [rsi+rax+8]
movq mm2, [rsi+rax*2]
movq mm5, [rsi+rax*2+8]
lea rsi, [rsi+rax*2]
add rsi, rax
movq [rdi], mm0
movq [rdi+8], mm3
movq [rdi+rcx], mm1
movq [rdi+rcx+8], mm4
movq [rdi+rcx*2], mm2
movq [rdi+rcx*2+8], mm5
lea rdi, [rdi+rcx*2]
add rdi, rcx
movq mm0, [rsi]
movq mm3, [rsi+8];
movq [rdi], mm0
movq [rdi+8], mm3
; begin epilog
pop rdi
pop rsi
UNSHADOW_ARGS
pop rbp
ret
|
