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
|
;
; Copyright (c) 2016, Alliance for Open Media. All rights reserved
;
; This source code is subject to the terms of the BSD 2 Clause License and
; the Alliance for Open Media Patent License 1.0. If the BSD 2 Clause License
; was not distributed with this source code in the LICENSE file, you can
; obtain it at www.aomedia.org/license/software. If the Alliance for Open
; Media Patent License 1.0 was not distributed with this source code in the
; PATENTS file, you can obtain it at www.aomedia.org/license/patent.
;
;
%include "aom_ports/x86_abi_support.asm"
%macro GET_PARAM_4 0
mov rdx, arg(5) ;filter ptr
mov rsi, arg(0) ;src_ptr
mov rdi, arg(2) ;output_ptr
mov rcx, 0x0400040
movdqa xmm3, [rdx] ;load filters
pshuflw xmm4, xmm3, 11111111b ;k3
psrldq xmm3, 8
pshuflw xmm3, xmm3, 0b ;k4
punpcklqdq xmm4, xmm3 ;k3k4
movq xmm3, rcx ;rounding
pshufd xmm3, xmm3, 0
pxor xmm2, xmm2
movsxd rax, DWORD PTR arg(1) ;pixels_per_line
movsxd rdx, DWORD PTR arg(3) ;out_pitch
movsxd rcx, DWORD PTR arg(4) ;output_height
%endm
%macro APPLY_FILTER_4 1
punpckldq xmm0, xmm1 ;two row in one register
punpcklbw xmm0, xmm2 ;unpack to word
pmullw xmm0, xmm4 ;multiply the filter factors
movdqa xmm1, xmm0
psrldq xmm1, 8
paddsw xmm0, xmm1
paddsw xmm0, xmm3 ;rounding
psraw xmm0, 7 ;shift
packuswb xmm0, xmm0 ;pack to byte
%if %1
movd xmm1, [rdi]
pavgb xmm0, xmm1
%endif
movd [rdi], xmm0
lea rsi, [rsi + rax]
lea rdi, [rdi + rdx]
dec rcx
%endm
%macro GET_PARAM 0
mov rdx, arg(5) ;filter ptr
mov rsi, arg(0) ;src_ptr
mov rdi, arg(2) ;output_ptr
mov rcx, 0x0400040
movdqa xmm7, [rdx] ;load filters
pshuflw xmm6, xmm7, 11111111b ;k3
pshufhw xmm7, xmm7, 0b ;k4
punpcklwd xmm6, xmm6
punpckhwd xmm7, xmm7
movq xmm4, rcx ;rounding
pshufd xmm4, xmm4, 0
pxor xmm5, xmm5
movsxd rax, DWORD PTR arg(1) ;pixels_per_line
movsxd rdx, DWORD PTR arg(3) ;out_pitch
movsxd rcx, DWORD PTR arg(4) ;output_height
%endm
%macro APPLY_FILTER_8 1
punpcklbw xmm0, xmm5
punpcklbw xmm1, xmm5
pmullw xmm0, xmm6
pmullw xmm1, xmm7
paddsw xmm0, xmm1
paddsw xmm0, xmm4 ;rounding
psraw xmm0, 7 ;shift
packuswb xmm0, xmm0 ;pack back to byte
%if %1
movq xmm1, [rdi]
pavgb xmm0, xmm1
%endif
movq [rdi], xmm0 ;store the result
lea rsi, [rsi + rax]
lea rdi, [rdi + rdx]
dec rcx
%endm
%macro APPLY_FILTER_16 1
punpcklbw xmm0, xmm5
punpcklbw xmm1, xmm5
punpckhbw xmm2, xmm5
punpckhbw xmm3, xmm5
pmullw xmm0, xmm6
pmullw xmm1, xmm7
pmullw xmm2, xmm6
pmullw xmm3, xmm7
paddsw xmm0, xmm1
paddsw xmm2, xmm3
paddsw xmm0, xmm4 ;rounding
paddsw xmm2, xmm4
psraw xmm0, 7 ;shift
psraw xmm2, 7
packuswb xmm0, xmm2 ;pack back to byte
%if %1
movdqu xmm1, [rdi]
pavgb xmm0, xmm1
%endif
movdqu [rdi], xmm0 ;store the result
lea rsi, [rsi + rax]
lea rdi, [rdi + rdx]
dec rcx
%endm
SECTION .text
globalsym(aom_filter_block1d4_v2_sse2)
sym(aom_filter_block1d4_v2_sse2):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 6
push rsi
push rdi
; end prolog
GET_PARAM_4
.loop:
movd xmm0, [rsi] ;load src
movd xmm1, [rsi + rax]
APPLY_FILTER_4 0
jnz .loop
; begin epilog
pop rdi
pop rsi
UNSHADOW_ARGS
pop rbp
ret
globalsym(aom_filter_block1d8_v2_sse2)
sym(aom_filter_block1d8_v2_sse2):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 6
SAVE_XMM 7
push rsi
push rdi
; end prolog
GET_PARAM
.loop:
movq xmm0, [rsi] ;0
movq xmm1, [rsi + rax] ;1
APPLY_FILTER_8 0
jnz .loop
; begin epilog
pop rdi
pop rsi
RESTORE_XMM
UNSHADOW_ARGS
pop rbp
ret
globalsym(aom_filter_block1d16_v2_sse2)
sym(aom_filter_block1d16_v2_sse2):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 6
SAVE_XMM 7
push rsi
push rdi
; end prolog
GET_PARAM
.loop:
movdqu xmm0, [rsi] ;0
movdqu xmm1, [rsi + rax] ;1
movdqa xmm2, xmm0
movdqa xmm3, xmm1
APPLY_FILTER_16 0
jnz .loop
; begin epilog
pop rdi
pop rsi
RESTORE_XMM
UNSHADOW_ARGS
pop rbp
ret
globalsym(aom_filter_block1d4_h2_sse2)
sym(aom_filter_block1d4_h2_sse2):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 6
push rsi
push rdi
; end prolog
GET_PARAM_4
.loop:
movdqu xmm0, [rsi] ;load src
movdqa xmm1, xmm0
psrldq xmm1, 1
APPLY_FILTER_4 0
jnz .loop
; begin epilog
pop rdi
pop rsi
UNSHADOW_ARGS
pop rbp
ret
globalsym(aom_filter_block1d8_h2_sse2)
sym(aom_filter_block1d8_h2_sse2):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 6
SAVE_XMM 7
push rsi
push rdi
; end prolog
GET_PARAM
.loop:
movdqu xmm0, [rsi] ;load src
movdqa xmm1, xmm0
psrldq xmm1, 1
APPLY_FILTER_8 0
jnz .loop
; begin epilog
pop rdi
pop rsi
RESTORE_XMM
UNSHADOW_ARGS
pop rbp
ret
globalsym(aom_filter_block1d16_h2_sse2)
sym(aom_filter_block1d16_h2_sse2):
push rbp
mov rbp, rsp
SHADOW_ARGS_TO_STACK 6
SAVE_XMM 7
push rsi
push rdi
; end prolog
GET_PARAM
.loop:
movdqu xmm0, [rsi] ;load src
movdqu xmm1, [rsi + 1]
movdqa xmm2, xmm0
movdqa xmm3, xmm1
APPLY_FILTER_16 0
jnz .loop
; begin epilog
pop rdi
pop rsi
RESTORE_XMM
UNSHADOW_ARGS
pop rbp
ret
|