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
|
;******************************************************************************
;* V210 SIMD pack
;* Copyright (c) 2014 Kieran Kunhya <kierank@obe.tv>
;*
;* This file is part of Libav.
;*
;* Libav is free software; you can redistribute it and/or
;* modify it under the terms of the GNU Lesser General Public
;* License as published by the Free Software Foundation; either
;* version 2.1 of the License, or (at your option) any later version.
;*
;* Libav 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
;* Lesser General Public License for more details.
;*
;* You should have received a copy of the GNU Lesser General Public
;* License along with Libav; if not, write to the Free Software
;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
;******************************************************************************
%include "libavutil/x86/x86util.asm"
SECTION_RODATA 32
v210_enc_min_10: times 32 dw 0x4
v210_enc_max_10: times 32 dw 0x3fb
v210_enc_luma_mult_10: times 2 dw 4,1,16,4,1,16,0,0
v210_enc_luma_shuf_10: times 2 db -1,0,1,-1,2,3,4,5,-1,6,7,-1,8,9,10,11
v210_enc_chroma_mult_10: times 2 dw 1,4,16,0,16,1,4,0
v210_enc_chroma_shuf_10: times 2 db 0,1,8,9,-1,2,3,-1,10,11,4,5,-1,12,13,-1
v210_enc_min_8: times 32 db 0x1
v210_enc_max_8: times 32 db 0xfe
v210_enc_luma_mult_8: times 2 dw 16,4,64,16,4,64,0,0
v210_enc_luma_shuf_8: times 2 db 6,-1,7,-1,8,-1,9,-1,10,-1,11,-1,-1,-1,-1,-1
v210_enc_chroma_mult_8: times 2 dw 4,16,64,0,64,4,16,0
v210_enc_chroma_shuf1_8: times 2 db 0,-1,1,-1,2,-1,3,-1,8,-1,9,-1,10,-1,11,-1
v210_enc_chroma_shuf2_8: times 2 db 3,-1,4,-1,5,-1,7,-1,11,-1,12,-1,13,-1,15,-1
SECTION .text
%macro v210_planar_pack_10 0
; v210_planar_pack_10(const uint16_t *y, const uint16_t *u, const uint16_t *v, uint8_t *dst, ptrdiff_t width)
cglobal v210_planar_pack_10, 5, 5, 4+cpuflag(avx2), y, u, v, dst, width
lea r0, [yq+2*widthq]
add uq, widthq
add vq, widthq
neg widthq
mova m2, [v210_enc_min_10]
mova m3, [v210_enc_max_10]
.loop:
movu xm0, [yq+2*widthq]
%if cpuflag(avx2)
vinserti128 m0, m0, [yq+2*widthq+12], 1
%endif
CLIPW m0, m2, m3
movq xm1, [uq+widthq]
movhps xm1, [vq+widthq]
%if cpuflag(avx2)
movq xm4, [uq+widthq+6]
movhps xm4, [vq+widthq+6]
vinserti128 m1, m1, xm4, 1
%endif
CLIPW m1, m2, m3
pmullw m0, [v210_enc_luma_mult_10]
pshufb m0, [v210_enc_luma_shuf_10]
pmullw m1, [v210_enc_chroma_mult_10]
pshufb m1, [v210_enc_chroma_shuf_10]
por m0, m1
movu [dstq], m0
add dstq, mmsize
add widthq, (mmsize*3)/8
jl .loop
RET
%endmacro
%if HAVE_SSSE3_EXTERNAL
INIT_XMM ssse3
v210_planar_pack_10
%endif
%if HAVE_AVX2_EXTERNAL
INIT_YMM avx2
v210_planar_pack_10
%endif
%macro v210_planar_pack_8 0
; v210_planar_pack_8(const uint8_t *y, const uint8_t *u, const uint8_t *v, uint8_t *dst, ptrdiff_t width)
cglobal v210_planar_pack_8, 5, 5, 7, y, u, v, dst, width
add yq, widthq
shr widthq, 1
add uq, widthq
add vq, widthq
neg widthq
mova m4, [v210_enc_min_8]
mova m5, [v210_enc_max_8]
pxor m6, m6
.loop:
movu xm1, [yq+2*widthq]
%if cpuflag(avx2)
vinserti128 m1, m1, [yq+2*widthq+12], 1
%endif
CLIPUB m1, m4, m5
punpcklbw m0, m1, m6
; can't unpack high bytes in the same way because we process
; only six bytes at a time
pshufb m1, [v210_enc_luma_shuf_8]
pmullw m0, [v210_enc_luma_mult_8]
pmullw m1, [v210_enc_luma_mult_8]
pshufb m0, [v210_enc_luma_shuf_10]
pshufb m1, [v210_enc_luma_shuf_10]
movq xm3, [uq+widthq]
movhps xm3, [vq+widthq]
%if cpuflag(avx2)
movq xm2, [uq+widthq+6]
movhps xm2, [vq+widthq+6]
vinserti128 m3, m3, xm2, 1
%endif
CLIPUB m3, m4, m5
; shuffle and multiply to get the same packing as in 10-bit
pshufb m2, m3, [v210_enc_chroma_shuf1_8]
pshufb m3, [v210_enc_chroma_shuf2_8]
pmullw m2, [v210_enc_chroma_mult_8]
pmullw m3, [v210_enc_chroma_mult_8]
pshufb m2, [v210_enc_chroma_shuf_10]
pshufb m3, [v210_enc_chroma_shuf_10]
por m0, m2
por m1, m3
movu [dstq], xm0
movu [dstq+16], xm1
%if cpuflag(avx2)
vextracti128 [dstq+32], m0, 1
vextracti128 [dstq+48], m1, 1
%endif
add dstq, 2*mmsize
add widthq, (mmsize*3)/8
jl .loop
RET
%endmacro
%if HAVE_SSSE3_EXTERNAL
INIT_XMM ssse3
v210_planar_pack_8
%endif
%if HAVE_AVX_EXTERNAL
INIT_XMM avx
v210_planar_pack_8
%endif
%if HAVE_AVX2_EXTERNAL
INIT_YMM avx2
v210_planar_pack_8
%endif
|
