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
|
;******************************************************************************
;* x86-SIMD-optimized IDCT for prores
;* this is identical to "simple" IDCT written by Michael Niedermayer
;* except for the clip range
;*
;* Copyright (c) 2011 Ronald S. Bultje <rsbultje@gmail.com>
;* Copyright (c) 2015 Christophe Gisquet
;*
;* This file is part of FFmpeg.
;*
;* FFmpeg 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.
;*
;* FFmpeg 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 FFmpeg; if not, write to the Free Software
;* 51, Inc., Foundation Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
;******************************************************************************
%include "libavutil/x86/x86util.asm"
%if ARCH_X86_64
SECTION_RODATA
cextern pw_2
cextern pw_16
cextern pw_1023
cextern pw_4095
pd_round_12: times 4 dd 1<<(12-1)
pd_round_15: times 4 dd 1<<(15-1)
pd_round_19: times 4 dd 1<<(19-1)
%macro CONST_DEC 3
const %1
times 4 dw %2, %3
%endmacro
%define W1sh2 22725 ; W1 = 90901 = 22725<<2 + 1
%define W2sh2 21407 ; W2 = 85627 = 21407<<2 - 1
%define W3sh2 19265 ; W3 = 77062 = 19265<<2 + 2
%define W4sh2 16384 ; W4 = 65535 = 16384<<2 - 1
%define W3sh2_lo 19266
%define W4sh2_lo 16383
%define W5sh2 12873 ; W5 = 51491 = 12873<<2 - 1
%define W6sh2 8867 ; W6 = 35468 = 8867<<2
%define W7sh2 4520 ; W7 = 18081 = 4520<<2 + 1
CONST_DEC w4_plus_w2_hi, W4sh2, +W2sh2
CONST_DEC w4_min_w2_hi, W4sh2, -W2sh2
CONST_DEC w4_plus_w6_hi, W4sh2, +W6sh2
CONST_DEC w4_min_w6_hi, W4sh2, -W6sh2
CONST_DEC w1_plus_w3_hi, W1sh2, +W3sh2
CONST_DEC w3_min_w1_hi, W3sh2, -W1sh2
CONST_DEC w7_plus_w3_hi, W7sh2, +W3sh2
CONST_DEC w3_min_w7_hi, W3sh2, -W7sh2
CONST_DEC w1_plus_w5, W1sh2, +W5sh2
CONST_DEC w5_min_w1, W5sh2, -W1sh2
CONST_DEC w5_plus_w7, W5sh2, +W7sh2
CONST_DEC w7_min_w5, W7sh2, -W5sh2
CONST_DEC w4_plus_w2_lo, W4sh2_lo, +W2sh2
CONST_DEC w4_min_w2_lo, W4sh2_lo, -W2sh2
CONST_DEC w4_plus_w6_lo, W4sh2_lo, +W6sh2
CONST_DEC w4_min_w6_lo, W4sh2_lo, -W6sh2
CONST_DEC w1_plus_w3_lo, W1sh2, +W3sh2_lo
CONST_DEC w3_min_w1_lo, W3sh2_lo, -W1sh2
CONST_DEC w7_plus_w3_lo, W7sh2, +W3sh2_lo
CONST_DEC w3_min_w7_lo, W3sh2_lo, -W7sh2
%include "libavcodec/x86/simple_idct10_template.asm"
SECTION .text
%macro idct_fn 0
define_constants _hi
cglobal simple_idct10, 1, 1, 16, block
IDCT_FN "", 12, "", 19, "store"
RET
cglobal simple_idct10_put, 3, 3, 16, pixels, lsize, block
IDCT_FN "", 12, "", 19, "put", 0, pw_1023
RET
cglobal simple_idct12, 1, 1, 16, block
; coeffs are already 15bits, adding the offset would cause
; overflow in the input
IDCT_FN "", 15, pw_2, 16, "store"
RET
cglobal simple_idct12_put, 3, 3, 16, pixels, lsize, block
; range isn't known, so the C simple_idct range is used
; Also, using a bias on input overflows, so use the bias
; on output of the first butterfly instead
IDCT_FN "", 15, pw_2, 16, "put", 0, pw_4095
RET
%endmacro
INIT_XMM sse2
idct_fn
%if HAVE_AVX_EXTERNAL
INIT_XMM avx
idct_fn
%endif
%endif
|
