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
|
/*
* AltiVec-enhanced yuv2yuvX
*
* Copyright (C) 2004 Romain Dolbeau <romain@dolbeau.org>
* based on the equivalent C code in swscale.c
*
* 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
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include <inttypes.h>
#include "config.h"
#include "libswscale/swscale.h"
#include "libswscale/swscale_internal.h"
#include "libavutil/attributes.h"
#include "libavutil/cpu.h"
#include "yuv2rgb_altivec.h"
#include "libavutil/ppc/util_altivec.h"
#if HAVE_VSX
#define vzero vec_splat_s32(0)
#if !HAVE_BIGENDIAN
#define GET_LS(a,b,c,s) {\
ls = a;\
a = vec_vsx_ld(((b) << 1) + 16, s);\
}
#define yuv2planeX_8(d1, d2, l1, src, x, perm, filter) do {\
vector signed short ls;\
GET_LS(l1, x, perm, src);\
vector signed int i1 = vec_mule(filter, ls);\
vector signed int i2 = vec_mulo(filter, ls);\
vector signed int vf1, vf2;\
vf1 = vec_mergeh(i1, i2);\
vf2 = vec_mergel(i1, i2);\
d1 = vec_add(d1, vf1);\
d2 = vec_add(d2, vf2);\
} while (0)
#define LOAD_FILTER(vf,f) {\
vf = vec_vsx_ld(joffset, f);\
}
#define LOAD_L1(ll1,s,p){\
ll1 = vec_vsx_ld(xoffset, s);\
}
// The 3 above is 2 (filterSize == 4) + 1 (sizeof(short) == 2).
// The neat trick: We only care for half the elements,
// high or low depending on (i<<3)%16 (it's 0 or 8 here),
// and we're going to use vec_mule, so we choose
// carefully how to "unpack" the elements into the even slots.
#define GET_VF4(a, vf, f) {\
vf = (vector signed short)vec_vsx_ld(a << 3, f);\
vf = vec_mergeh(vf, (vector signed short)vzero);\
}
#define FIRST_LOAD(sv, pos, s, per) {}
#define UPDATE_PTR(s0, d0, s1, d1) {}
#define LOAD_SRCV(pos, a, s, per, v0, v1, vf) {\
vf = vec_vsx_ld(pos + a, s);\
}
#define LOAD_SRCV8(pos, a, s, per, v0, v1, vf) LOAD_SRCV(pos, a, s, per, v0, v1, vf)
#define GET_VFD(a, b, f, vf0, vf1, per, vf, off) {\
vf = vec_vsx_ld((a * 2 * filterSize) + (b * 2) + off, f);\
}
#define FUNC(name) name ## _vsx
#include "swscale_ppc_template.c"
#undef FUNC
#endif /* !HAVE_BIGENDIAN */
static void yuv2plane1_8_u(const int16_t *src, uint8_t *dest, int dstW,
const uint8_t *dither, int offset, int start)
{
int i;
for (i = start; i < dstW; i++) {
int val = (src[i] + dither[(i + offset) & 7]) >> 7;
dest[i] = av_clip_uint8(val);
}
}
static void yuv2plane1_8_vsx(const int16_t *src, uint8_t *dest, int dstW,
const uint8_t *dither, int offset)
{
const int dst_u = -(uintptr_t)dest & 15;
int i, j;
LOCAL_ALIGNED(16, int16_t, val, [16]);
const vector uint16_t shifts = (vector uint16_t) {7, 7, 7, 7, 7, 7, 7, 7};
vector int16_t vi, vileft, ditherleft, ditherright;
vector uint8_t vd;
for (j = 0; j < 16; j++) {
val[j] = dither[(dst_u + offset + j) & 7];
}
ditherleft = vec_ld(0, val);
ditherright = vec_ld(0, &val[8]);
yuv2plane1_8_u(src, dest, dst_u, dither, offset, 0);
for (i = dst_u; i < dstW - 15; i += 16) {
vi = vec_vsx_ld(0, &src[i]);
vi = vec_adds(ditherleft, vi);
vileft = vec_sra(vi, shifts);
vi = vec_vsx_ld(0, &src[i + 8]);
vi = vec_adds(ditherright, vi);
vi = vec_sra(vi, shifts);
vd = vec_packsu(vileft, vi);
vec_st(vd, 0, &dest[i]);
}
yuv2plane1_8_u(src, dest, dstW, dither, offset, i);
}
#endif /* HAVE_VSX */
av_cold void ff_sws_init_swscale_vsx(SwsContext *c)
{
#if HAVE_VSX
enum AVPixelFormat dstFormat = c->dstFormat;
if (!(av_get_cpu_flags() & AV_CPU_FLAG_VSX))
return;
#if !HAVE_BIGENDIAN
if (c->srcBpc == 8 && c->dstBpc <= 14) {
c->hyScale = c->hcScale = hScale_real_vsx;
}
if (!is16BPS(dstFormat) && !isNBPS(dstFormat) &&
dstFormat != AV_PIX_FMT_NV12 && dstFormat != AV_PIX_FMT_NV21 &&
dstFormat != AV_PIX_FMT_GRAYF32BE && dstFormat != AV_PIX_FMT_GRAYF32LE &&
!c->needAlpha) {
c->yuv2planeX = yuv2planeX_vsx;
}
#endif
if (!(c->flags & (SWS_BITEXACT | SWS_FULL_CHR_H_INT)) && !c->needAlpha) {
switch (c->dstBpc) {
case 8:
c->yuv2plane1 = yuv2plane1_8_vsx;
break;
}
}
#endif /* HAVE_VSX */
}
|
