Skip to content
Projects
Groups
Snippets
Help
Loading...
Sign in / Register
Toggle navigation
F
ffmpeg
Project
Project
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Packages
Packages
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
submodule
ffmpeg
Commits
f1148390
Commit
f1148390
authored
Feb 08, 2016
by
Clément Bœsch
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
sws/aarch64: add {nv12,nv21,yuv420p,yuv422p}_to_{argb,rgba,abgr,rgba}_neon
parent
7bcc57ad
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
5 changed files
with
138 additions
and
0 deletions
+138
-0
Makefile
libswscale/aarch64/Makefile
+3
-0
swscale_unscaled.c
libswscale/aarch64/swscale_unscaled.c
+132
-0
yuv2rgb_neon.S
libswscale/aarch64/yuv2rgb_neon.S
+0
-0
swscale_internal.h
libswscale/swscale_internal.h
+1
-0
swscale_unscaled.c
libswscale/swscale_unscaled.c
+2
-0
No files found.
libswscale/aarch64/Makefile
0 → 100644
View file @
f1148390
OBJS
+=
aarch64/swscale_unscaled.o
NEON-OBJS
+=
aarch64/yuv2rgb_neon.o
libswscale/aarch64/swscale_unscaled.c
0 → 100644
View file @
f1148390
/*
* 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 "config.h"
#include "libswscale/swscale.h"
#include "libswscale/swscale_internal.h"
#include "libavutil/aarch64/cpu.h"
#define YUV_TO_RGB_TABLE \
c->yuv2rgb_v2r_coeff, \
c->yuv2rgb_u2g_coeff, \
c->yuv2rgb_v2g_coeff, \
c->yuv2rgb_u2b_coeff, \
#define DECLARE_FF_YUVX_TO_RGBX_FUNCS(ifmt, ofmt) \
int ff_##ifmt##_to_##ofmt##_neon(int w, int h, \
uint8_t *dst, int linesize, \
const uint8_t *srcY, int linesizeY, \
const uint8_t *srcU, int linesizeU, \
const uint8_t *srcV, int linesizeV, \
const int16_t *table, \
int y_offset, \
int y_coeff); \
\
static int ifmt##_to_##ofmt##_neon_wrapper(SwsContext *c, const uint8_t *src[], \
int srcStride[], int srcSliceY, int srcSliceH, \
uint8_t *dst[], int dstStride[]) { \
const int16_t yuv2rgb_table[] = { YUV_TO_RGB_TABLE }; \
\
ff_##ifmt##_to_##ofmt##_neon(c->srcW, srcSliceH, \
dst[0] + srcSliceY * dstStride[0], dstStride[0], \
src[0], srcStride[0], \
src[1], srcStride[1], \
src[2], srcStride[2], \
yuv2rgb_table, \
c->yuv2rgb_y_offset >> 6, \
c->yuv2rgb_y_coeff); \
return 0; \
} \
#define DECLARE_FF_YUVX_TO_ALL_RGBX_FUNCS(yuvx) \
DECLARE_FF_YUVX_TO_RGBX_FUNCS(yuvx, argb) \
DECLARE_FF_YUVX_TO_RGBX_FUNCS(yuvx, rgba) \
DECLARE_FF_YUVX_TO_RGBX_FUNCS(yuvx, abgr) \
DECLARE_FF_YUVX_TO_RGBX_FUNCS(yuvx, bgra) \
DECLARE_FF_YUVX_TO_ALL_RGBX_FUNCS
(
yuv420p
)
DECLARE_FF_YUVX_TO_ALL_RGBX_FUNCS
(
yuv422p
)
#define DECLARE_FF_NVX_TO_RGBX_FUNCS(ifmt, ofmt) \
int ff_##ifmt##_to_##ofmt##_neon(int w, int h, \
uint8_t *dst, int linesize, \
const uint8_t *srcY, int linesizeY, \
const uint8_t *srcC, int linesizeC, \
const int16_t *table, \
int y_offset, \
int y_coeff); \
\
static int ifmt##_to_##ofmt##_neon_wrapper(SwsContext *c, const uint8_t *src[], \
int srcStride[], int srcSliceY, int srcSliceH, \
uint8_t *dst[], int dstStride[]) { \
const int16_t yuv2rgb_table[] = { YUV_TO_RGB_TABLE }; \
\
ff_##ifmt##_to_##ofmt##_neon(c->srcW, srcSliceH, \
dst[0] + srcSliceY * dstStride[0], dstStride[0], \
src[0], srcStride[0], src[1], srcStride[1], \
yuv2rgb_table, \
c->yuv2rgb_y_offset >> 6, \
c->yuv2rgb_y_coeff); \
\
return 0; \
} \
#define DECLARE_FF_NVX_TO_ALL_RGBX_FUNCS(nvx) \
DECLARE_FF_NVX_TO_RGBX_FUNCS(nvx, argb) \
DECLARE_FF_NVX_TO_RGBX_FUNCS(nvx, rgba) \
DECLARE_FF_NVX_TO_RGBX_FUNCS(nvx, abgr) \
DECLARE_FF_NVX_TO_RGBX_FUNCS(nvx, bgra) \
DECLARE_FF_NVX_TO_ALL_RGBX_FUNCS
(
nv12
)
DECLARE_FF_NVX_TO_ALL_RGBX_FUNCS
(
nv21
)
/* We need a 16 pixel width alignment. This constraint can easily be removed
* for input reading but for the output which is 4-bytes per pixel (RGBA) the
* assembly might be writing as much as 4*15=60 extra bytes at the end of the
* line, which won't fit the 32-bytes buffer alignment. */
#define SET_FF_NVX_TO_RGBX_FUNC(ifmt, IFMT, ofmt, OFMT, accurate_rnd) do { \
if (c->srcFormat == AV_PIX_FMT_##IFMT \
&& c->dstFormat == AV_PIX_FMT_##OFMT \
&& !(c->srcH & 1) \
&& !(c->srcW & 15) \
&& !accurate_rnd) \
c->swscale = ifmt##_to_##ofmt##_neon_wrapper; \
} while (0)
#define SET_FF_NVX_TO_ALL_RGBX_FUNC(nvx, NVX, accurate_rnd) do { \
SET_FF_NVX_TO_RGBX_FUNC(nvx, NVX, argb, ARGB, accurate_rnd); \
SET_FF_NVX_TO_RGBX_FUNC(nvx, NVX, rgba, RGBA, accurate_rnd); \
SET_FF_NVX_TO_RGBX_FUNC(nvx, NVX, abgr, ABGR, accurate_rnd); \
SET_FF_NVX_TO_RGBX_FUNC(nvx, NVX, bgra, BGRA, accurate_rnd); \
} while (0)
static
void
get_unscaled_swscale_neon
(
SwsContext
*
c
)
{
int
accurate_rnd
=
c
->
flags
&
SWS_ACCURATE_RND
;
SET_FF_NVX_TO_ALL_RGBX_FUNC
(
nv12
,
NV12
,
accurate_rnd
);
SET_FF_NVX_TO_ALL_RGBX_FUNC
(
nv21
,
NV21
,
accurate_rnd
);
SET_FF_NVX_TO_ALL_RGBX_FUNC
(
yuv420p
,
YUV420P
,
accurate_rnd
);
SET_FF_NVX_TO_ALL_RGBX_FUNC
(
yuv422p
,
YUV422P
,
accurate_rnd
);
}
void
ff_get_unscaled_swscale_aarch64
(
SwsContext
*
c
)
{
int
cpu_flags
=
av_get_cpu_flags
();
if
(
have_neon
(
cpu_flags
))
get_unscaled_swscale_neon
(
c
);
}
libswscale/aarch64/yuv2rgb_neon.S
0 → 100644
View file @
f1148390
This diff is collapsed.
Click to expand it.
libswscale/swscale_internal.h
View file @
f1148390
...
...
@@ -877,6 +877,7 @@ extern const AVClass ff_sws_context_class;
void
ff_get_unscaled_swscale
(
SwsContext
*
c
);
void
ff_get_unscaled_swscale_ppc
(
SwsContext
*
c
);
void
ff_get_unscaled_swscale_arm
(
SwsContext
*
c
);
void
ff_get_unscaled_swscale_aarch64
(
SwsContext
*
c
);
/**
* Return function pointer to fastest main scaler path function depending
...
...
libswscale/swscale_unscaled.c
View file @
f1148390
...
...
@@ -1779,6 +1779,8 @@ void ff_get_unscaled_swscale(SwsContext *c)
ff_get_unscaled_swscale_ppc
(
c
);
if
(
ARCH_ARM
)
ff_get_unscaled_swscale_arm
(
c
);
if
(
ARCH_AARCH64
)
ff_get_unscaled_swscale_aarch64
(
c
);
}
/* Convert the palette to the same packed 32-bit format as the palette */
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment