FFmpeg/libswscale/arm/swscale_unscaled.c
Yu Xiaolei 1c67ad9d93 swscale: NEON optimized unscaled rgba to nv12 conversion
Signed-off-by: Yu Xiaolei <dreifachstein@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2013-12-16 00:47:39 +01:00

80 lines
2.9 KiB
C

/*
* Copyright (C) 2013 Xiaolei Yu <dreifachstein@gmail.com>
*
* 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/arm/cpu.h"
extern void rgbx_to_nv12_neon_32(const uint8_t *src, uint8_t *y, uint8_t *chroma,
int width, int height,
int y_stride, int c_stride, int src_stride,
int32_t coeff_tbl[9]);
extern void rgbx_to_nv12_neon_16(const uint8_t *src, uint8_t *y, uint8_t *chroma,
int width, int height,
int y_stride, int c_stride, int src_stride,
int32_t coeff_tbl[9]);
static int rgbx_to_nv12_neon_32_wrapper(SwsContext *context, const uint8_t *src[],
int srcStride[], int srcSliceY, int srcSliceH,
uint8_t *dst[], int dstStride[]) {
rgbx_to_nv12_neon_32(src[0] + srcSliceY * srcStride[0],
dst[0] + srcSliceY * dstStride[0],
dst[1] + (srcSliceY / 2) * dstStride[1],
context->srcW, srcSliceH,
dstStride[0], dstStride[1], srcStride[0],
context->input_rgb2yuv_table);
return 0;
}
static int rgbx_to_nv12_neon_16_wrapper(SwsContext *context, const uint8_t *src[],
int srcStride[], int srcSliceY, int srcSliceH,
uint8_t *dst[], int dstStride[]) {
rgbx_to_nv12_neon_16(src[0] + srcSliceY * srcStride[0],
dst[0] + srcSliceY * dstStride[0],
dst[1] + (srcSliceY / 2) * dstStride[1],
context->srcW, srcSliceH,
dstStride[0], dstStride[1], srcStride[0],
context->input_rgb2yuv_table);
return 0;
}
static void get_unscaled_swscale_neon(SwsContext *c) {
int accurate_rnd = c->flags & SWS_ACCURATE_RND;
if (c->srcFormat == AV_PIX_FMT_RGBA
&& c->dstFormat == AV_PIX_FMT_NV12
&& (c->srcW >= 16)) {
c->swscale = accurate_rnd ? rgbx_to_nv12_neon_32_wrapper
: rgbx_to_nv12_neon_16_wrapper;
}
}
void ff_get_unscaled_swscale_arm(SwsContext *c)
{
int cpu_flags = av_get_cpu_flags();
if (have_neon(cpu_flags))
get_unscaled_swscale_neon(c);
}