mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-18 03:19:31 +02:00
e4a94d8b36
This avoids SIMD-optimized functions having to sign-extend their stride argument manually to be able to do pointer arithmetic.
176 lines
6.0 KiB
C
176 lines
6.0 KiB
C
/*
|
|
* Copyright (c) 2000, 2001 Fabrice Bellard
|
|
* Copyright (c) 2002-2004 Michael Niedermayer <michaelni@gmx.at>
|
|
*
|
|
* 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 <assert.h>
|
|
#include <stddef.h>
|
|
|
|
#include "bit_depth_template.c"
|
|
|
|
#define H264_CHROMA_MC(OPNAME, OP)\
|
|
static void FUNCC(OPNAME ## h264_chroma_mc2)(uint8_t *_dst /*align 8*/, uint8_t *_src /*align 1*/, ptrdiff_t stride, int h, int x, int y)\
|
|
{\
|
|
pixel *dst = (pixel*)_dst;\
|
|
pixel *src = (pixel*)_src;\
|
|
const int A=(8-x)*(8-y);\
|
|
const int B=( x)*(8-y);\
|
|
const int C=(8-x)*( y);\
|
|
const int D=( x)*( y);\
|
|
int i;\
|
|
stride /= sizeof(pixel);\
|
|
\
|
|
assert(x<8 && y<8 && x>=0 && y>=0);\
|
|
\
|
|
if(D){\
|
|
for(i=0; i<h; i++){\
|
|
OP(dst[0], (A*src[0] + B*src[1] + C*src[stride+0] + D*src[stride+1]));\
|
|
OP(dst[1], (A*src[1] + B*src[2] + C*src[stride+1] + D*src[stride+2]));\
|
|
dst+= stride;\
|
|
src+= stride;\
|
|
}\
|
|
} else if (B + C) {\
|
|
const int E= B+C;\
|
|
const ptrdiff_t step = C ? stride : 1;\
|
|
for(i=0; i<h; i++){\
|
|
OP(dst[0], (A*src[0] + E*src[step+0]));\
|
|
OP(dst[1], (A*src[1] + E*src[step+1]));\
|
|
dst+= stride;\
|
|
src+= stride;\
|
|
}\
|
|
} else {\
|
|
for ( i = 0; i < h; i++){\
|
|
OP(dst[0], A * src[0]);\
|
|
OP(dst[1], A * src[1]);\
|
|
dst += stride;\
|
|
src += stride;\
|
|
}\
|
|
}\
|
|
}\
|
|
\
|
|
static void FUNCC(OPNAME ## h264_chroma_mc4)(uint8_t *_dst /*align 8*/, uint8_t *_src /*align 1*/, ptrdiff_t stride, int h, int x, int y)\
|
|
{\
|
|
pixel *dst = (pixel*)_dst;\
|
|
pixel *src = (pixel*)_src;\
|
|
const int A=(8-x)*(8-y);\
|
|
const int B=( x)*(8-y);\
|
|
const int C=(8-x)*( y);\
|
|
const int D=( x)*( y);\
|
|
int i;\
|
|
stride /= sizeof(pixel);\
|
|
\
|
|
assert(x<8 && y<8 && x>=0 && y>=0);\
|
|
\
|
|
if(D){\
|
|
for(i=0; i<h; i++){\
|
|
OP(dst[0], (A*src[0] + B*src[1] + C*src[stride+0] + D*src[stride+1]));\
|
|
OP(dst[1], (A*src[1] + B*src[2] + C*src[stride+1] + D*src[stride+2]));\
|
|
OP(dst[2], (A*src[2] + B*src[3] + C*src[stride+2] + D*src[stride+3]));\
|
|
OP(dst[3], (A*src[3] + B*src[4] + C*src[stride+3] + D*src[stride+4]));\
|
|
dst+= stride;\
|
|
src+= stride;\
|
|
}\
|
|
} else if (B + C) {\
|
|
const int E= B+C;\
|
|
const ptrdiff_t step = C ? stride : 1;\
|
|
for(i=0; i<h; i++){\
|
|
OP(dst[0], (A*src[0] + E*src[step+0]));\
|
|
OP(dst[1], (A*src[1] + E*src[step+1]));\
|
|
OP(dst[2], (A*src[2] + E*src[step+2]));\
|
|
OP(dst[3], (A*src[3] + E*src[step+3]));\
|
|
dst+= stride;\
|
|
src+= stride;\
|
|
}\
|
|
} else {\
|
|
for ( i = 0; i < h; i++){\
|
|
OP(dst[0], A * src[0]);\
|
|
OP(dst[1], A * src[1]);\
|
|
OP(dst[2], A * src[2]);\
|
|
OP(dst[3], A * src[3]);\
|
|
dst += stride;\
|
|
src += stride;\
|
|
}\
|
|
}\
|
|
}\
|
|
\
|
|
static void FUNCC(OPNAME ## h264_chroma_mc8)(uint8_t *_dst /*align 8*/, uint8_t *_src /*align 1*/, ptrdiff_t stride, int h, int x, int y)\
|
|
{\
|
|
pixel *dst = (pixel*)_dst;\
|
|
pixel *src = (pixel*)_src;\
|
|
const int A=(8-x)*(8-y);\
|
|
const int B=( x)*(8-y);\
|
|
const int C=(8-x)*( y);\
|
|
const int D=( x)*( y);\
|
|
int i;\
|
|
stride /= sizeof(pixel);\
|
|
\
|
|
assert(x<8 && y<8 && x>=0 && y>=0);\
|
|
\
|
|
if(D){\
|
|
for(i=0; i<h; i++){\
|
|
OP(dst[0], (A*src[0] + B*src[1] + C*src[stride+0] + D*src[stride+1]));\
|
|
OP(dst[1], (A*src[1] + B*src[2] + C*src[stride+1] + D*src[stride+2]));\
|
|
OP(dst[2], (A*src[2] + B*src[3] + C*src[stride+2] + D*src[stride+3]));\
|
|
OP(dst[3], (A*src[3] + B*src[4] + C*src[stride+3] + D*src[stride+4]));\
|
|
OP(dst[4], (A*src[4] + B*src[5] + C*src[stride+4] + D*src[stride+5]));\
|
|
OP(dst[5], (A*src[5] + B*src[6] + C*src[stride+5] + D*src[stride+6]));\
|
|
OP(dst[6], (A*src[6] + B*src[7] + C*src[stride+6] + D*src[stride+7]));\
|
|
OP(dst[7], (A*src[7] + B*src[8] + C*src[stride+7] + D*src[stride+8]));\
|
|
dst+= stride;\
|
|
src+= stride;\
|
|
}\
|
|
} else if (B + C) {\
|
|
const int E= B+C;\
|
|
const ptrdiff_t step = C ? stride : 1;\
|
|
for(i=0; i<h; i++){\
|
|
OP(dst[0], (A*src[0] + E*src[step+0]));\
|
|
OP(dst[1], (A*src[1] + E*src[step+1]));\
|
|
OP(dst[2], (A*src[2] + E*src[step+2]));\
|
|
OP(dst[3], (A*src[3] + E*src[step+3]));\
|
|
OP(dst[4], (A*src[4] + E*src[step+4]));\
|
|
OP(dst[5], (A*src[5] + E*src[step+5]));\
|
|
OP(dst[6], (A*src[6] + E*src[step+6]));\
|
|
OP(dst[7], (A*src[7] + E*src[step+7]));\
|
|
dst+= stride;\
|
|
src+= stride;\
|
|
}\
|
|
} else {\
|
|
for ( i = 0; i < h; i++){\
|
|
OP(dst[0], A * src[0]);\
|
|
OP(dst[1], A * src[1]);\
|
|
OP(dst[2], A * src[2]);\
|
|
OP(dst[3], A * src[3]);\
|
|
OP(dst[4], A * src[4]);\
|
|
OP(dst[5], A * src[5]);\
|
|
OP(dst[6], A * src[6]);\
|
|
OP(dst[7], A * src[7]);\
|
|
dst += stride;\
|
|
src += stride;\
|
|
}\
|
|
}\
|
|
}
|
|
|
|
#define op_avg(a, b) a = (((a)+(((b) + 32)>>6)+1)>>1)
|
|
#define op_put(a, b) a = (((b) + 32)>>6)
|
|
|
|
H264_CHROMA_MC(put_ , op_put)
|
|
H264_CHROMA_MC(avg_ , op_avg)
|
|
#undef op_avg
|
|
#undef op_put
|