mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2024-12-17 21:14:47 +00:00
7a556ebccf
* commit '0c15a9aa7e1654a19144eb594f9639a57fd47482': sh4: Remove dubious aligned dsputil code Conflicts: libavcodec/sh4/dsputil_align.c libavcodec/sh4/h264chroma_init.c libavcodec/sh4/hpeldsp.c libavcodec/sh4/qpel.c If someone wants to maintain the sh4 code in ffmpeg, wants to add more optimizations, or volunteers to maintain any of what is removed here and can confirm that they are faster. Then please contact us! Merged-by: Michael Niedermayer <michaelni@gmx.at>
108 lines
3.3 KiB
C
108 lines
3.3 KiB
C
/*
|
|
* sh4 dsputil
|
|
*
|
|
* Copyright (c) 2003 BERO <bero@geocities.co.jp>
|
|
*
|
|
* 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 "libavutil/attributes.h"
|
|
#include "libavcodec/avcodec.h"
|
|
#include "libavcodec/dsputil.h"
|
|
#include "dsputil_sh4.h"
|
|
#include "sh4.h"
|
|
|
|
static void memzero_align8(void *dst,size_t size)
|
|
{
|
|
int fpscr;
|
|
fp_single_enter(fpscr);
|
|
dst = (char *)dst + size;
|
|
size /= 32;
|
|
__asm__ volatile (
|
|
" fldi0 fr0\n"
|
|
" fldi0 fr1\n"
|
|
" fschg\n" // double
|
|
"1: \n" \
|
|
" dt %1\n"
|
|
" fmov dr0,@-%0\n"
|
|
" fmov dr0,@-%0\n"
|
|
" fmov dr0,@-%0\n"
|
|
" bf.s 1b\n"
|
|
" fmov dr0,@-%0\n"
|
|
" fschg" //back to single
|
|
: "+r"(dst),"+r"(size) :: "memory" );
|
|
fp_single_leave(fpscr);
|
|
}
|
|
|
|
static void clear_blocks_sh4(int16_t *blocks)
|
|
{
|
|
memzero_align8(blocks,sizeof(int16_t)*6*64);
|
|
}
|
|
|
|
static void idct_put(uint8_t *dest, int line_size, int16_t *block)
|
|
{
|
|
int i;
|
|
const uint8_t *cm = ff_cropTbl + MAX_NEG_CROP;
|
|
ff_idct_sh4(block);
|
|
for(i=0;i<8;i++) {
|
|
dest[0] = cm[block[0]];
|
|
dest[1] = cm[block[1]];
|
|
dest[2] = cm[block[2]];
|
|
dest[3] = cm[block[3]];
|
|
dest[4] = cm[block[4]];
|
|
dest[5] = cm[block[5]];
|
|
dest[6] = cm[block[6]];
|
|
dest[7] = cm[block[7]];
|
|
dest+=line_size;
|
|
block+=8;
|
|
}
|
|
}
|
|
static void idct_add(uint8_t *dest, int line_size, int16_t *block)
|
|
{
|
|
int i;
|
|
const uint8_t *cm = ff_cropTbl + MAX_NEG_CROP;
|
|
ff_idct_sh4(block);
|
|
for(i=0;i<8;i++) {
|
|
dest[0] = cm[dest[0]+block[0]];
|
|
dest[1] = cm[dest[1]+block[1]];
|
|
dest[2] = cm[dest[2]+block[2]];
|
|
dest[3] = cm[dest[3]+block[3]];
|
|
dest[4] = cm[dest[4]+block[4]];
|
|
dest[5] = cm[dest[5]+block[5]];
|
|
dest[6] = cm[dest[6]+block[6]];
|
|
dest[7] = cm[dest[7]+block[7]];
|
|
dest+=line_size;
|
|
block+=8;
|
|
}
|
|
}
|
|
|
|
av_cold void ff_dsputil_init_sh4(DSPContext *c, AVCodecContext *avctx)
|
|
{
|
|
const int idct_algo= avctx->idct_algo;
|
|
const int high_bit_depth = avctx->bits_per_raw_sample > 8;
|
|
|
|
if (!high_bit_depth)
|
|
c->clear_blocks = clear_blocks_sh4;
|
|
if (avctx->bits_per_raw_sample <= 8 &&
|
|
(idct_algo==FF_IDCT_AUTO || idct_algo==FF_IDCT_SH4)) {
|
|
c->idct_put = idct_put;
|
|
c->idct_add = idct_add;
|
|
c->idct = ff_idct_sh4;
|
|
c->idct_permutation_type= FF_NO_IDCT_PERM;
|
|
}
|
|
}
|