Commit 20b4106b authored by Loren Merritt's avatar Loren Merritt

remove x264_mc_clip1.

it's wrong for sufficiently perverse inputs, and clip_uint8 is faster anyway.
parent c17218e8
/*****************************************************************************
* clip1.h: h264 encoder library
*****************************************************************************
* Copyright (C) 2003 Laurent Aimar
* $Id: clip1.h,v 1.1 2004/06/03 19:27:06 fenrir Exp $
*
* Authors: Laurent Aimar <fenrir@via.ecp.fr>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111, USA.
*****************************************************************************/
#ifndef _CLIP1_H
#define _CLIP1_H 1
/* Clip1 table
* XXX : only for tap filter.
*
* With tap filter (( 1, -5, 20, 20, -5, 1 ) + 16 )/ 32
* -> (-2*5 * 255+16)/32 <= out <= (2*1*255 + 2*20*255+16)/32
* -> -80 <= out <= 335
* So we need a table of 80+335+1 = 416 entries
*/
static const uint8_t x264_mc_clip1_table[80+1+335] =
{
/* -80 -> -1 */
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,
/* 0 -> 255 */
0, 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,
162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,
180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,
198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,
216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,
234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,
252,253,254,255,
/* 256 -> 340 */
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,
255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,
255,255,255,255,255,255,255,255,
};
static inline uint8_t x264_mc_clip1( int x )
{
return x264_mc_clip1_table[x+80];
}
static inline uint8_t x264_clip_uint8( int x )
{
return x&(~255) ? (-x)>>31 : x;
}
#endif
......@@ -102,6 +102,11 @@ void x264_log( x264_t *h, int i_level, const char *psz_fmt, ... );
void x264_reduce_fraction( int *n, int *d );
static inline uint8_t x264_clip_uint8( int x )
{
return x&(~255) ? (-x)>>31 : x;
}
static inline int x264_clip3( int v, int i_min, int i_max )
{
return ( (v < i_min) ? i_min : (v > i_max) ? i_max : v );
......
......@@ -32,14 +32,6 @@
int x264_dct4_weight2_zigzag[2][16];
int x264_dct8_weight2_zigzag[2][64];
static inline int clip_uint8( int a )
{
if (a&(~255))
return (-a)>>31;
else
return a;
}
/*
* XXX For all dct dc : input could be equal to output so ...
*/
......@@ -232,7 +224,7 @@ static void add4x4_idct( uint8_t *p_dst, int16_t dct[4][4] )
{
for( x = 0; x < 4; x++ )
{
p_dst[x] = clip_uint8( p_dst[x] + d[y][x] );
p_dst[x] = x264_clip_uint8( p_dst[x] + d[y][x] );
}
p_dst += FDEC_STRIDE;
}
......@@ -356,7 +348,7 @@ static void add8x8_idct8( uint8_t *dst, int16_t dct[8][8] )
#undef DST
#define SRC(x) dct[i][x]
#define DST(x,rhs) dst[i + x*FDEC_STRIDE] = clip_uint8( dst[i + x*FDEC_STRIDE] + ((rhs) >> 6) );
#define DST(x,rhs) dst[i + x*FDEC_STRIDE] = x264_clip_uint8( dst[i + x*FDEC_STRIDE] + ((rhs) >> 6) );
for( i = 0; i < 8; i++ )
IDCT8_1D
#undef SRC
......
......@@ -22,7 +22,6 @@
*****************************************************************************/
#include "common.h"
#include "clip1.h"
#ifdef HAVE_MMX
#include "x86/mc.h"
......@@ -163,7 +162,7 @@ static inline void mc_hh( uint8_t *src, int i_src_stride, uint8_t *dst, int i_ds
{
for( x = 0; x < i_width; x++ )
{
dst[x] = x264_mc_clip1( ( x264_tapfilter1( &src[x] ) + 16 ) >> 5 );
dst[x] = x264_clip_uint8( ( x264_tapfilter1( &src[x] ) + 16 ) >> 5 );
}
src += i_src_stride;
dst += i_dst_stride;
......@@ -177,7 +176,7 @@ static inline void mc_hv( uint8_t *src, int i_src_stride, uint8_t *dst, int i_ds
{
for( x = 0; x < i_width; x++ )
{
dst[x] = x264_mc_clip1( ( x264_tapfilter( &src[x], i_src_stride ) + 16 ) >> 5 );
dst[x] = x264_clip_uint8( ( x264_tapfilter( &src[x], i_src_stride ) + 16 ) >> 5 );
}
src += i_src_stride;
dst += i_dst_stride;
......@@ -206,7 +205,7 @@ static inline void mc_hc( uint8_t *src, int i_src_stride, uint8_t *dst, int i_ds
{
tap[5] = x264_tapfilter1( &pix[ 3*i_src_stride] );
*out = x264_mc_clip1( ( tap[0] - 5*tap[1] + 20 * tap[2] + 20 * tap[3] -5*tap[4] + tap[5] + 512 ) >> 10 );
*out = x264_clip_uint8( ( tap[0] - 5*tap[1] + 20 * tap[2] + 20 * tap[3] -5*tap[4] + tap[5] + 512 ) >> 10 );
/* Next line */
pix += i_src_stride;
......
......@@ -22,7 +22,6 @@
*****************************************************************************/
#include "common.h"
#include "clip1.h"
#ifdef HAVE_MMX
# include "x86/pixel.h"
......
......@@ -26,7 +26,6 @@
#include "common.h"
#include "clip1.h"
#ifdef _MSC_VER
#undef HAVE_MMX /* not finished now */
......
......@@ -22,7 +22,6 @@
*****************************************************************************/
#include "common/common.h"
#include "common/clip1.h"
#include "predict.h"
#include "pixel.h"
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment