dsp_dct.c

基于DM642平台的H.264编码器优化代码

#include <math.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include "dsp_dct.h"
#include "dsp_type.h"
#include "dsp_global.h"
#include "dsp_stream.h"
#include "dsp_vop.h"
#include "dsp_vlc.h"
//	#include "idct_8x8.h"
//	#include "fdct_8x8.h"


static double c11[8][8]; /* transform coefficients */ //global
static short iclip[1024]; /* clipping table */ //global
static short *iclp;//global

#define W1 2841 /* 2048*sqrt(2)*cos(1*pi/16) */
#define W2 2676 /* 2048*sqrt(2)*cos(2*pi/16) */
#define W3 2408 /* 2048*sqrt(2)*cos(3*pi/16) */
#define W5 1609 /* 2048*sqrt(2)*cos(5*pi/16) */
#define W6 1108 /* 2048*sqrt(2)*cos(6*pi/16) */
#define W7 565  /* 2048*sqrt(2)*cos(7*pi/16) */

void init_fdct_enc()
{
  int i, j;
  double s;

  for (i=0; i<8; i++)
  {
    s = (i==0) ? sqrt(0.125) : 0.5;

    for (j=0; j<8; j++)
      c11[i][j] = s * cos((PI/8.0)*i*(j+0.5));
  }
}

void init_idct_enc()
{
  int i;

  iclp = iclip+512;
  for (i= -512; i<512; i++)
    iclp[i] = (i<-256) ? -256 : ((i>255) ? 255 : i);
}

void fdct_enc(short *block)

{
  int i, j, k;
  double s;
  double tmp[64];

  for (i=0; i<8; i++)
    for (j=0; j<8; j++)
    {
      s = 0.0;

      for (k=0; k<8; k++)
        s += c11[j][k] * block[8*i+k];

      tmp[8*i+j] = s;
    }

  for (j=0; j<8; j++)
    for (i=0; i<8; i++)
    {
      s = 0.0;

      for (k=0; k<8; k++)
        s += c11[i][k] * tmp[8*k+j];

      block[8*i+j] = (int)floor(s+0.499999);
      /*
       * reason for adding 0.499999 instead of 0.5:
       * s is quite often x.5 (at least for i and/or j = 0 or 4)
       * and setting the rounding threshold exactly to 0.5 leads to an
       * extremely high arithmetic implementation dependency of the result;
       * s being between x.5 and x.500001 (which is now incorrectly rounded
       * downwards instead of upwards) is assumed to occur less often
       * (if at all)
       */
    }
}
void idct_enc(short *block)

{
  int i;

  for (i=0; i<8; i++)
    idctrow_enc(block+8*i);

  for (i=0; i<8; i++)
    idctcol_enc(block+i);
}

static void idctrow_enc(short *blk)

{
  int x0, x1, x2, x3, x4, x5, x6, x7, x8;

  /* shortcut */
  if (!((x1 = blk[4]<<11) | (x2 = blk[6]) | (x3 = blk[2]) |
        (x4 = blk[1]) | (x5 = blk[7]) | (x6 = blk[5]) | (x7 = blk[3])))
  {
    blk[0]=blk[1]=blk[2]=blk[3]=blk[4]=blk[5]=blk[6]=blk[7]=blk[0]<<3;
    return;
  }

  x0 = (blk[0]<<11) + 128; /* for proper rounding in the fourth stage */

  /* first stage */
  x8 = W7*(x4+x5);
  x4 = x8 + (W1-W7)*x4;
  x5 = x8 - (W1+W7)*x5;
  x8 = W3*(x6+x7);
  x6 = x8 - (W3-W5)*x6;
  x7 = x8 - (W3+W5)*x7;
  
  /* second stage */
  x8 = x0 + x1;
  x0 -= x1;
  x1 = W6*(x3+x2);
  x2 = x1 - (W2+W6)*x2;
  x3 = x1 + (W2-W6)*x3;
  x1 = x4 + x6;
  x4 -= x6;
  x6 = x5 + x7;
  x5 -= x7;
  
  /* third stage */
  x7 = x8 + x3;
  x8 -= x3;
  x3 = x0 + x2;
  x0 -= x2;
  x2 = (181*(x4+x5)+128)>>8;
  x4 = (181*(x4-x5)+128)>>8;
  
  /* fourth stage */
  blk[0] = (x7+x1)>>8;
  blk[1] = (x3+x2)>>8;
  blk[2] = (x0+x4)>>8;
  blk[3] = (x8+x6)>>8;
  blk[4] = (x8-x6)>>8;
  blk[5] = (x0-x4)>>8;
  blk[6] = (x3-x2)>>8;
  blk[7] = (x7-x1)>>8;
}

static void idctcol_enc(short *blk)

{
  int x0, x1, x2, x3, x4, x5, x6, x7, x8;

  /* shortcut */
  if (!((x1 = (blk[8*4]<<8)) | (x2 = blk[8*6]) | (x3 = blk[8*2]) |
        (x4 = blk[8*1]) | (x5 = blk[8*7]) | (x6 = blk[8*5]) | (x7 = blk[8*3])))
  {
    blk[8*0]=blk[8*1]=blk[8*2]=blk[8*3]=blk[8*4]=blk[8*5]=blk[8*6]=blk[8*7]=
      iclp[(blk[8*0]+32)>>6];
    return;
  }

  x0 = (blk[8*0]<<8) + 8192;

  /* first stage */
  x8 = W7*(x4+x5) + 4;
  x4 = (x8+(W1-W7)*x4)>>3;
  x5 = (x8-(W1+W7)*x5)>>3;
  x8 = W3*(x6+x7) + 4;
  x6 = (x8-(W3-W5)*x6)>>3;
  x7 = (x8-(W3+W5)*x7)>>3;
  
  /* second stage */
  x8 = x0 + x1;
  x0 -= x1;
  x1 = W6*(x3+x2) + 4;
  x2 = (x1-(W2+W6)*x2)>>3;
  x3 = (x1+(W2-W6)*x3)>>3;
  x1 = x4 + x6;
  x4 -= x6;
  x6 = x5 + x7;
  x5 -= x7;
  
  /* third stage */
  x7 = x8 + x3;
  x8 -= x3;
  x3 = x0 + x2;
  x0 -= x2;
  x2 = (181*(x4+x5)+128)>>8;
  x4 = (181*(x4-x5)+128)>>8;
  
  /* fourth stage */
  blk[8*0] = iclp[(x7+x1)>>14];
  blk[8*1] = iclp[(x3+x2)>>14];
  blk[8*2] = iclp[(x0+x4)>>14];
  blk[8*3] = iclp[(x8+x6)>>14];
  blk[8*4] = iclp[(x8-x6)>>14];
  blk[8*5] = iclp[(x0-x4)>>14];
  blk[8*6] = iclp[(x3-x2)>>14];
  blk[8*7] = iclp[(x7-x1)>>14];
}