idct_arai.cc

PIXIL is a small footprint operating environment, complete with PDA PIM applications, a browser and

      a6 = tmp[v][1]-tmp[v][7];
      a7 = tmp1 + tmp2;

      tmp4 = MUL32(C6,(a4+a6));
      b2 = IDESCALE(MUL32(C4 , a2)       , IDCT_PostM1_Shift);
      b4 = IDESCALE(MUL32(Q  , a4) -tmp4 , IDCT_PostM1_Shift);
      b5 = IDESCALE(MUL32(C4 , a5)       , IDCT_PostM1_Shift);
      b6 = IDESCALE(MUL32(R  , a6) -tmp4 , IDCT_PostM1_Shift);

      a0 >>= -(IDCT_M1Scale - IDCT_PostM1_Shift);
      a1 >>= -(IDCT_M1Scale - IDCT_PostM1_Shift);
      a3 >>= -(IDCT_M1Scale - IDCT_PostM1_Shift);
      a7 >>= -(IDCT_M1Scale - IDCT_PostM1_Shift);

      tmp3 = b6-a7;
      n0 = tmp3-b5;
      n1 = a0-a1;
      n2 = b2-a3;
      n3 = a0+a1;

      m3 = n1+n2;
      m4 = n3+a3;
      m5 = n1-n2;
      m6 = n3-a3;
      m7 = b4-n0;

      out[v][0] = IDESCALE( (m4+a7)   , IDCT_PostM1_NK);
      out[v][1] = IDESCALE( (m3+tmp3) , IDCT_PostM1_NK);
      out[v][2] = IDESCALE( (m5-n0)   , IDCT_PostM1_NK);
      out[v][3] = IDESCALE( (m6-m7)   , IDCT_PostM1_NK);
      out[v][4] = IDESCALE( (m6+m7)   , IDCT_PostM1_NK);
      out[v][5] = IDESCALE( (m5+n0)   , IDCT_PostM1_NK);
      out[v][6] = IDESCALE( (m3-tmp3) , IDCT_PostM1_NK);
      out[v][7] = IDESCALE( (m4-a7)   , IDCT_PostM1_NK);
    }}
}





//// --------------- The following IDCT-code originates from libJPEG ! -----------------

/**********************************************************/
/* inverse two dimensional DCT, Chen-Wang algorithm       */
/* (cf. IEEE ASSP-32, pp. 803-816, Aug. 1984)             */
/* 32-bit integer arithmetic (8 bit coefficients)         */
/* 11 mults, 29 adds per DCT                              */
/*                                      sE, 18.8.91       */
/**********************************************************/
/* coefficients extended to 12 bit for IEEE1180-1990      */
/* compliance                           sE,  2.1.94       */
/**********************************************************/

/* this code assumes >> to be a two's-complement arithmetic */
/* right shift: (-2)>>1 == -1 , (-3)>>1 == -2               */

// #include "config.h"

#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) */

/* global declarations */
//void Initialize_Fast_IDCT _ANSI_ARGS_((void));
//void Fast_IDCT _ANSI_ARGS_((short *block));

/* private prototypes */
//static void idctrow _ANSI_ARGS_((short *blk));
//static void idctcol _ANSI_ARGS_((short *blk));

/* row (horizontal) IDCT
 *
 *           7                       pi         1
 * dst[k] = sum c[l] * src[l] * cos( -- * ( k + - ) * l )
 *          l=0                      8          2
 *
 * where: c[0]    = 128
 *        c[1..7] = 128*sqrt(2)
 */

inline void idctrow(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;
}

/* column (vertical) IDCT
 *
 *             7                         pi         1
 * dst[8*k] = sum c[l] * src[8*l] * cos( -- * ( k + - ) * l )
 *            l=0                        8          2
 *
 * where: c[0]    = 1/1024
 *        c[1..7] = (1/1024)*sqrt(2)
 */
inline void idctcol2(short **in,int i,short** out)
{
  int x0, x1, x2, x3, x4, x5, x6, x7, x8;

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

  x0 = (in[0][i]<<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 */
  out[0][i] = (x7+x1)>>14;
  out[1][i] = (x3+x2)>>14;
  out[2][i] = (x0+x4)>>14;
  out[3][i] = (x8+x6)>>14;
  out[4][i] = (x8-x6)>>14;
  out[5][i] = (x0-x4)>>14;
  out[6][i] = (x3-x2)>>14;
  out[7][i] = (x7-x1)>>14;
}

inline void idctcol2b(short *in,int i,Pixel** out,bool add)
{
  int x0, x1, x2, x3, x4, x5, x6, x7, x8;

  /* shortcut */
  if (!((x1 = (in[4*8]<<8)) | (x2 = in[6*8]) | (x3 = in[2*8]) |
        (x4 = in[1*8]) | (x5 = in[7*8]) | (x6 = in[5*8]) | (x7 = in[3*8])))
  {
    if (add)
      {
#if 0
        out[0][i] = clip2_0_255[ out[0][i] + ((in[0][i]+32)>>6)];
        out[1][i] = clip2_0_255[ out[1][i] + ((in[1][i]+32)>>6)];
        out[2][i] = clip2_0_255[ out[2][i] + ((in[2][i]+32)>>6)];
        out[3][i] = clip2_0_255[ out[3][i] + ((in[3][i]+32)>>6)];
        out[4][i] = clip2_0_255[ out[4][i] + ((in[4][i]+32)>>6)];
        out[5][i] = clip2_0_255[ out[5][i] + ((in[5][i]+32)>>6)];
        out[6][i] = clip2_0_255[ out[6][i] + ((in[6][i]+32)>>6)];
        out[7][i] = clip2_0_255[ out[7][i] + ((in[7][i]+32)>>6)];
        return;
#endif
      }
    else
      {
#if 1
        out[0][i] = out[1][i] = out[2][i] = out[3][i] =
        out[4][i] = out[5][i] = out[6][i] = out[7][i] = clip2_0_255[(in[0*8]+32)>>6];  //iclp
        return;
#endif
      }
  }

  x0 = (in[0*8]<<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 */

  if (add)
    {
      out[0][i] = clip2_0_255[ out[0][i] + ((x7+x1)>>14) ];
      out[7][i] = clip2_0_255[ out[7][i] + ((x7-x1)>>14) ];
      out[1][i] = clip2_0_255[ out[1][i] + ((x3+x2)>>14) ];
      out[6][i] = clip2_0_255[ out[6][i] + ((x3-x2)>>14) ];
      out[2][i] = clip2_0_255[ out[2][i] + ((x0+x4)>>14) ];
      out[5][i] = clip2_0_255[ out[5][i] + ((x0-x4)>>14) ];
      out[3][i] = clip2_0_255[ out[3][i] + ((x8+x6)>>14) ];
      out[4][i] = clip2_0_255[ out[4][i] + ((x8-x6)>>14) ];
    }
  else
    {
      out[0][i] = clip2_0_255[ ((x7+x1)>>14) ];
      out[7][i] = clip2_0_255[ ((x7-x1)>>14) ];
      out[1][i] = clip2_0_255[ ((x3+x2)>>14) ];
      out[6][i] = clip2_0_255[ ((x3-x2)>>14) ];
      out[2][i] = clip2_0_255[ ((x0+x4)>>14) ];
      out[5][i] = clip2_0_255[ ((x0-x4)>>14) ];
      out[3][i] = clip2_0_255[ ((x8+x6)>>14) ];
      out[4][i] = clip2_0_255[ ((x8-x6)>>14) ];
    }
}

/* two dimensional inverse discrete cosine transform */
void IDCT_Int2(short* in[8], short* out[8])
{
  int i;

  for (i=0; i<8; i++)
    idctrow(in[i]);

  for (i=0; i<8; i++)
    idctcol2(in,i,out);
}


void IDCT_Int2b(short* in, Pixel* out[8],bool add)
{
  int i;

  for (i=0; i<8; i++)
    idctrow(in+8*i);

  for (i=0; i<8; i++)
    idctcol2b(in+i,i,out,add);
}