/*
 * This module is specialized to the case DCTSIZE = 8.
 */

#include "cjpeg.h"

/*
 * Perform the forward DCT on one block of samples.
 */

void
jpeg_fdct(float *data)
{
  float tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
  float tmp10, tmp11, tmp12, tmp13;
  float z1, z2, z3, z4, z5, z11, z13;
  float *dataptr;
  int ctr;

  /* Pass 1: process rows. */

  dataptr = data;
  for (ctr = 0; ctr < DCTSIZE; ctr++) {
    /* Load data into workspace */
    tmp0 = dataptr[0] + dataptr[7];
    tmp7 = dataptr[0] - dataptr[7];
    tmp1 = dataptr[1] + dataptr[6];
    tmp6 = dataptr[1] - dataptr[6];
    tmp2 = dataptr[2] + dataptr[5];
    tmp5 = dataptr[2] - dataptr[5];
    tmp3 = dataptr[3] + dataptr[4];
    tmp4 = dataptr[3] - dataptr[4];

    /* Even part */

    tmp10 = tmp0 + tmp3;	/* phase 2 */
    tmp13 = tmp0 - tmp3;
    tmp11 = tmp1 + tmp2;
    tmp12 = tmp1 - tmp2;

    /* Apply unsigned->signed conversion */
    dataptr[0] = tmp10 + tmp11; /* phase 3 */
    dataptr[4] = tmp10 - tmp11;

    z1 = (tmp12 + tmp13) * ((float) 0.707106781); /* c4 */
    dataptr[2] = tmp13 + z1;	/* phase 5 */
    dataptr[6] = tmp13 - z1;

    /* Odd part */

    tmp10 = tmp4 + tmp5;	/* phase 2 */
    tmp11 = tmp5 + tmp6;
    tmp12 = tmp6 + tmp7;

    /* The rotator is modified from fig 4-8 to avoid extra negations. */
    z5 = (tmp10 - tmp12) * ((float) 0.382683433); /* c6 */
    z2 = ((float) 0.541196100) * tmp10 + z5; /* c2-c6 */
    z4 = ((float) 1.306562965) * tmp12 + z5; /* c2+c6 */
    z3 = tmp11 * ((float) 0.707106781); /* c4 */

    z11 = tmp7 + z3;		/* phase 5 */
    z13 = tmp7 - z3;

    dataptr[5] = z13 + z2;	/* phase 6 */
    dataptr[3] = z13 - z2;
    dataptr[1] = z11 + z4;
    dataptr[7] = z11 - z4;

    dataptr += DCTSIZE;		/* advance pointer to next row */
  }

  /* Pass 2: process columns. */

  dataptr = data;
  for (ctr = DCTSIZE-1; ctr >= 0; ctr--) {
    tmp0 = dataptr[DCTSIZE*0] + dataptr[DCTSIZE*7];
    tmp7 = dataptr[DCTSIZE*0] - dataptr[DCTSIZE*7];
    tmp1 = dataptr[DCTSIZE*1] + dataptr[DCTSIZE*6];
    tmp6 = dataptr[DCTSIZE*1] - dataptr[DCTSIZE*6];
    tmp2 = dataptr[DCTSIZE*2] + dataptr[DCTSIZE*5];
    tmp5 = dataptr[DCTSIZE*2] - dataptr[DCTSIZE*5];
    tmp3 = dataptr[DCTSIZE*3] + dataptr[DCTSIZE*4];
    tmp4 = dataptr[DCTSIZE*3] - dataptr[DCTSIZE*4];

    /* Even part */

    tmp10 = tmp0 + tmp3;	/* phase 2 */
    tmp13 = tmp0 - tmp3;
    tmp11 = tmp1 + tmp2;
    tmp12 = tmp1 - tmp2;

    dataptr[DCTSIZE*0] = tmp10 + tmp11; /* phase 3 */
    dataptr[DCTSIZE*4] = tmp10 - tmp11;

    z1 = (tmp12 + tmp13) * ((float) 0.707106781); /* c4 */
    dataptr[DCTSIZE*2] = tmp13 + z1; /* phase 5 */
    dataptr[DCTSIZE*6] = tmp13 - z1;

    /* Odd part */

    tmp10 = tmp4 + tmp5;	/* phase 2 */
    tmp11 = tmp5 + tmp6;
    tmp12 = tmp6 + tmp7;

    /* The rotator is modified from fig 4-8 to avoid extra negations. */
    z5 = (tmp10 - tmp12) * ((float) 0.382683433); /* c6 */
    z2 = ((float) 0.541196100) * tmp10 + z5; /* c2-c6 */
    z4 = ((float) 1.306562965) * tmp12 + z5; /* c2+c6 */
    z3 = tmp11 * ((float) 0.707106781); /* c4 */

    z11 = tmp7 + z3;		/* phase 5 */
    z13 = tmp7 - z3;

    dataptr[DCTSIZE*5] = z13 + z2; /* phase 6 */
    dataptr[DCTSIZE*3] = z13 - z2;
    dataptr[DCTSIZE*1] = z11 + z4;
    dataptr[DCTSIZE*7] = z11 - z4;

    dataptr++;			/* advance pointer to next column */
  }
}