jcdctmgr.c

这是在PCA下的基于IPP库示例代码例子,在网上下了IPP的库之后,设置相关参数就可以编译该代码.

/*
 * jcdctmgr.c
 *
 * Copyright (C) 1994-1996, Thomas G. Lane.
 * This file is part of the Independent JPEG Group's software.
 * For conditions of distribution and use, see the accompanying README file.
 *
 * This file contains the forward-DCT management logic.
 * This code selects a particular DCT implementation to be used,
 * and it performs related housekeeping chores including coefficient
 * quantization.
 */

#define JPEG_INTERNALS
#include "jinclude.h"
#include "jpeglib.h"
#include "jdct.h"   /* Private declarations for DCT subsystem */
#include "jpegipp.h"


/* Private subobject for this module */

typedef struct {
  struct jpeg_forward_dct pub;  /* public fields */

  /* Pointer to the DCT routine actually in use */
  forward_DCT_method_ptr do_dct;

  /* The actual post-DCT divisors --- not identical to the quant table
   * entries, because of scaling (especially for an unnormalized DCT).
   * Each table is given in normal array order.
   */
  DCTELEM * divisors[NUM_QUANT_TBLS];

#ifdef DCT_FLOAT_SUPPORTED
  /* Same as above for the floating-point case. */
  float_DCT_method_ptr do_float_dct;
  FAST_FLOAT * float_divisors[NUM_QUANT_TBLS];
#endif
} my_fdct_controller;

typedef my_fdct_controller * my_fdct_ptr;


/*
 * Initialize for a processing pass.
 * Verify that all referenced Q-tables are present, and set up
 * the divisor table for each one.
 * In the current implementation, DCT of all components is done during
 * the first pass, even if only some components will be output in the
 * first scan.  Hence all components should be examined here.
 */

METHODDEF(void)
start_pass_fdctmgr (j_compress_ptr cinfo)
{
  my_fdct_ptr fdct = (my_fdct_ptr) cinfo->fdct;
  int ci, qtblno, i;
  jpeg_component_info *compptr;
  JQUANT_TBL * qtbl;
  DCTELEM * dtbl;

  Ipp8u rawqtbl[DCTSIZE2];
  int izigzag_index[DCTSIZE2] =
  {
     0,  1,  8, 16,  9,  2,  3, 10,
    17, 24, 32, 25, 18, 11,  4,  5,
    12, 19, 26, 33, 40, 48, 41, 34,
    27, 20, 13,  6,  7, 14, 21, 28,
    35, 42, 49, 56, 57, 50, 43, 36,
    29, 22, 15, 23, 30, 37, 44, 51,
    58, 59, 52, 45, 38, 31, 39, 46,
    53, 60, 61, 54, 47, 55, 62, 63
  };

  for(ci = 0, compptr = cinfo->comp_info; ci < cinfo->num_components; ci++, compptr++)
  {
    qtblno = compptr->quant_tbl_no;

    /* Make sure specified quantization table is present */
    if(qtblno < 0 || qtblno >= NUM_QUANT_TBLS || cinfo->quant_tbl_ptrs[qtblno] == NULL)
      ERREXIT1(cinfo, JERR_NO_QUANT_TABLE, qtblno);

    qtbl = cinfo->quant_tbl_ptrs[qtblno];

    /* Compute divisors for this quant table */
    /* We may do this more than once for same table, but it's not a big deal */
    switch(cinfo->dct_method)
    {
#ifdef DCT_ISLOW_SUPPORTED
    case JDCT_ISLOW:
      /* For LL&M IDCT method, divisors are equal to raw quantization
       * coefficients multiplied by 8 (to counteract scaling).
       */
      if(fdct->divisors[qtblno] == NULL)
      {
        fdct->divisors[qtblno] = (DCTELEM *)
          (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
          DCTSIZE2 * SIZEOF(DCTELEM));
      }

      dtbl = fdct->divisors[qtblno];

      if(cinfo->UseIPP) {
        /* reorder to zig-zag, because IPPJ expect raw tables in zig-zag */
        /* but IJG have it in natural order */
        for(i = 0; i < DCTSIZE2; i++)
        {
          rawqtbl[i] = (unsigned char)qtbl->quantval[izigzag_index[i]];
        }
        /* build encoder quant table */
        ippiQuantFwdTableInit_JPEG_8u16u(rawqtbl,(Ipp16u*)dtbl);
      } else {
        for(i = 0; i < DCTSIZE2; i++)
        {
          dtbl[i] = ((DCTELEM) qtbl->quantval[i]) << 3;
        }
      }

      break;
#endif

#ifdef DCT_IFAST_SUPPORTED
    case JDCT_IFAST:
      {
        /* For AA&N IDCT method, divisors are equal to quantization
         * coefficients scaled by scalefactor[row]*scalefactor[col], where
         *   scalefactor[0] = 1
         *   scalefactor[k] = cos(k*PI/16) * sqrt(2)    for k=1..7
         * We apply a further scale factor of 8.
         */
#define CONST_BITS 14
         static const INT16 aanscales[DCTSIZE2] = {
           /* precomputed values scaled up by 14 bits */
           16384, 22725, 21407, 19266, 16384, 12873,  8867,  4520,
           22725, 31521, 29692, 26722, 22725, 17855, 12299,  6270,
           21407, 29692, 27969, 25172, 21407, 16819, 11585,  5906,
           19266, 26722, 25172, 22654, 19266, 15137, 10426,  5315,
           16384, 22725, 21407, 19266, 16384, 12873,  8867,  4520,
           12873, 17855, 16819, 15137, 12873, 10114,  6967,  3552,
            8867, 12299, 11585, 10426,  8867,  6967,  4799,  2446,
            4520,  6270,  5906,  5315,  4520,  3552,  2446,  1247
         };
         SHIFT_TEMPS

         if (fdct->divisors[qtblno] == NULL) {
           fdct->divisors[qtblno] = (DCTELEM *)
               (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
               DCTSIZE2 * SIZEOF(DCTELEM));
         }
         dtbl = fdct->divisors[qtblno];
         for (i = 0; i < DCTSIZE2; i++) {
           dtbl[i] = (DCTELEM)
               DESCALE(MULTIPLY16V16((INT32) qtbl->quantval[i],
               (INT32) aanscales[i]),
               CONST_BITS-3);
         }
      }
      break;
#endif
#ifdef DCT_FLOAT_SUPPORTED
    case JDCT_FLOAT:
      {
        /* For float AA&N IDCT method, divisors are equal to quantization
         * coefficients scaled by scalefactor[row]*scalefactor[col], where
         *   scalefactor[0] = 1
         *   scalefactor[k] = cos(k*PI/16) * sqrt(2)    for k=1..7
         * We apply a further scale factor of 8.
         * What's actually stored is 1/divisor so that the inner loop can
         * use a multiplication rather than a division.
         */
        FAST_FLOAT * fdtbl;
        int row, col;
        static const double aanscalefactor[DCTSIZE] = {
          1.0, 1.387039845, 1.306562965, 1.175875602,
          1.0, 0.785694958, 0.541196100, 0.275899379
        };

        if (fdct->float_divisors[qtblno] == NULL) {
          fdct->float_divisors[qtblno] = (FAST_FLOAT *)
              (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
              DCTSIZE2 * SIZEOF(FAST_FLOAT));
        }
        fdtbl = fdct->float_divisors[qtblno];
        i = 0;
        for (row = 0; row < DCTSIZE; row++) {
          for (col = 0; col < DCTSIZE; col++) {
            fdtbl[i] = (FAST_FLOAT)
              (1.0 / (((double) qtbl->quantval[i] *
              aanscalefactor[row] * aanscalefactor[col] * 8.0)));
            i++;
          }
        }
      }
      break;
#endif
    default:
      ERREXIT(cinfo, JERR_NOT_COMPILED);
      break;
    }
  }
}


/*
 * Perform forward DCT on one or more blocks of a component.
 *
 * The input samples are taken from the sample_data[] array starting at
 * position start_row/start_col, and moving to the right for any additional
 * blocks. The quantized coefficients are returned in coef_blocks[].
 */

METHODDEF(void)
forward_DCT (j_compress_ptr cinfo, jpeg_component_info * compptr,
       JSAMPARRAY sample_data, JBLOCKROW coef_blocks,
       JDIMENSION start_row, JDIMENSION start_col,
       JDIMENSION num_blocks)
/* This version is used for integer DCT implementations. */
{
  /* This routine is heavily used, so it's worth coding it tightly. */
  my_fdct_ptr fdct = (my_fdct_ptr) cinfo->fdct;
  forward_DCT_method_ptr do_dct = fdct->do_dct;
  DCTELEM * divisors = fdct->divisors[compptr->quant_tbl_no];
  DCTELEM workspace[DCTSIZE2];  /* work area for FDCT subroutine */
  JDIMENSION bi;

  sample_data += start_row; /* fold in the vertical offset once */

  for (bi = 0; bi < num_blocks; bi++, start_col += DCTSIZE)
  {
    /* Load data into workspace, applying unsigned->signed conversion */
    {
      register DCTELEM *workspaceptr;
      register JSAMPROW elemptr;
      register int elemr;

      workspaceptr = workspace;
      for (elemr = 0; elemr < DCTSIZE; elemr++)
      {
        elemptr = sample_data[elemr] + start_col;
#if DCTSIZE == 8    /* unroll the inner loop */
        *workspaceptr++ = GETJSAMPLE(*elemptr++) - CENTERJSAMPLE;