xref: /external/jpeg/mips_jidctfst.c

/*
 * IDCT implementation using the MIPS DSP ASE (little endian version)
 *
 * jidctfst.c
 *
 * Copyright (C) 1994-1998, 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 a fast, not so accurate integer implementation of the
 * inverse DCT (Discrete Cosine Transform).  In the IJG code, this routine
 * must also perform dequantization of the input coefficients.
 *
 * A 2-D IDCT can be done by 1-D IDCT on each column followed by 1-D IDCT
 * on each row (or vice versa, but it's more convenient to emit a row at
 * a time).  Direct algorithms are also available, but they are much more
 * complex and seem not to be any faster when reduced to code.
 *
 * This implementation is based on Arai, Agui, and Nakajima's algorithm for
 * scaled DCT.  Their original paper (Trans. IEICE E-71(11):1095) is in
 * Japanese, but the algorithm is described in the Pennebaker & Mitchell
 * JPEG textbook (see REFERENCES section in file README).  The following code
 * is based directly on figure 4-8 in P&M.
 * While an 8-point DCT cannot be done in less than 11 multiplies, it is
 * possible to arrange the computation so that many of the multiplies are
 * simple scalings of the final outputs.  These multiplies can then be
 * folded into the multiplications or divisions by the JPEG quantization
 * table entries.  The AA&N method leaves only 5 multiplies and 29 adds
 * to be done in the DCT itself.
 * The primary disadvantage of this method is that with fixed-point math,
 * accuracy is lost due to imprecise representation of the scaled
 * quantization values.  The smaller the quantization table entry, the less
 * precise the scaled value, so this implementation does worse with high-
 * quality-setting files than with low-quality ones.
 */

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

#ifdef DCT_IFAST_SUPPORTED


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

#if DCTSIZE != 8
  Sorry, this code only copes with 8x8 DCTs. /* deliberate syntax err */
#endif


/* Scaling decisions are generally the same as in the LL&M algorithm;
 * see jidctint.c for more details.  However, we choose to descale
 * (right shift) multiplication products as soon as they are formed,
 * rather than carrying additional fractional bits into subsequent additions.
 * This compromises accuracy slightly, but it lets us save a few shifts.
 * More importantly, 16-bit arithmetic is then adequate (for 8-bit samples)
 * everywhere except in the multiplications proper; this saves a good deal
 * of work on 16-bit-int machines.
 *
 * The dequantized coefficients are not integers because the AA&N scaling
 * factors have been incorporated.  We represent them scaled up by PASS1_BITS,
 * so that the first and second IDCT rounds have the same input scaling.
 * For 8-bit JSAMPLEs, we choose IFAST_SCALE_BITS = PASS1_BITS so as to
 * avoid a descaling shift; this compromises accuracy rather drastically
 * for small quantization table entries, but it saves a lot of shifts.
 * For 12-bit JSAMPLEs, there's no hope of using 16x16 multiplies anyway,
 * so we use a much larger scaling factor to preserve accuracy.
 *
 * A final compromise is to represent the multiplicative constants to only
 * 8 fractional bits, rather than 13.  This saves some shifting work on some
 * machines, and may also reduce the cost of multiplication (since there
 * are fewer one-bits in the constants).
 */

#if BITS_IN_JSAMPLE == 8
#define CONST_BITS  8
#define PASS1_BITS  2
#else
#define CONST_BITS  8
#define PASS1_BITS  1           /* lose a little precision to avoid overflow */
#endif

/* Some C compilers fail to reduce "FIX(constant)" at compile time, thus
 * causing a lot of useless floating-point operations at run time.
 * To get around this we use the following pre-calculated constants.
 * If you change CONST_BITS you may want to add appropriate values.
 * (With a reasonable C compiler, you can just rely on the FIX() macro...)
 */

#if CONST_BITS == 8
#define FIX_1_082392200  ((INT32)  277)         /* FIX(1.082392200) */
#define FIX_1_414213562  ((INT32)  362)         /* FIX(1.414213562) */
#define FIX_1_847759065  ((INT32)  473)         /* FIX(1.847759065) */
#define FIX_2_613125930  ((INT32)  669)         /* FIX(2.613125930) */
#else
#define FIX_1_082392200  FIX(1.082392200)
#define FIX_1_414213562  FIX(1.414213562)
#define FIX_1_847759065  FIX(1.847759065)
#define FIX_2_613125930  FIX(2.613125930)
#endif


/* We can gain a little more speed, with a further compromise in accuracy,
 * by omitting the addition in a descaling shift.  This yields an incorrectly
 * rounded result half the time...
 */

#ifndef USE_ACCURATE_ROUNDING
#undef DESCALE
#define DESCALE(x,n)  RIGHT_SHIFT(x, n)
#endif


/* Multiply a DCTELEM variable by an INT32 constant, and immediately
 * descale to yield a DCTELEM result.
 */

#define MULTIPLY(var,const)  ((DCTELEM) DESCALE((var) * (const), CONST_BITS))


/* Dequantize a coefficient by multiplying it by the multiplier-table
 * entry; produce a DCTELEM result.  For 8-bit data a 16x16->16
 * multiplication will do.  For 12-bit data, the multiplier table is
 * declared INT32, so a 32-bit multiply will be used.
 */

#if BITS_IN_JSAMPLE == 8
#define DEQUANTIZE(coef,quantval)  (((IFAST_MULT_TYPE) (coef)) * (quantval))
#else
#define DEQUANTIZE(coef,quantval)  \
        DESCALE((coef)*(quantval), IFAST_SCALE_BITS-PASS1_BITS)
#endif


/* Like DESCALE, but applies to a DCTELEM and produces an int.
 * We assume that int right shift is unsigned if INT32 right shift is.
 */

#ifdef RIGHT_SHIFT_IS_UNSIGNED
#define ISHIFT_TEMPS    DCTELEM ishift_temp;
#if BITS_IN_JSAMPLE == 8
#define DCTELEMBITS  16         /* DCTELEM may be 16 or 32 bits */
#else
#define DCTELEMBITS  32         /* DCTELEM must be 32 bits */
#endif
#define IRIGHT_SHIFT(x,shft)  \
    ((ishift_temp = (x)) < 0 ? \
     (ishift_temp >> (shft)) | ((~((DCTELEM) 0)) << (DCTELEMBITS-(shft))) : \
     (ishift_temp >> (shft)))
#else
#define ISHIFT_TEMPS
#define IRIGHT_SHIFT(x,shft)    ((x) >> (shft))
#endif

#ifdef USE_ACCURATE_ROUNDING
#define IDESCALE(x,n)  ((int) IRIGHT_SHIFT((x) + (1 << ((n)-1)), n))
#else
#define IDESCALE(x,n)  ((int) IRIGHT_SHIFT(x, n))
#endif


// this table of constants has been moved from mips_idct_le/_be.s to
// avoid having to make the assembler code position independent
static const int mips_idct_coefs[4] = {
  0x45464546,           // FIX( 1.082392200 / 2) =  17734 = 0x4546
  0x5A825A82,           // FIX( 1.414213562 / 2) =  23170 = 0x5A82
  0x76427642,           // FIX( 1.847759065 / 2) =  30274 = 0x7642
  0xAC61AC61            // FIX(-2.613125930 / 4) = -21407 = 0xAC61
};

void mips_idct_columns(JCOEF * inptr, IFAST_MULT_TYPE * quantptr,
                       DCTELEM * wsptr, const int * mips_idct_coefs);
void mips_idct_rows(DCTELEM * wsptr, JSAMPARRAY output_buf,
                    JDIMENSION output_col, const int * mips_idct_coefs);


/*
 * Perform dequantization and inverse DCT on one block of coefficients.
 */

GLOBAL(void)
jpeg_idct_mips (j_decompress_ptr cinfo, jpeg_component_info * compptr,
                 JCOEFPTR coef_block,
                 JSAMPARRAY output_buf, JDIMENSION output_col)
{
  JCOEFPTR inptr;
  IFAST_MULT_TYPE * quantptr;
  DCTELEM workspace[DCTSIZE2];  /* buffers data between passes */

  /* Pass 1: process columns from input, store into work array. */

  inptr = coef_block;
  quantptr = (IFAST_MULT_TYPE *) compptr->dct_table;

  mips_idct_columns(inptr, quantptr, workspace, mips_idct_coefs);

  /* Pass 2: process rows from work array, store into output array. */
  /* Note that we must descale the results by a factor of 8 == 2**3, */
  /* and also undo the PASS1_BITS scaling. */

  mips_idct_rows(workspace, output_buf, output_col, mips_idct_coefs);

}

#endif /* DCT_IFAST_SUPPORTED */