/* * reserved comment block * DO NOT REMOVE OR ALTER!
*/ /* * 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.
*/
/* * 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...)
*/
/* 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...
*/
/* 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.
*/
/* * Perform dequantization and inverse DCT on one block of coefficients.
*/
GLOBAL(void)
jpeg_idct_ifast (j_decompress_ptr cinfo, jpeg_component_info * compptr,
JCOEFPTR coef_block,
JSAMPARRAY output_buf, JDIMENSION output_col)
{
DCTELEM tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
DCTELEM tmp10, tmp11, tmp12, tmp13;
DCTELEM z5, z10, z11, z12, z13;
JCOEFPTR inptr;
IFAST_MULT_TYPE * quantptr; int * wsptr;
JSAMPROW outptr;
JSAMPLE *range_limit = IDCT_range_limit(cinfo); int ctr; int workspace[DCTSIZE2]; /* buffers data between passes */
SHIFT_TEMPS /* for DESCALE */
ISHIFT_TEMPS /* for IDESCALE */
/* Pass 1: process columns from input, store into work array. */
inptr = coef_block;
quantptr = (IFAST_MULT_TYPE *) compptr->dct_table;
wsptr = workspace; for (ctr = DCTSIZE; ctr > 0; ctr--) { /* Due to quantization, we will usually find that many of the input * coefficients are zero, especially the AC terms. We can exploit this * by short-circuiting the IDCT calculation for any column in which all * the AC terms are zero. In that case each output is equal to the * DC coefficient (with scale factor as needed). * With typical images and quantization tables, half or more of the * column DCT calculations can be simplified this way.
*/
if (inptr[DCTSIZE*1] == 0 && inptr[DCTSIZE*2] == 0 &&
inptr[DCTSIZE*3] == 0 && inptr[DCTSIZE*4] == 0 &&
inptr[DCTSIZE*5] == 0 && inptr[DCTSIZE*6] == 0 &&
inptr[DCTSIZE*7] == 0) { /* AC terms all zero */ int dcval = (int) DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);
inptr++; /* advance pointers to next column */
quantptr++;
wsptr++;
}
/* 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. */
wsptr = workspace; for (ctr = 0; ctr < DCTSIZE; ctr++) {
outptr = output_buf[ctr] + output_col; /* Rows of zeroes can be exploited in the same way as we did with columns. * However, the column calculation has created many nonzero AC terms, so * the simplification applies less often (typically 5% to 10% of the time). * On machines with very fast multiplication, it's possible that the * test takes more time than it's worth. In that case this section * may be commented out.
*/
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.
