/* * jfdctfst.c * * This file was part of the Independent JPEG Group's software: * Copyright (C) 1994-1996, Thomas G. Lane. * libjpeg-turbo Modifications: * Copyright (C) 2015, D. R. Commander. * For conditions of distribution and use, see the accompanying README.ijg * file. * * This file contains a fast, not so accurate integer implementation of the * forward DCT (Discrete Cosine Transform). * * A 2-D DCT can be done by 1-D DCT on each row followed by 1-D DCT * on each column. 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.ijg). 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 jfdctint.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. * * Again to save a few shifts, the intermediate results between pass 1 and * pass 2 are not upscaled, but are represented only to integral precision. * * 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). */ #define CONST_BITS … /* 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_0_382683433 … #define FIX_0_541196100 … #define FIX_0_707106781 … #define FIX_1_306562965 … #else #define FIX_0_382683433 … #define FIX_0_541196100 … #define FIX_0_707106781 … #define FIX_1_306562965 … #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) … #endif /* Multiply a DCTELEM variable by an JLONG constant, and immediately * descale to yield a DCTELEM result. */ #define MULTIPLY(var, const) … /* * Perform the forward DCT on one block of samples. */ GLOBAL(void) jpeg_fdct_ifast(DCTELEM *data) { … } #endif /* DCT_IFAST_SUPPORTED */
Codebase Browser
chromium