mirror of
https://gitlab.winehq.org/wine/wine-gecko.git
synced 2024-09-13 09:24:08 -07:00
--HG-- rename : jpeg/MOZCHANGES => media/libjpeg/MOZCHANGES rename : jpeg/Makefile.in => media/libjpeg/Makefile.in rename : jpeg/README => media/libjpeg/README rename : jpeg/README-turbo.txt => media/libjpeg/README-turbo.txt rename : jpeg/cderror.h => media/libjpeg/cderror.h rename : jpeg/cdjpeg.h => media/libjpeg/cdjpeg.h rename : jpeg/jaricom.c => media/libjpeg/jaricom.c rename : jpeg/jcapimin.c => media/libjpeg/jcapimin.c rename : jpeg/jcapistd.c => media/libjpeg/jcapistd.c rename : jpeg/jcarith.c => media/libjpeg/jcarith.c rename : jpeg/jccoefct.c => media/libjpeg/jccoefct.c rename : jpeg/jccolor.c => media/libjpeg/jccolor.c rename : jpeg/jcdctmgr.c => media/libjpeg/jcdctmgr.c rename : jpeg/jchuff.c => media/libjpeg/jchuff.c rename : jpeg/jchuff.h => media/libjpeg/jchuff.h rename : jpeg/jcinit.c => media/libjpeg/jcinit.c rename : jpeg/jcmainct.c => media/libjpeg/jcmainct.c rename : jpeg/jcmarker.c => media/libjpeg/jcmarker.c rename : jpeg/jcmaster.c => media/libjpeg/jcmaster.c rename : jpeg/jcomapi.c => media/libjpeg/jcomapi.c rename : jpeg/jconfig.h => media/libjpeg/jconfig.h rename : jpeg/jconfig.h.in => media/libjpeg/jconfig.h.in rename : jpeg/jcparam.c => media/libjpeg/jcparam.c rename : jpeg/jcphuff.c => media/libjpeg/jcphuff.c rename : jpeg/jcprepct.c => media/libjpeg/jcprepct.c rename : jpeg/jcsample.c => media/libjpeg/jcsample.c rename : jpeg/jdapimin.c => media/libjpeg/jdapimin.c rename : jpeg/jdapistd.c => media/libjpeg/jdapistd.c rename : jpeg/jdarith.c => media/libjpeg/jdarith.c rename : jpeg/jdatadst.c => media/libjpeg/jdatadst.c rename : jpeg/jdatasrc.c => media/libjpeg/jdatasrc.c rename : jpeg/jdcoefct.c => media/libjpeg/jdcoefct.c rename : jpeg/jdcolor.c => media/libjpeg/jdcolor.c rename : jpeg/jdct.h => media/libjpeg/jdct.h rename : jpeg/jddctmgr.c => media/libjpeg/jddctmgr.c rename : jpeg/jdhuff.c => media/libjpeg/jdhuff.c rename : jpeg/jdhuff.h => media/libjpeg/jdhuff.h rename : jpeg/jdinput.c => media/libjpeg/jdinput.c rename : jpeg/jdmainct.c => media/libjpeg/jdmainct.c rename : jpeg/jdmarker.c => media/libjpeg/jdmarker.c rename : jpeg/jdmaster.c => media/libjpeg/jdmaster.c rename : jpeg/jdmerge.c => media/libjpeg/jdmerge.c rename : jpeg/jdphuff.c => media/libjpeg/jdphuff.c rename : jpeg/jdpostct.c => media/libjpeg/jdpostct.c rename : jpeg/jdsample.c => media/libjpeg/jdsample.c rename : jpeg/jdtrans.c => media/libjpeg/jdtrans.c rename : jpeg/jerror.c => media/libjpeg/jerror.c rename : jpeg/jerror.h => media/libjpeg/jerror.h rename : jpeg/jfdctflt.c => media/libjpeg/jfdctflt.c rename : jpeg/jfdctfst.c => media/libjpeg/jfdctfst.c rename : jpeg/jfdctint.c => media/libjpeg/jfdctint.c rename : jpeg/jidctflt.c => media/libjpeg/jidctflt.c rename : jpeg/jidctfst.c => media/libjpeg/jidctfst.c rename : jpeg/jidctint.c => media/libjpeg/jidctint.c rename : jpeg/jidctred.c => media/libjpeg/jidctred.c rename : jpeg/jinclude.h => media/libjpeg/jinclude.h rename : jpeg/jmemmgr.c => media/libjpeg/jmemmgr.c rename : jpeg/jmemnobs.c => media/libjpeg/jmemnobs.c rename : jpeg/jmemsys.h => media/libjpeg/jmemsys.h rename : jpeg/jmorecfg.h => media/libjpeg/jmorecfg.h rename : jpeg/jpegcomp.h => media/libjpeg/jpegcomp.h rename : jpeg/jpegint.h => media/libjpeg/jpegint.h rename : jpeg/jpeglib.h => media/libjpeg/jpeglib.h rename : jpeg/jquant1.c => media/libjpeg/jquant1.c rename : jpeg/jquant2.c => media/libjpeg/jquant2.c rename : jpeg/jsimd.h => media/libjpeg/jsimd.h rename : jpeg/jsimd_none.c => media/libjpeg/jsimd_none.c rename : jpeg/jsimddct.h => media/libjpeg/jsimddct.h rename : jpeg/jutils.c => media/libjpeg/jutils.c rename : jpeg/jversion.h => media/libjpeg/jversion.h rename : jpeg/simd/Makefile.in => media/libjpeg/simd/Makefile.in rename : jpeg/simd/jcclrmmx.asm => media/libjpeg/simd/jcclrmmx.asm rename : jpeg/simd/jcclrss2-64.asm => media/libjpeg/simd/jcclrss2-64.asm rename : jpeg/simd/jcclrss2.asm => media/libjpeg/simd/jcclrss2.asm rename : jpeg/simd/jccolmmx.asm => media/libjpeg/simd/jccolmmx.asm rename : jpeg/simd/jccolss2-64.asm => media/libjpeg/simd/jccolss2-64.asm rename : jpeg/simd/jccolss2.asm => media/libjpeg/simd/jccolss2.asm rename : jpeg/simd/jcolsamp.inc => media/libjpeg/simd/jcolsamp.inc rename : jpeg/simd/jcqnt3dn.asm => media/libjpeg/simd/jcqnt3dn.asm rename : jpeg/simd/jcqntmmx.asm => media/libjpeg/simd/jcqntmmx.asm rename : jpeg/simd/jcqnts2f-64.asm => media/libjpeg/simd/jcqnts2f-64.asm rename : jpeg/simd/jcqnts2f.asm => media/libjpeg/simd/jcqnts2f.asm rename : jpeg/simd/jcqnts2i-64.asm => media/libjpeg/simd/jcqnts2i-64.asm rename : jpeg/simd/jcqnts2i.asm => media/libjpeg/simd/jcqnts2i.asm rename : jpeg/simd/jcqntsse.asm => media/libjpeg/simd/jcqntsse.asm rename : jpeg/simd/jcsammmx.asm => media/libjpeg/simd/jcsammmx.asm rename : jpeg/simd/jcsamss2-64.asm => media/libjpeg/simd/jcsamss2-64.asm rename : jpeg/simd/jcsamss2.asm => media/libjpeg/simd/jcsamss2.asm rename : jpeg/simd/jdclrmmx.asm => media/libjpeg/simd/jdclrmmx.asm rename : jpeg/simd/jdclrss2-64.asm => media/libjpeg/simd/jdclrss2-64.asm rename : jpeg/simd/jdclrss2.asm => media/libjpeg/simd/jdclrss2.asm rename : jpeg/simd/jdcolmmx.asm => media/libjpeg/simd/jdcolmmx.asm rename : jpeg/simd/jdcolss2-64.asm => media/libjpeg/simd/jdcolss2-64.asm rename : jpeg/simd/jdcolss2.asm => media/libjpeg/simd/jdcolss2.asm rename : jpeg/simd/jdct.inc => media/libjpeg/simd/jdct.inc rename : jpeg/simd/jdmermmx.asm => media/libjpeg/simd/jdmermmx.asm rename : jpeg/simd/jdmerss2-64.asm => media/libjpeg/simd/jdmerss2-64.asm rename : jpeg/simd/jdmerss2.asm => media/libjpeg/simd/jdmerss2.asm rename : jpeg/simd/jdmrgmmx.asm => media/libjpeg/simd/jdmrgmmx.asm rename : jpeg/simd/jdmrgss2-64.asm => media/libjpeg/simd/jdmrgss2-64.asm rename : jpeg/simd/jdmrgss2.asm => media/libjpeg/simd/jdmrgss2.asm rename : jpeg/simd/jdsammmx.asm => media/libjpeg/simd/jdsammmx.asm rename : jpeg/simd/jdsamss2-64.asm => media/libjpeg/simd/jdsamss2-64.asm rename : jpeg/simd/jdsamss2.asm => media/libjpeg/simd/jdsamss2.asm rename : jpeg/simd/jf3dnflt.asm => media/libjpeg/simd/jf3dnflt.asm rename : jpeg/simd/jfmmxfst.asm => media/libjpeg/simd/jfmmxfst.asm rename : jpeg/simd/jfmmxint.asm => media/libjpeg/simd/jfmmxint.asm rename : jpeg/simd/jfss2fst-64.asm => media/libjpeg/simd/jfss2fst-64.asm rename : jpeg/simd/jfss2fst.asm => media/libjpeg/simd/jfss2fst.asm rename : jpeg/simd/jfss2int-64.asm => media/libjpeg/simd/jfss2int-64.asm rename : jpeg/simd/jfss2int.asm => media/libjpeg/simd/jfss2int.asm rename : jpeg/simd/jfsseflt-64.asm => media/libjpeg/simd/jfsseflt-64.asm rename : jpeg/simd/jfsseflt.asm => media/libjpeg/simd/jfsseflt.asm rename : jpeg/simd/ji3dnflt.asm => media/libjpeg/simd/ji3dnflt.asm rename : jpeg/simd/jimmxfst.asm => media/libjpeg/simd/jimmxfst.asm rename : jpeg/simd/jimmxint.asm => media/libjpeg/simd/jimmxint.asm rename : jpeg/simd/jimmxred.asm => media/libjpeg/simd/jimmxred.asm rename : jpeg/simd/jiss2flt-64.asm => media/libjpeg/simd/jiss2flt-64.asm rename : jpeg/simd/jiss2flt.asm => media/libjpeg/simd/jiss2flt.asm rename : jpeg/simd/jiss2fst-64.asm => media/libjpeg/simd/jiss2fst-64.asm rename : jpeg/simd/jiss2fst.asm => media/libjpeg/simd/jiss2fst.asm rename : jpeg/simd/jiss2int-64.asm => media/libjpeg/simd/jiss2int-64.asm rename : jpeg/simd/jiss2int.asm => media/libjpeg/simd/jiss2int.asm rename : jpeg/simd/jiss2red-64.asm => media/libjpeg/simd/jiss2red-64.asm rename : jpeg/simd/jiss2red.asm => media/libjpeg/simd/jiss2red.asm rename : jpeg/simd/jisseflt.asm => media/libjpeg/simd/jisseflt.asm rename : jpeg/simd/jsimd.h => media/libjpeg/simd/jsimd.h rename : jpeg/simd/jsimd_i386.c => media/libjpeg/simd/jsimd_i386.c rename : jpeg/simd/jsimd_x86_64.c => media/libjpeg/simd/jsimd_x86_64.c rename : jpeg/simd/jsimdcfg.inc => media/libjpeg/simd/jsimdcfg.inc rename : jpeg/simd/jsimdcfg.inc.h => media/libjpeg/simd/jsimdcfg.inc.h rename : jpeg/simd/jsimdcpu.asm => media/libjpeg/simd/jsimdcpu.asm rename : jpeg/simd/jsimdext.inc => media/libjpeg/simd/jsimdext.inc rename : jpeg/transupp.h => media/libjpeg/transupp.h
284 lines
11 KiB
C
284 lines
11 KiB
C
/*
|
|
* jfdctint.c
|
|
*
|
|
* Copyright (C) 1991-1996, 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 a slow-but-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 an algorithm described in
|
|
* C. Loeffler, A. Ligtenberg and G. Moschytz, "Practical Fast 1-D DCT
|
|
* Algorithms with 11 Multiplications", Proc. Int'l. Conf. on Acoustics,
|
|
* Speech, and Signal Processing 1989 (ICASSP '89), pp. 988-991.
|
|
* The primary algorithm described there uses 11 multiplies and 29 adds.
|
|
* We use their alternate method with 12 multiplies and 32 adds.
|
|
* The advantage of this method is that no data path contains more than one
|
|
* multiplication; this allows a very simple and accurate implementation in
|
|
* scaled fixed-point arithmetic, with a minimal number of shifts.
|
|
*/
|
|
|
|
#define JPEG_INTERNALS
|
|
#include "jinclude.h"
|
|
#include "jpeglib.h"
|
|
#include "jdct.h" /* Private declarations for DCT subsystem */
|
|
|
|
#ifdef DCT_ISLOW_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
|
|
|
|
|
|
/*
|
|
* The poop on this scaling stuff is as follows:
|
|
*
|
|
* Each 1-D DCT step produces outputs which are a factor of sqrt(N)
|
|
* larger than the true DCT outputs. The final outputs are therefore
|
|
* a factor of N larger than desired; since N=8 this can be cured by
|
|
* a simple right shift at the end of the algorithm. The advantage of
|
|
* this arrangement is that we save two multiplications per 1-D DCT,
|
|
* because the y0 and y4 outputs need not be divided by sqrt(N).
|
|
* In the IJG code, this factor of 8 is removed by the quantization step
|
|
* (in jcdctmgr.c), NOT in this module.
|
|
*
|
|
* We have to do addition and subtraction of the integer inputs, which
|
|
* is no problem, and multiplication by fractional constants, which is
|
|
* a problem to do in integer arithmetic. We multiply all the constants
|
|
* by CONST_SCALE and convert them to integer constants (thus retaining
|
|
* CONST_BITS bits of precision in the constants). After doing a
|
|
* multiplication we have to divide the product by CONST_SCALE, with proper
|
|
* rounding, to produce the correct output. This division can be done
|
|
* cheaply as a right shift of CONST_BITS bits. We postpone shifting
|
|
* as long as possible so that partial sums can be added together with
|
|
* full fractional precision.
|
|
*
|
|
* The outputs of the first pass are scaled up by PASS1_BITS bits so that
|
|
* they are represented to better-than-integral precision. These outputs
|
|
* require BITS_IN_JSAMPLE + PASS1_BITS + 3 bits; this fits in a 16-bit word
|
|
* with the recommended scaling. (For 12-bit sample data, the intermediate
|
|
* array is INT32 anyway.)
|
|
*
|
|
* To avoid overflow of the 32-bit intermediate results in pass 2, we must
|
|
* have BITS_IN_JSAMPLE + CONST_BITS + PASS1_BITS <= 26. Error analysis
|
|
* shows that the values given below are the most effective.
|
|
*/
|
|
|
|
#if BITS_IN_JSAMPLE == 8
|
|
#define CONST_BITS 13
|
|
#define PASS1_BITS 2
|
|
#else
|
|
#define CONST_BITS 13
|
|
#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 == 13
|
|
#define FIX_0_298631336 ((INT32) 2446) /* FIX(0.298631336) */
|
|
#define FIX_0_390180644 ((INT32) 3196) /* FIX(0.390180644) */
|
|
#define FIX_0_541196100 ((INT32) 4433) /* FIX(0.541196100) */
|
|
#define FIX_0_765366865 ((INT32) 6270) /* FIX(0.765366865) */
|
|
#define FIX_0_899976223 ((INT32) 7373) /* FIX(0.899976223) */
|
|
#define FIX_1_175875602 ((INT32) 9633) /* FIX(1.175875602) */
|
|
#define FIX_1_501321110 ((INT32) 12299) /* FIX(1.501321110) */
|
|
#define FIX_1_847759065 ((INT32) 15137) /* FIX(1.847759065) */
|
|
#define FIX_1_961570560 ((INT32) 16069) /* FIX(1.961570560) */
|
|
#define FIX_2_053119869 ((INT32) 16819) /* FIX(2.053119869) */
|
|
#define FIX_2_562915447 ((INT32) 20995) /* FIX(2.562915447) */
|
|
#define FIX_3_072711026 ((INT32) 25172) /* FIX(3.072711026) */
|
|
#else
|
|
#define FIX_0_298631336 FIX(0.298631336)
|
|
#define FIX_0_390180644 FIX(0.390180644)
|
|
#define FIX_0_541196100 FIX(0.541196100)
|
|
#define FIX_0_765366865 FIX(0.765366865)
|
|
#define FIX_0_899976223 FIX(0.899976223)
|
|
#define FIX_1_175875602 FIX(1.175875602)
|
|
#define FIX_1_501321110 FIX(1.501321110)
|
|
#define FIX_1_847759065 FIX(1.847759065)
|
|
#define FIX_1_961570560 FIX(1.961570560)
|
|
#define FIX_2_053119869 FIX(2.053119869)
|
|
#define FIX_2_562915447 FIX(2.562915447)
|
|
#define FIX_3_072711026 FIX(3.072711026)
|
|
#endif
|
|
|
|
|
|
/* Multiply an INT32 variable by an INT32 constant to yield an INT32 result.
|
|
* For 8-bit samples with the recommended scaling, all the variable
|
|
* and constant values involved are no more than 16 bits wide, so a
|
|
* 16x16->32 bit multiply can be used instead of a full 32x32 multiply.
|
|
* For 12-bit samples, a full 32-bit multiplication will be needed.
|
|
*/
|
|
|
|
#if BITS_IN_JSAMPLE == 8
|
|
#define MULTIPLY(var,const) MULTIPLY16C16(var,const)
|
|
#else
|
|
#define MULTIPLY(var,const) ((var) * (const))
|
|
#endif
|
|
|
|
|
|
/*
|
|
* Perform the forward DCT on one block of samples.
|
|
*/
|
|
|
|
GLOBAL(void)
|
|
jpeg_fdct_islow (DCTELEM * data)
|
|
{
|
|
INT32 tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
|
|
INT32 tmp10, tmp11, tmp12, tmp13;
|
|
INT32 z1, z2, z3, z4, z5;
|
|
DCTELEM *dataptr;
|
|
int ctr;
|
|
SHIFT_TEMPS
|
|
|
|
/* Pass 1: process rows. */
|
|
/* Note results are scaled up by sqrt(8) compared to a true DCT; */
|
|
/* furthermore, we scale the results by 2**PASS1_BITS. */
|
|
|
|
dataptr = data;
|
|
for (ctr = DCTSIZE-1; ctr >= 0; ctr--) {
|
|
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 per LL&M figure 1 --- note that published figure is faulty;
|
|
* rotator "sqrt(2)*c1" should be "sqrt(2)*c6".
|
|
*/
|
|
|
|
tmp10 = tmp0 + tmp3;
|
|
tmp13 = tmp0 - tmp3;
|
|
tmp11 = tmp1 + tmp2;
|
|
tmp12 = tmp1 - tmp2;
|
|
|
|
dataptr[0] = (DCTELEM) ((tmp10 + tmp11) << PASS1_BITS);
|
|
dataptr[4] = (DCTELEM) ((tmp10 - tmp11) << PASS1_BITS);
|
|
|
|
z1 = MULTIPLY(tmp12 + tmp13, FIX_0_541196100);
|
|
dataptr[2] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp13, FIX_0_765366865),
|
|
CONST_BITS-PASS1_BITS);
|
|
dataptr[6] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp12, - FIX_1_847759065),
|
|
CONST_BITS-PASS1_BITS);
|
|
|
|
/* Odd part per figure 8 --- note paper omits factor of sqrt(2).
|
|
* cK represents cos(K*pi/16).
|
|
* i0..i3 in the paper are tmp4..tmp7 here.
|
|
*/
|
|
|
|
z1 = tmp4 + tmp7;
|
|
z2 = tmp5 + tmp6;
|
|
z3 = tmp4 + tmp6;
|
|
z4 = tmp5 + tmp7;
|
|
z5 = MULTIPLY(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */
|
|
|
|
tmp4 = MULTIPLY(tmp4, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */
|
|
tmp5 = MULTIPLY(tmp5, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */
|
|
tmp6 = MULTIPLY(tmp6, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */
|
|
tmp7 = MULTIPLY(tmp7, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */
|
|
z1 = MULTIPLY(z1, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */
|
|
z2 = MULTIPLY(z2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */
|
|
z3 = MULTIPLY(z3, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */
|
|
z4 = MULTIPLY(z4, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */
|
|
|
|
z3 += z5;
|
|
z4 += z5;
|
|
|
|
dataptr[7] = (DCTELEM) DESCALE(tmp4 + z1 + z3, CONST_BITS-PASS1_BITS);
|
|
dataptr[5] = (DCTELEM) DESCALE(tmp5 + z2 + z4, CONST_BITS-PASS1_BITS);
|
|
dataptr[3] = (DCTELEM) DESCALE(tmp6 + z2 + z3, CONST_BITS-PASS1_BITS);
|
|
dataptr[1] = (DCTELEM) DESCALE(tmp7 + z1 + z4, CONST_BITS-PASS1_BITS);
|
|
|
|
dataptr += DCTSIZE; /* advance pointer to next row */
|
|
}
|
|
|
|
/* Pass 2: process columns.
|
|
* We remove the PASS1_BITS scaling, but leave the results scaled up
|
|
* by an overall factor of 8.
|
|
*/
|
|
|
|
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 per LL&M figure 1 --- note that published figure is faulty;
|
|
* rotator "sqrt(2)*c1" should be "sqrt(2)*c6".
|
|
*/
|
|
|
|
tmp10 = tmp0 + tmp3;
|
|
tmp13 = tmp0 - tmp3;
|
|
tmp11 = tmp1 + tmp2;
|
|
tmp12 = tmp1 - tmp2;
|
|
|
|
dataptr[DCTSIZE*0] = (DCTELEM) DESCALE(tmp10 + tmp11, PASS1_BITS);
|
|
dataptr[DCTSIZE*4] = (DCTELEM) DESCALE(tmp10 - tmp11, PASS1_BITS);
|
|
|
|
z1 = MULTIPLY(tmp12 + tmp13, FIX_0_541196100);
|
|
dataptr[DCTSIZE*2] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp13, FIX_0_765366865),
|
|
CONST_BITS+PASS1_BITS);
|
|
dataptr[DCTSIZE*6] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp12, - FIX_1_847759065),
|
|
CONST_BITS+PASS1_BITS);
|
|
|
|
/* Odd part per figure 8 --- note paper omits factor of sqrt(2).
|
|
* cK represents cos(K*pi/16).
|
|
* i0..i3 in the paper are tmp4..tmp7 here.
|
|
*/
|
|
|
|
z1 = tmp4 + tmp7;
|
|
z2 = tmp5 + tmp6;
|
|
z3 = tmp4 + tmp6;
|
|
z4 = tmp5 + tmp7;
|
|
z5 = MULTIPLY(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */
|
|
|
|
tmp4 = MULTIPLY(tmp4, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */
|
|
tmp5 = MULTIPLY(tmp5, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */
|
|
tmp6 = MULTIPLY(tmp6, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */
|
|
tmp7 = MULTIPLY(tmp7, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */
|
|
z1 = MULTIPLY(z1, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */
|
|
z2 = MULTIPLY(z2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */
|
|
z3 = MULTIPLY(z3, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */
|
|
z4 = MULTIPLY(z4, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */
|
|
|
|
z3 += z5;
|
|
z4 += z5;
|
|
|
|
dataptr[DCTSIZE*7] = (DCTELEM) DESCALE(tmp4 + z1 + z3,
|
|
CONST_BITS+PASS1_BITS);
|
|
dataptr[DCTSIZE*5] = (DCTELEM) DESCALE(tmp5 + z2 + z4,
|
|
CONST_BITS+PASS1_BITS);
|
|
dataptr[DCTSIZE*3] = (DCTELEM) DESCALE(tmp6 + z2 + z3,
|
|
CONST_BITS+PASS1_BITS);
|
|
dataptr[DCTSIZE*1] = (DCTELEM) DESCALE(tmp7 + z1 + z4,
|
|
CONST_BITS+PASS1_BITS);
|
|
|
|
dataptr++; /* advance pointer to next column */
|
|
}
|
|
}
|
|
|
|
#endif /* DCT_ISLOW_SUPPORTED */
|