mirror of
https://gitlab.winehq.org/wine/wine-gecko.git
synced 2024-09-13 09:24:08 -07:00
6bca192856
--HG-- rename : media/libjpeg/config.h => media/libjpeg/jconfigint.h rename : media/libjpeg/simd/jcclrmmx.asm => media/libjpeg/simd/jccolext-mmx.asm rename : media/libjpeg/simd/jcclrss2-64.asm => media/libjpeg/simd/jccolext-sse2-64.asm rename : media/libjpeg/simd/jcclrss2.asm => media/libjpeg/simd/jccolext-sse2.asm rename : media/libjpeg/simd/jccolmmx.asm => media/libjpeg/simd/jccolor-mmx.asm rename : media/libjpeg/simd/jccolss2-64.asm => media/libjpeg/simd/jccolor-sse2-64.asm rename : media/libjpeg/simd/jccolss2.asm => media/libjpeg/simd/jccolor-sse2.asm rename : media/libjpeg/simd/jcgrammx.asm => media/libjpeg/simd/jcgray-mmx.asm rename : media/libjpeg/simd/jcgrass2-64.asm => media/libjpeg/simd/jcgray-sse2-64.asm rename : media/libjpeg/simd/jcgrass2.asm => media/libjpeg/simd/jcgray-sse2.asm rename : media/libjpeg/simd/jcgrymmx.asm => media/libjpeg/simd/jcgryext-mmx.asm rename : media/libjpeg/simd/jcgryss2-64.asm => media/libjpeg/simd/jcgryext-sse2-64.asm rename : media/libjpeg/simd/jcgryss2.asm => media/libjpeg/simd/jcgryext-sse2.asm rename : media/libjpeg/simd/jcsammmx.asm => media/libjpeg/simd/jcsample-mmx.asm rename : media/libjpeg/simd/jcsamss2-64.asm => media/libjpeg/simd/jcsample-sse2-64.asm rename : media/libjpeg/simd/jcsamss2.asm => media/libjpeg/simd/jcsample-sse2.asm rename : media/libjpeg/simd/jdclrmmx.asm => media/libjpeg/simd/jdcolext-mmx.asm rename : media/libjpeg/simd/jdclrss2-64.asm => media/libjpeg/simd/jdcolext-sse2-64.asm rename : media/libjpeg/simd/jdclrss2.asm => media/libjpeg/simd/jdcolext-sse2.asm rename : media/libjpeg/simd/jdcolmmx.asm => media/libjpeg/simd/jdcolor-mmx.asm rename : media/libjpeg/simd/jdcolss2-64.asm => media/libjpeg/simd/jdcolor-sse2-64.asm rename : media/libjpeg/simd/jdcolss2.asm => media/libjpeg/simd/jdcolor-sse2.asm rename : media/libjpeg/simd/jdmermmx.asm => media/libjpeg/simd/jdmerge-mmx.asm rename : media/libjpeg/simd/jdmerss2-64.asm => media/libjpeg/simd/jdmerge-sse2-64.asm rename : media/libjpeg/simd/jdmerss2.asm => media/libjpeg/simd/jdmerge-sse2.asm rename : media/libjpeg/simd/jdmrgmmx.asm => media/libjpeg/simd/jdmrgext-mmx.asm rename : media/libjpeg/simd/jdmrgss2-64.asm => media/libjpeg/simd/jdmrgext-sse2-64.asm rename : media/libjpeg/simd/jdmrgss2.asm => media/libjpeg/simd/jdmrgext-sse2.asm rename : media/libjpeg/simd/jdsammmx.asm => media/libjpeg/simd/jdsample-mmx.asm rename : media/libjpeg/simd/jdsamss2-64.asm => media/libjpeg/simd/jdsample-sse2-64.asm rename : media/libjpeg/simd/jdsamss2.asm => media/libjpeg/simd/jdsample-sse2.asm rename : media/libjpeg/simd/jf3dnflt.asm => media/libjpeg/simd/jfdctflt-3dn.asm rename : media/libjpeg/simd/jfsseflt-64.asm => media/libjpeg/simd/jfdctflt-sse-64.asm rename : media/libjpeg/simd/jfsseflt.asm => media/libjpeg/simd/jfdctflt-sse.asm rename : media/libjpeg/simd/jfmmxfst.asm => media/libjpeg/simd/jfdctfst-mmx.asm rename : media/libjpeg/simd/jfss2fst-64.asm => media/libjpeg/simd/jfdctfst-sse2-64.asm rename : media/libjpeg/simd/jfss2fst.asm => media/libjpeg/simd/jfdctfst-sse2.asm rename : media/libjpeg/simd/jfmmxint.asm => media/libjpeg/simd/jfdctint-mmx.asm rename : media/libjpeg/simd/jfss2int-64.asm => media/libjpeg/simd/jfdctint-sse2-64.asm rename : media/libjpeg/simd/jfss2int.asm => media/libjpeg/simd/jfdctint-sse2.asm rename : media/libjpeg/simd/ji3dnflt.asm => media/libjpeg/simd/jidctflt-3dn.asm rename : media/libjpeg/simd/jisseflt.asm => media/libjpeg/simd/jidctflt-sse.asm rename : media/libjpeg/simd/jiss2flt-64.asm => media/libjpeg/simd/jidctflt-sse2-64.asm rename : media/libjpeg/simd/jiss2flt.asm => media/libjpeg/simd/jidctflt-sse2.asm rename : media/libjpeg/simd/jimmxfst.asm => media/libjpeg/simd/jidctfst-mmx.asm rename : media/libjpeg/simd/jiss2fst-64.asm => media/libjpeg/simd/jidctfst-sse2-64.asm rename : media/libjpeg/simd/jiss2fst.asm => media/libjpeg/simd/jidctfst-sse2.asm rename : media/libjpeg/simd/jimmxint.asm => media/libjpeg/simd/jidctint-mmx.asm rename : media/libjpeg/simd/jiss2int-64.asm => media/libjpeg/simd/jidctint-sse2-64.asm rename : media/libjpeg/simd/jiss2int.asm => media/libjpeg/simd/jidctint-sse2.asm rename : media/libjpeg/simd/jimmxred.asm => media/libjpeg/simd/jidctred-mmx.asm rename : media/libjpeg/simd/jiss2red-64.asm => media/libjpeg/simd/jidctred-sse2-64.asm rename : media/libjpeg/simd/jiss2red.asm => media/libjpeg/simd/jidctred-sse2.asm rename : media/libjpeg/simd/jcqnt3dn.asm => media/libjpeg/simd/jquant-3dn.asm rename : media/libjpeg/simd/jcqntmmx.asm => media/libjpeg/simd/jquant-mmx.asm rename : media/libjpeg/simd/jcqntsse.asm => media/libjpeg/simd/jquant-sse.asm rename : media/libjpeg/simd/jcqnts2f-64.asm => media/libjpeg/simd/jquantf-sse2-64.asm rename : media/libjpeg/simd/jcqnts2f.asm => media/libjpeg/simd/jquantf-sse2.asm rename : media/libjpeg/simd/jcqnts2i-64.asm => media/libjpeg/simd/jquanti-sse2-64.asm rename : media/libjpeg/simd/jcqnts2i.asm => media/libjpeg/simd/jquanti-sse2.asm
169 lines
5.4 KiB
C
169 lines
5.4 KiB
C
/*
|
|
* jfdctflt.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 a floating-point implementation of the
|
|
* forward DCT (Discrete Cosine Transform).
|
|
*
|
|
* This implementation should be more accurate than either of the integer
|
|
* DCT implementations. However, it may not give the same results on all
|
|
* machines because of differences in roundoff behavior. Speed will depend
|
|
* on the hardware's floating point capacity.
|
|
*
|
|
* 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). 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 a fixed-point
|
|
* implementation, accuracy is lost due to imprecise representation of the
|
|
* scaled quantization values. However, that problem does not arise if
|
|
* we use floating point arithmetic.
|
|
*/
|
|
|
|
#define JPEG_INTERNALS
|
|
#include "jinclude.h"
|
|
#include "jpeglib.h"
|
|
#include "jdct.h" /* Private declarations for DCT subsystem */
|
|
|
|
#ifdef DCT_FLOAT_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
|
|
|
|
|
|
/*
|
|
* Perform the forward DCT on one block of samples.
|
|
*/
|
|
|
|
GLOBAL(void)
|
|
jpeg_fdct_float (FAST_FLOAT * data)
|
|
{
|
|
FAST_FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
|
|
FAST_FLOAT tmp10, tmp11, tmp12, tmp13;
|
|
FAST_FLOAT z1, z2, z3, z4, z5, z11, z13;
|
|
FAST_FLOAT *dataptr;
|
|
int ctr;
|
|
|
|
/* Pass 1: process rows. */
|
|
|
|
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 */
|
|
|
|
tmp10 = tmp0 + tmp3; /* phase 2 */
|
|
tmp13 = tmp0 - tmp3;
|
|
tmp11 = tmp1 + tmp2;
|
|
tmp12 = tmp1 - tmp2;
|
|
|
|
dataptr[0] = tmp10 + tmp11; /* phase 3 */
|
|
dataptr[4] = tmp10 - tmp11;
|
|
|
|
z1 = (tmp12 + tmp13) * ((FAST_FLOAT) 0.707106781); /* c4 */
|
|
dataptr[2] = tmp13 + z1; /* phase 5 */
|
|
dataptr[6] = tmp13 - z1;
|
|
|
|
/* Odd part */
|
|
|
|
tmp10 = tmp4 + tmp5; /* phase 2 */
|
|
tmp11 = tmp5 + tmp6;
|
|
tmp12 = tmp6 + tmp7;
|
|
|
|
/* The rotator is modified from fig 4-8 to avoid extra negations. */
|
|
z5 = (tmp10 - tmp12) * ((FAST_FLOAT) 0.382683433); /* c6 */
|
|
z2 = ((FAST_FLOAT) 0.541196100) * tmp10 + z5; /* c2-c6 */
|
|
z4 = ((FAST_FLOAT) 1.306562965) * tmp12 + z5; /* c2+c6 */
|
|
z3 = tmp11 * ((FAST_FLOAT) 0.707106781); /* c4 */
|
|
|
|
z11 = tmp7 + z3; /* phase 5 */
|
|
z13 = tmp7 - z3;
|
|
|
|
dataptr[5] = z13 + z2; /* phase 6 */
|
|
dataptr[3] = z13 - z2;
|
|
dataptr[1] = z11 + z4;
|
|
dataptr[7] = z11 - z4;
|
|
|
|
dataptr += DCTSIZE; /* advance pointer to next row */
|
|
}
|
|
|
|
/* Pass 2: process columns. */
|
|
|
|
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 */
|
|
|
|
tmp10 = tmp0 + tmp3; /* phase 2 */
|
|
tmp13 = tmp0 - tmp3;
|
|
tmp11 = tmp1 + tmp2;
|
|
tmp12 = tmp1 - tmp2;
|
|
|
|
dataptr[DCTSIZE*0] = tmp10 + tmp11; /* phase 3 */
|
|
dataptr[DCTSIZE*4] = tmp10 - tmp11;
|
|
|
|
z1 = (tmp12 + tmp13) * ((FAST_FLOAT) 0.707106781); /* c4 */
|
|
dataptr[DCTSIZE*2] = tmp13 + z1; /* phase 5 */
|
|
dataptr[DCTSIZE*6] = tmp13 - z1;
|
|
|
|
/* Odd part */
|
|
|
|
tmp10 = tmp4 + tmp5; /* phase 2 */
|
|
tmp11 = tmp5 + tmp6;
|
|
tmp12 = tmp6 + tmp7;
|
|
|
|
/* The rotator is modified from fig 4-8 to avoid extra negations. */
|
|
z5 = (tmp10 - tmp12) * ((FAST_FLOAT) 0.382683433); /* c6 */
|
|
z2 = ((FAST_FLOAT) 0.541196100) * tmp10 + z5; /* c2-c6 */
|
|
z4 = ((FAST_FLOAT) 1.306562965) * tmp12 + z5; /* c2+c6 */
|
|
z3 = tmp11 * ((FAST_FLOAT) 0.707106781); /* c4 */
|
|
|
|
z11 = tmp7 + z3; /* phase 5 */
|
|
z13 = tmp7 - z3;
|
|
|
|
dataptr[DCTSIZE*5] = z13 + z2; /* phase 6 */
|
|
dataptr[DCTSIZE*3] = z13 - z2;
|
|
dataptr[DCTSIZE*1] = z11 + z4;
|
|
dataptr[DCTSIZE*7] = z11 - z4;
|
|
|
|
dataptr++; /* advance pointer to next column */
|
|
}
|
|
}
|
|
|
|
#endif /* DCT_FLOAT_SUPPORTED */
|