ryan/mozjpeg
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Improve floating point DCT

Browse Source 
From libjpeg-turbo r1288
Port the more accurate (and slightly faster) floating point IDCT
implementation from jpeg-8a and later.  New research revealed that the
SSE/SSE2 floating point IDCT implementation was actually more accurate
than the jpeg-6b implementation, not less, which is why its
mathematical results have always differed from those of the jpeg-6b
implementation.  This patch brings the accuracy of the C code in line
with that of the SSE/SSE2 code.
This commit is contained in:
Frank Bossen
2014-07-23 10:26:46 -04:00
parent ccb1d12f53
commit 3adc64a4cb
3 changed files with 56 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

79
jidctflt.c
View File

@@ -1,9 +1,12 @@
/*
* jidctflt.c
*
* This file was part of the Independent JPEG Group's software:
* 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.
* Modified 2010 by Guido Vollbeding.
* libjpeg-turbo Modifications:
* Copyright (C) 2014, D. R. Commander.
* For conditions of distribution and use, see the accompanying README file.
*
* This file contains a floating-point implementation of the
* inverse DCT (Discrete Cosine Transform). In the IJG code, this routine
@@ -76,10 +79,10 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
FLOAT_MULT_TYPE * quantptr;
FAST_FLOAT * wsptr;
JSAMPROW outptr;
JSAMPLE *range_limit = IDCT_range_limit(cinfo);
JSAMPLE *range_limit = cinfo->sample_range_limit;
int ctr;
FAST_FLOAT workspace[DCTSIZE2]; /* buffers data between passes */
SHIFT_TEMPS
#define _0_125 ((FLOAT_MULT_TYPE)0.125)
/* Pass 1: process columns from input, store into work array. */
@@ -101,7 +104,8 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
inptr[DCTSIZE*5] == 0 && inptr[DCTSIZE*6] == 0 &&
inptr[DCTSIZE*7] == 0) {
/* AC terms all zero */
FAST_FLOAT dcval = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);
FAST_FLOAT dcval = DEQUANTIZE(inptr[DCTSIZE*0],
quantptr[DCTSIZE*0] * _0_125);
wsptr[DCTSIZE*0] = dcval;
wsptr[DCTSIZE*1] = dcval;
@@ -120,10 +124,10 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
/* Even part */
tmp0 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);
tmp1 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]);
tmp2 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]);
tmp3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]);
tmp0 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0] * _0_125);
tmp1 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2] * _0_125);
tmp2 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4] * _0_125);
tmp3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6] * _0_125);
tmp10 = tmp0 + tmp2; /* phase 3 */
tmp11 = tmp0 - tmp2;
@@ -138,10 +142,10 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
/* Odd part */
tmp4 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]);
tmp5 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]);
tmp6 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]);
tmp7 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]);
tmp4 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1] * _0_125);
tmp5 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3] * _0_125);
tmp6 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5] * _0_125);
tmp7 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7] * _0_125);
z13 = tmp6 + tmp5; /* phase 6 */
z10 = tmp6 - tmp5;
@@ -152,12 +156,12 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
tmp11 = (z11 - z13) * ((FAST_FLOAT) 1.414213562); /* 2*c4 */
z5 = (z10 + z12) * ((FAST_FLOAT) 1.847759065); /* 2*c2 */
tmp10 = ((FAST_FLOAT) 1.082392200) * z12 - z5; /* 2*(c2-c6) */
tmp12 = ((FAST_FLOAT) -2.613125930) * z10 + z5; /* -2*(c2+c6) */
tmp10 = z5 - z12 * ((FAST_FLOAT) 1.082392200); /* 2*(c2-c6) */
tmp12 = z5 - z10 * ((FAST_FLOAT) 2.613125930); /* 2*(c2+c6) */
tmp6 = tmp12 - tmp7; /* phase 2 */
tmp5 = tmp11 - tmp6;
tmp4 = tmp10 + tmp5;
tmp4 = tmp10 - tmp5;
wsptr[DCTSIZE*0] = tmp0 + tmp7;
wsptr[DCTSIZE*7] = tmp0 - tmp7;
@@ -165,8 +169,8 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
wsptr[DCTSIZE*6] = tmp1 - tmp6;
wsptr[DCTSIZE*2] = tmp2 + tmp5;
wsptr[DCTSIZE*5] = tmp2 - tmp5;
wsptr[DCTSIZE*4] = tmp3 + tmp4;
wsptr[DCTSIZE*3] = tmp3 - tmp4;
wsptr[DCTSIZE*3] = tmp3 + tmp4;
wsptr[DCTSIZE*4] = tmp3 - tmp4;
inptr++; /* advance pointers to next column */
quantptr++;
@@ -174,7 +178,6 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
}
/* 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. */
wsptr = workspace;
for (ctr = 0; ctr < DCTSIZE; ctr++) {
@@ -187,8 +190,10 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
/* Even part */
tmp10 = wsptr[0] + wsptr[4];
tmp11 = wsptr[0] - wsptr[4];
/* Apply signed->unsigned and prepare float->int conversion */
z5 = wsptr[0] + ((FAST_FLOAT) CENTERJSAMPLE + (FAST_FLOAT) 0.5);
tmp10 = z5 + wsptr[4];
tmp11 = z5 - wsptr[4];
tmp13 = wsptr[2] + wsptr[6];
tmp12 = (wsptr[2] - wsptr[6]) * ((FAST_FLOAT) 1.414213562) - tmp13;
@@ -209,31 +214,23 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
tmp11 = (z11 - z13) * ((FAST_FLOAT) 1.414213562);
z5 = (z10 + z12) * ((FAST_FLOAT) 1.847759065); /* 2*c2 */
tmp10 = ((FAST_FLOAT) 1.082392200) * z12 - z5; /* 2*(c2-c6) */
tmp12 = ((FAST_FLOAT) -2.613125930) * z10 + z5; /* -2*(c2+c6) */
tmp10 = z5 - z12 * ((FAST_FLOAT) 1.082392200); /* 2*(c2-c6) */
tmp12 = z5 - z10 * ((FAST_FLOAT) 2.613125930); /* 2*(c2+c6) */
tmp6 = tmp12 - tmp7;
tmp5 = tmp11 - tmp6;
tmp4 = tmp10 + tmp5;
tmp4 = tmp10 - tmp5;
/* Final output stage: scale down by a factor of 8 and range-limit */
/* Final output stage: float->int conversion and range-limit */
outptr[0] = range_limit[(int) DESCALE((INT32) (tmp0 + tmp7), 3)
& RANGE_MASK];
outptr[7] = range_limit[(int) DESCALE((INT32) (tmp0 - tmp7), 3)
& RANGE_MASK];
outptr[1] = range_limit[(int) DESCALE((INT32) (tmp1 + tmp6), 3)
& RANGE_MASK];
outptr[6] = range_limit[(int) DESCALE((INT32) (tmp1 - tmp6), 3)
& RANGE_MASK];
outptr[2] = range_limit[(int) DESCALE((INT32) (tmp2 + tmp5), 3)
& RANGE_MASK];
outptr[5] = range_limit[(int) DESCALE((INT32) (tmp2 - tmp5), 3)
& RANGE_MASK];
outptr[4] = range_limit[(int) DESCALE((INT32) (tmp3 + tmp4), 3)
& RANGE_MASK];
outptr[3] = range_limit[(int) DESCALE((INT32) (tmp3 - tmp4), 3)
& RANGE_MASK];
outptr[0] = range_limit[((int) (tmp0 + tmp7)) & RANGE_MASK];
outptr[7] = range_limit[((int) (tmp0 - tmp7)) & RANGE_MASK];
outptr[1] = range_limit[((int) (tmp1 + tmp6)) & RANGE_MASK];
outptr[6] = range_limit[((int) (tmp1 - tmp6)) & RANGE_MASK];
outptr[2] = range_limit[((int) (tmp2 + tmp5)) & RANGE_MASK];
outptr[5] = range_limit[((int) (tmp2 - tmp5)) & RANGE_MASK];
outptr[3] = range_limit[((int) (tmp3 + tmp4)) & RANGE_MASK];
outptr[4] = range_limit[((int) (tmp3 - tmp4)) & RANGE_MASK];
wsptr += DCTSIZE; /* advance pointer to next row */
}