diff options
author | 2017-01-25 17:49:53 +0100 | |
---|---|---|
committer | 2017-01-25 17:49:53 +0100 | |
commit | 78a7342750182687a08060c5e060cb897800e9f6 (patch) | |
tree | 73ab5b3a3b09c56a73a74950a71701adf7a22cc7 /3rdparty/libjpeg/jidctint.c | |
parent | 93c92be81517a982ef9b47eed610a3e42ed244bc (diff) |
updated libjpeg to 9c (nw)
Diffstat (limited to '3rdparty/libjpeg/jidctint.c')
-rw-r--r-- | 3rdparty/libjpeg/jidctint.c | 588 |
1 files changed, 345 insertions, 243 deletions
diff --git a/3rdparty/libjpeg/jidctint.c b/3rdparty/libjpeg/jidctint.c index dcdf7ce4547..de233ec996e 100644 --- a/3rdparty/libjpeg/jidctint.c +++ b/3rdparty/libjpeg/jidctint.c @@ -2,7 +2,7 @@ * jidctint.c * * Copyright (C) 1991-1998, Thomas G. Lane. - * Modification developed 2002-2009 by Guido Vollbeding. + * Modification developed 2002-2015 by Guido Vollbeding. * This file is part of the Independent JPEG Group's software. * For conditions of distribution and use, see the accompanying README file. * @@ -165,6 +165,8 @@ /* * Perform dequantization and inverse DCT on one block of coefficients. + * + * cK represents sqrt(2) * cos(K*pi/16). */ GLOBAL(void) @@ -184,9 +186,10 @@ jpeg_idct_islow (j_decompress_ptr cinfo, jpeg_component_info * compptr, int workspace[DCTSIZE2]; /* buffers data between passes */ SHIFT_TEMPS - /* Pass 1: process columns from input, store into work array. */ - /* Note results are scaled up by sqrt(8) compared to a true IDCT; */ - /* furthermore, we scale the results by 2**PASS1_BITS. */ + /* Pass 1: process columns from input, store into work array. + * Note results are scaled up by sqrt(8) compared to a true IDCT; + * furthermore, we scale the results by 2**PASS1_BITS. + */ inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; @@ -223,15 +226,9 @@ jpeg_idct_islow (j_decompress_ptr cinfo, jpeg_component_info * compptr, continue; } - /* Even part: reverse the even part of the forward DCT. */ - /* The rotator is sqrt(2)*c(-6). */ - - z2 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]); - z3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]); - - z1 = MULTIPLY(z2 + z3, FIX_0_541196100); - tmp2 = z1 + MULTIPLY(z2, FIX_0_765366865); - tmp3 = z1 - MULTIPLY(z3, FIX_1_847759065); + /* Even part: reverse the even part of the forward DCT. + * The rotator is c(-6). + */ z2 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]); z3 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]); @@ -243,6 +240,13 @@ jpeg_idct_islow (j_decompress_ptr cinfo, jpeg_component_info * compptr, tmp0 = z2 + z3; tmp1 = z2 - z3; + z2 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]); + z3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]); + + z1 = MULTIPLY(z2 + z3, FIX_0_541196100); /* c6 */ + tmp2 = z1 + MULTIPLY(z2, FIX_0_765366865); /* c2-c6 */ + tmp3 = z1 - MULTIPLY(z3, FIX_1_847759065); /* c2+c6 */ + tmp10 = tmp0 + tmp2; tmp13 = tmp0 - tmp2; tmp11 = tmp1 + tmp3; @@ -256,25 +260,25 @@ jpeg_idct_islow (j_decompress_ptr cinfo, jpeg_component_info * compptr, tmp1 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]); tmp2 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]); tmp3 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]); - + z2 = tmp0 + tmp2; z3 = tmp1 + tmp3; - z1 = MULTIPLY(z2 + z3, FIX_1_175875602); /* sqrt(2) * c3 */ - z2 = MULTIPLY(z2, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */ - z3 = MULTIPLY(z3, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */ + z1 = MULTIPLY(z2 + z3, FIX_1_175875602); /* c3 */ + z2 = MULTIPLY(z2, - FIX_1_961570560); /* -c3-c5 */ + z3 = MULTIPLY(z3, - FIX_0_390180644); /* -c3+c5 */ z2 += z1; z3 += z1; - z1 = MULTIPLY(tmp0 + tmp3, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */ - tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */ - tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */ + z1 = MULTIPLY(tmp0 + tmp3, - FIX_0_899976223); /* -c3+c7 */ + tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* -c1+c3+c5-c7 */ + tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* c1+c3-c5-c7 */ tmp0 += z1 + z2; tmp3 += z1 + z3; - z1 = MULTIPLY(tmp1 + tmp2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */ - tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */ - tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */ + z1 = MULTIPLY(tmp1 + tmp2, - FIX_2_562915447); /* -c1-c3 */ + tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* c1+c3-c5+c7 */ + tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* c1+c3+c5-c7 */ tmp1 += z1 + z3; tmp2 += z1 + z2; @@ -288,19 +292,26 @@ jpeg_idct_islow (j_decompress_ptr cinfo, jpeg_component_info * compptr, wsptr[DCTSIZE*5] = (int) RIGHT_SHIFT(tmp12 - tmp1, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*3] = (int) RIGHT_SHIFT(tmp13 + tmp0, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*4] = (int) RIGHT_SHIFT(tmp13 - tmp0, CONST_BITS-PASS1_BITS); - + 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. */ + /* 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; + + /* Add range center and fudge factor for final descale and range-limit. */ + z2 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); + /* 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). @@ -313,7 +324,7 @@ jpeg_idct_islow (j_decompress_ptr cinfo, jpeg_component_info * compptr, if (wsptr[1] == 0 && wsptr[2] == 0 && wsptr[3] == 0 && wsptr[4] == 0 && wsptr[5] == 0 && wsptr[6] == 0 && wsptr[7] == 0) { /* AC terms all zero */ - JSAMPLE dcval = range_limit[(int) DESCALE((INT32) wsptr[0], PASS1_BITS+3) + JSAMPLE dcval = range_limit[(int) RIGHT_SHIFT(z2, PASS1_BITS+3) & RANGE_MASK]; outptr[0] = dcval; @@ -330,23 +341,22 @@ jpeg_idct_islow (j_decompress_ptr cinfo, jpeg_component_info * compptr, } #endif - /* Even part: reverse the even part of the forward DCT. */ - /* The rotator is sqrt(2)*c(-6). */ - - z2 = (INT32) wsptr[2]; - z3 = (INT32) wsptr[6]; - - z1 = MULTIPLY(z2 + z3, FIX_0_541196100); - tmp2 = z1 + MULTIPLY(z2, FIX_0_765366865); - tmp3 = z1 - MULTIPLY(z3, FIX_1_847759065); + /* Even part: reverse the even part of the forward DCT. + * The rotator is c(-6). + */ - /* Add fudge factor here for final descale. */ - z2 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); z3 = (INT32) wsptr[4]; tmp0 = (z2 + z3) << CONST_BITS; tmp1 = (z2 - z3) << CONST_BITS; - + + z2 = (INT32) wsptr[2]; + z3 = (INT32) wsptr[6]; + + z1 = MULTIPLY(z2 + z3, FIX_0_541196100); /* c6 */ + tmp2 = z1 + MULTIPLY(z2, FIX_0_765366865); /* c2-c6 */ + tmp3 = z1 - MULTIPLY(z3, FIX_1_847759065); /* c2+c6 */ + tmp10 = tmp0 + tmp2; tmp13 = tmp0 - tmp2; tmp11 = tmp1 + tmp3; @@ -364,21 +374,21 @@ jpeg_idct_islow (j_decompress_ptr cinfo, jpeg_component_info * compptr, z2 = tmp0 + tmp2; z3 = tmp1 + tmp3; - z1 = MULTIPLY(z2 + z3, FIX_1_175875602); /* sqrt(2) * c3 */ - z2 = MULTIPLY(z2, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */ - z3 = MULTIPLY(z3, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */ + z1 = MULTIPLY(z2 + z3, FIX_1_175875602); /* c3 */ + z2 = MULTIPLY(z2, - FIX_1_961570560); /* -c3-c5 */ + z3 = MULTIPLY(z3, - FIX_0_390180644); /* -c3+c5 */ z2 += z1; z3 += z1; - z1 = MULTIPLY(tmp0 + tmp3, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */ - tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */ - tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */ + z1 = MULTIPLY(tmp0 + tmp3, - FIX_0_899976223); /* -c3+c7 */ + tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* -c1+c3+c5-c7 */ + tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* c1+c3-c5-c7 */ tmp0 += z1 + z2; tmp3 += z1 + z3; - z1 = MULTIPLY(tmp1 + tmp2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */ - tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */ - tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */ + z1 = MULTIPLY(tmp1 + tmp2, - FIX_2_562915447); /* -c1-c3 */ + tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* c1+c3-c5+c7 */ + tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* c1+c3+c5-c7 */ tmp1 += z1 + z3; tmp2 += z1 + z2; @@ -502,8 +512,10 @@ jpeg_idct_7x7 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - tmp13 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp13 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp13 <<= CONST_BITS; z1 = (INT32) wsptr[2]; @@ -638,8 +650,10 @@ jpeg_idct_6x6 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - tmp0 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp0 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp0 <<= CONST_BITS; tmp2 = (INT32) wsptr[4]; tmp10 = MULTIPLY(tmp2, FIX(0.707106781)); /* c4 */ @@ -757,8 +771,10 @@ jpeg_idct_5x5 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - tmp12 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp12 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp12 <<= CONST_BITS; tmp0 = (INT32) wsptr[2]; tmp1 = (INT32) wsptr[4]; @@ -869,8 +885,10 @@ jpeg_idct_4x4 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - tmp0 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp0 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp2 = (INT32) wsptr[2]; tmp10 = (tmp0 + tmp2) << CONST_BITS; @@ -966,8 +984,10 @@ jpeg_idct_3x3 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - tmp0 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp0 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp0 <<= CONST_BITS; tmp2 = (INT32) wsptr[2]; tmp12 = MULTIPLY(tmp2, FIX(0.707106781)); /* c2 */ @@ -1008,11 +1028,11 @@ jpeg_idct_2x2 (j_decompress_ptr cinfo, jpeg_component_info * compptr, JCOEFPTR coef_block, JSAMPARRAY output_buf, JDIMENSION output_col) { - INT32 tmp0, tmp1, tmp2, tmp3, tmp4, tmp5; + DCTELEM tmp0, tmp1, tmp2, tmp3, tmp4, tmp5; ISLOW_MULT_TYPE * quantptr; JSAMPROW outptr; JSAMPLE *range_limit = IDCT_range_limit(cinfo); - SHIFT_TEMPS + ISHIFT_TEMPS /* Pass 1: process columns from input. */ @@ -1021,8 +1041,8 @@ jpeg_idct_2x2 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Column 0 */ tmp4 = DEQUANTIZE(coef_block[DCTSIZE*0], quantptr[DCTSIZE*0]); tmp5 = DEQUANTIZE(coef_block[DCTSIZE*1], quantptr[DCTSIZE*1]); - /* Add fudge factor here for final descale. */ - tmp4 += ONE << 2; + /* Add range center and fudge factor for final descale and range-limit. */ + tmp4 += (((DCTELEM) RANGE_CENTER) << 3) + (1 << 2); tmp0 = tmp4 + tmp5; tmp2 = tmp4 - tmp5; @@ -1039,14 +1059,14 @@ jpeg_idct_2x2 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Row 0 */ outptr = output_buf[0] + output_col; - outptr[0] = range_limit[(int) RIGHT_SHIFT(tmp0 + tmp1, 3) & RANGE_MASK]; - outptr[1] = range_limit[(int) RIGHT_SHIFT(tmp0 - tmp1, 3) & RANGE_MASK]; + outptr[0] = range_limit[(int) IRIGHT_SHIFT(tmp0 + tmp1, 3) & RANGE_MASK]; + outptr[1] = range_limit[(int) IRIGHT_SHIFT(tmp0 - tmp1, 3) & RANGE_MASK]; /* Row 1 */ outptr = output_buf[1] + output_col; - outptr[0] = range_limit[(int) RIGHT_SHIFT(tmp2 + tmp3, 3) & RANGE_MASK]; - outptr[1] = range_limit[(int) RIGHT_SHIFT(tmp2 - tmp3, 3) & RANGE_MASK]; + outptr[0] = range_limit[(int) IRIGHT_SHIFT(tmp2 + tmp3, 3) & RANGE_MASK]; + outptr[1] = range_limit[(int) IRIGHT_SHIFT(tmp2 - tmp3, 3) & RANGE_MASK]; } @@ -1063,17 +1083,21 @@ jpeg_idct_1x1 (j_decompress_ptr cinfo, jpeg_component_info * compptr, JCOEFPTR coef_block, JSAMPARRAY output_buf, JDIMENSION output_col) { - int dcval; + DCTELEM dcval; ISLOW_MULT_TYPE * quantptr; JSAMPLE *range_limit = IDCT_range_limit(cinfo); - SHIFT_TEMPS + ISHIFT_TEMPS /* 1x1 is trivial: just take the DC coefficient divided by 8. */ + quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; + dcval = DEQUANTIZE(coef_block[0], quantptr[0]); - dcval = (int) DESCALE((INT32) dcval, 3); + /* Add range center and fudge factor for descale and range-limit. */ + dcval += (((DCTELEM) RANGE_CENTER) << 3) + (1 << 2); - output_buf[0][output_col] = range_limit[dcval & RANGE_MASK]; + output_buf[0][output_col] = + range_limit[(int) IRIGHT_SHIFT(dcval, 3) & RANGE_MASK]; } @@ -1172,8 +1196,10 @@ jpeg_idct_9x9 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - tmp0 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp0 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp0 <<= CONST_BITS; z1 = (INT32) wsptr[2]; @@ -1355,8 +1381,10 @@ jpeg_idct_10x10 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - z3 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + z3 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); z3 <<= CONST_BITS; z4 = (INT32) wsptr[4]; z1 = MULTIPLY(z4, FIX(1.144122806)); /* c4 */ @@ -1548,8 +1576,10 @@ jpeg_idct_11x11 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - tmp10 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp10 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp10 <<= CONST_BITS; z1 = (INT32) wsptr[2]; @@ -1752,8 +1782,10 @@ jpeg_idct_12x12 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - z3 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + z3 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); z3 <<= CONST_BITS; z4 = (INT32) wsptr[4]; @@ -1973,8 +2005,10 @@ jpeg_idct_13x13 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - z1 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + z1 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); z1 <<= CONST_BITS; z2 = (INT32) wsptr[2]; @@ -2200,8 +2234,10 @@ jpeg_idct_14x14 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - z1 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + z1 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); z1 <<= CONST_BITS; z4 = (INT32) wsptr[4]; z2 = MULTIPLY(z4, FIX(1.274162392)); /* c4 */ @@ -2432,8 +2468,10 @@ jpeg_idct_15x15 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - z1 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + z1 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); z1 <<= CONST_BITS; z2 = (INT32) wsptr[2]; @@ -2683,8 +2721,10 @@ jpeg_idct_16x16 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - tmp0 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp0 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp0 <<= CONST_BITS; z1 = (INT32) wsptr[4]; @@ -2835,9 +2875,11 @@ jpeg_idct_16x8 (j_decompress_ptr cinfo, jpeg_component_info * compptr, int workspace[8*8]; /* buffers data between passes */ SHIFT_TEMPS - /* Pass 1: process columns from input, store into work array. */ - /* Note results are scaled up by sqrt(8) compared to a true IDCT; */ - /* furthermore, we scale the results by 2**PASS1_BITS. */ + /* Pass 1: process columns from input, store into work array. + * Note results are scaled up by sqrt(8) compared to a true IDCT; + * furthermore, we scale the results by 2**PASS1_BITS. + * 8-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/16). + */ inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; @@ -2851,14 +2893,14 @@ jpeg_idct_16x8 (j_decompress_ptr cinfo, jpeg_component_info * compptr, * 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 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]) << PASS1_BITS; - + wsptr[DCTSIZE*0] = dcval; wsptr[DCTSIZE*1] = dcval; wsptr[DCTSIZE*2] = dcval; @@ -2867,23 +2909,24 @@ jpeg_idct_16x8 (j_decompress_ptr cinfo, jpeg_component_info * compptr, wsptr[DCTSIZE*5] = dcval; wsptr[DCTSIZE*6] = dcval; wsptr[DCTSIZE*7] = dcval; - + inptr++; /* advance pointers to next column */ quantptr++; wsptr++; continue; } - - /* Even part: reverse the even part of the forward DCT. */ - /* The rotator is sqrt(2)*c(-6). */ - + + /* Even part: reverse the even part of the forward DCT. + * The rotator is c(-6). + */ + z2 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]); z3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]); - - z1 = MULTIPLY(z2 + z3, FIX_0_541196100); - tmp2 = z1 + MULTIPLY(z2, FIX_0_765366865); - tmp3 = z1 - MULTIPLY(z3, FIX_1_847759065); - + + z1 = MULTIPLY(z2 + z3, FIX_0_541196100); /* c6 */ + tmp2 = z1 + MULTIPLY(z2, FIX_0_765366865); /* c2-c6 */ + tmp3 = z1 - MULTIPLY(z3, FIX_1_847759065); /* c2+c6 */ + z2 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]); z3 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]); z2 <<= CONST_BITS; @@ -2893,44 +2936,44 @@ jpeg_idct_16x8 (j_decompress_ptr cinfo, jpeg_component_info * compptr, tmp0 = z2 + z3; tmp1 = z2 - z3; - + tmp10 = tmp0 + tmp2; tmp13 = tmp0 - tmp2; tmp11 = tmp1 + tmp3; tmp12 = tmp1 - tmp3; - + /* Odd part per figure 8; the matrix is unitary and hence its * transpose is its inverse. i0..i3 are y7,y5,y3,y1 respectively. */ - + tmp0 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]); tmp1 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]); tmp2 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]); tmp3 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]); - + z2 = tmp0 + tmp2; z3 = tmp1 + tmp3; - z1 = MULTIPLY(z2 + z3, FIX_1_175875602); /* sqrt(2) * c3 */ - z2 = MULTIPLY(z2, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */ - z3 = MULTIPLY(z3, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */ + z1 = MULTIPLY(z2 + z3, FIX_1_175875602); /* c3 */ + z2 = MULTIPLY(z2, - FIX_1_961570560); /* -c3-c5 */ + z3 = MULTIPLY(z3, - FIX_0_390180644); /* -c3+c5 */ z2 += z1; z3 += z1; - z1 = MULTIPLY(tmp0 + tmp3, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */ - tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */ - tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */ + z1 = MULTIPLY(tmp0 + tmp3, - FIX_0_899976223); /* -c3+c7 */ + tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* -c1+c3+c5-c7 */ + tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* c1+c3-c5-c7 */ tmp0 += z1 + z2; tmp3 += z1 + z3; - z1 = MULTIPLY(tmp1 + tmp2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */ - tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */ - tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */ + z1 = MULTIPLY(tmp1 + tmp2, - FIX_2_562915447); /* -c1-c3 */ + tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* c1+c3-c5+c7 */ + tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* c1+c3+c5-c7 */ tmp1 += z1 + z3; tmp2 += z1 + z2; - + /* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */ - + wsptr[DCTSIZE*0] = (int) RIGHT_SHIFT(tmp10 + tmp3, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*7] = (int) RIGHT_SHIFT(tmp10 - tmp3, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*1] = (int) RIGHT_SHIFT(tmp11 + tmp2, CONST_BITS-PASS1_BITS); @@ -2939,7 +2982,7 @@ jpeg_idct_16x8 (j_decompress_ptr cinfo, jpeg_component_info * compptr, wsptr[DCTSIZE*5] = (int) RIGHT_SHIFT(tmp12 - tmp1, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*3] = (int) RIGHT_SHIFT(tmp13 + tmp0, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*4] = (int) RIGHT_SHIFT(tmp13 - tmp0, CONST_BITS-PASS1_BITS); - + inptr++; /* advance pointers to next column */ quantptr++; wsptr++; @@ -2948,14 +2991,17 @@ jpeg_idct_16x8 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 2: process 8 rows from work array, store into output array. * 16-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/32). */ + wsptr = workspace; for (ctr = 0; ctr < 8; ctr++) { outptr = output_buf[ctr] + output_col; /* Even part */ - /* Add fudge factor here for final descale. */ - tmp0 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp0 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp0 <<= CONST_BITS; z1 = (INT32) wsptr[4]; @@ -3109,6 +3155,7 @@ jpeg_idct_14x7 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 1: process columns from input, store into work array. * 7-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/14). */ + inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; @@ -3164,14 +3211,17 @@ jpeg_idct_14x7 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 2: process 7 rows from work array, store into output array. * 14-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/28). */ + wsptr = workspace; for (ctr = 0; ctr < 7; ctr++) { outptr = output_buf[ctr] + output_col; /* Even part */ - /* Add fudge factor here for final descale. */ - z1 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + z1 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); z1 <<= CONST_BITS; z4 = (INT32) wsptr[4]; z2 = MULTIPLY(z4, FIX(1.274162392)); /* c4 */ @@ -3304,6 +3354,7 @@ jpeg_idct_12x6 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 1: process columns from input, store into work array. * 6-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/12). */ + inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; @@ -3346,14 +3397,17 @@ jpeg_idct_12x6 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 2: process 6 rows from work array, store into output array. * 12-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/24). */ + wsptr = workspace; for (ctr = 0; ctr < 6; ctr++) { outptr = output_buf[ctr] + output_col; /* Even part */ - /* Add fudge factor here for final descale. */ - z3 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + z3 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); z3 <<= CONST_BITS; z4 = (INT32) wsptr[4]; @@ -3480,6 +3534,7 @@ jpeg_idct_10x5 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 1: process columns from input, store into work array. * 5-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/10). */ + inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; @@ -3520,14 +3575,17 @@ jpeg_idct_10x5 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 2: process 5 rows from work array, store into output array. * 10-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/20). */ + wsptr = workspace; for (ctr = 0; ctr < 5; ctr++) { outptr = output_buf[ctr] + output_col; /* Even part */ - /* Add fudge factor here for final descale. */ - z3 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + z3 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); z3 <<= CONST_BITS; z4 = (INT32) wsptr[4]; z1 = MULTIPLY(z4, FIX(1.144122806)); /* c4 */ @@ -3639,8 +3697,10 @@ jpeg_idct_8x4 (j_decompress_ptr cinfo, jpeg_component_info * compptr, SHIFT_TEMPS /* Pass 1: process columns from input, store into work array. - * 4-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/16). + * 4-point IDCT kernel, + * cK represents sqrt(2) * cos(K*pi/16) [refers to 8-point IDCT]. */ + inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; @@ -3675,31 +3735,36 @@ jpeg_idct_8x4 (j_decompress_ptr cinfo, jpeg_component_info * compptr, wsptr[8*2] = (int) (tmp12 - tmp2); } - /* 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. */ + /* 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. + * 8-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/16). + */ wsptr = workspace; for (ctr = 0; ctr < 4; ctr++) { outptr = output_buf[ctr] + output_col; - /* Even part: reverse the even part of the forward DCT. */ - /* The rotator is sqrt(2)*c(-6). */ + /* Even part: reverse the even part of the forward DCT. + * The rotator is c(-6). + */ - z2 = (INT32) wsptr[2]; - z3 = (INT32) wsptr[6]; - - z1 = MULTIPLY(z2 + z3, FIX_0_541196100); - tmp2 = z1 + MULTIPLY(z2, FIX_0_765366865); - tmp3 = z1 - MULTIPLY(z3, FIX_1_847759065); - - /* Add fudge factor here for final descale. */ - z2 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + z2 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); z3 = (INT32) wsptr[4]; - + tmp0 = (z2 + z3) << CONST_BITS; tmp1 = (z2 - z3) << CONST_BITS; - + + z2 = (INT32) wsptr[2]; + z3 = (INT32) wsptr[6]; + + z1 = MULTIPLY(z2 + z3, FIX_0_541196100); /* c6 */ + tmp2 = z1 + MULTIPLY(z2, FIX_0_765366865); /* c2-c6 */ + tmp3 = z1 - MULTIPLY(z3, FIX_1_847759065); /* c2+c6 */ + tmp10 = tmp0 + tmp2; tmp13 = tmp0 - tmp2; tmp11 = tmp1 + tmp3; @@ -3717,21 +3782,21 @@ jpeg_idct_8x4 (j_decompress_ptr cinfo, jpeg_component_info * compptr, z2 = tmp0 + tmp2; z3 = tmp1 + tmp3; - z1 = MULTIPLY(z2 + z3, FIX_1_175875602); /* sqrt(2) * c3 */ - z2 = MULTIPLY(z2, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */ - z3 = MULTIPLY(z3, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */ + z1 = MULTIPLY(z2 + z3, FIX_1_175875602); /* c3 */ + z2 = MULTIPLY(z2, - FIX_1_961570560); /* -c3-c5 */ + z3 = MULTIPLY(z3, - FIX_0_390180644); /* -c3+c5 */ z2 += z1; z3 += z1; - z1 = MULTIPLY(tmp0 + tmp3, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */ - tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */ - tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */ + z1 = MULTIPLY(tmp0 + tmp3, - FIX_0_899976223); /* -c3+c7 */ + tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* -c1+c3+c5-c7 */ + tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* c1+c3-c5-c7 */ tmp0 += z1 + z2; tmp3 += z1 + z3; - z1 = MULTIPLY(tmp1 + tmp2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */ - tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */ - tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */ + z1 = MULTIPLY(tmp1 + tmp2, - FIX_2_562915447); /* -c1-c3 */ + tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* c1+c3-c5+c7 */ + tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* c1+c3+c5-c7 */ tmp1 += z1 + z3; tmp2 += z1 + z2; @@ -3793,6 +3858,7 @@ jpeg_idct_6x3 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 1: process columns from input, store into work array. * 3-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/6). */ + inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; @@ -3823,14 +3889,17 @@ jpeg_idct_6x3 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 2: process 3 rows from work array, store into output array. * 6-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/12). */ + wsptr = workspace; for (ctr = 0; ctr < 3; ctr++) { outptr = output_buf[ctr] + output_col; /* Even part */ - /* Add fudge factor here for final descale. */ - tmp0 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp0 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp0 <<= CONST_BITS; tmp2 = (INT32) wsptr[4]; tmp10 = MULTIPLY(tmp2, FIX(0.707106781)); /* c4 */ @@ -3924,14 +3993,15 @@ jpeg_idct_4x2 (j_decompress_ptr cinfo, jpeg_component_info * compptr, * 4-point IDCT kernel, * cK represents sqrt(2) * cos(K*pi/16) [refers to 8-point IDCT]. */ + wsptr = workspace; for (ctr = 0; ctr < 2; ctr++) { outptr = output_buf[ctr] + output_col; /* Even part */ - /* Add fudge factor here for final descale. */ - tmp0 = wsptr[0] + (ONE << 2); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp0 = wsptr[0] + ((((INT32) RANGE_CENTER) << 3) + (ONE << 2)); tmp2 = wsptr[2]; tmp10 = (tmp0 + tmp2) << CONST_BITS; @@ -3979,11 +4049,11 @@ jpeg_idct_2x1 (j_decompress_ptr cinfo, jpeg_component_info * compptr, JCOEFPTR coef_block, JSAMPARRAY output_buf, JDIMENSION output_col) { - INT32 tmp0, tmp10; + DCTELEM tmp0, tmp1; ISLOW_MULT_TYPE * quantptr; JSAMPROW outptr; JSAMPLE *range_limit = IDCT_range_limit(cinfo); - SHIFT_TEMPS + ISHIFT_TEMPS /* Pass 1: empty. */ @@ -3994,18 +4064,18 @@ jpeg_idct_2x1 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - tmp10 = DEQUANTIZE(coef_block[0], quantptr[0]); - /* Add fudge factor here for final descale. */ - tmp10 += ONE << 2; + tmp0 = DEQUANTIZE(coef_block[0], quantptr[0]); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp0 += (((DCTELEM) RANGE_CENTER) << 3) + (1 << 2); /* Odd part */ - tmp0 = DEQUANTIZE(coef_block[1], quantptr[1]); + tmp1 = DEQUANTIZE(coef_block[1], quantptr[1]); /* Final output stage */ - outptr[0] = range_limit[(int) RIGHT_SHIFT(tmp10 + tmp0, 3) & RANGE_MASK]; - outptr[1] = range_limit[(int) RIGHT_SHIFT(tmp10 - tmp0, 3) & RANGE_MASK]; + outptr[0] = range_limit[(int) IRIGHT_SHIFT(tmp0 + tmp1, 3) & RANGE_MASK]; + outptr[1] = range_limit[(int) IRIGHT_SHIFT(tmp0 - tmp1, 3) & RANGE_MASK]; } @@ -4036,6 +4106,7 @@ jpeg_idct_8x16 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 1: process columns from input, store into work array. * 16-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/32). */ + inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; @@ -4134,69 +4205,74 @@ jpeg_idct_8x16 (j_decompress_ptr cinfo, jpeg_component_info * compptr, wsptr[8*7] = (int) RIGHT_SHIFT(tmp27 + tmp13, CONST_BITS-PASS1_BITS); wsptr[8*8] = (int) RIGHT_SHIFT(tmp27 - tmp13, CONST_BITS-PASS1_BITS); } - - /* 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. */ + + /* 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. + * 8-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/16). + */ wsptr = workspace; for (ctr = 0; ctr < 16; ctr++) { outptr = output_buf[ctr] + output_col; - - /* Even part: reverse the even part of the forward DCT. */ - /* The rotator is sqrt(2)*c(-6). */ - - z2 = (INT32) wsptr[2]; - z3 = (INT32) wsptr[6]; - - z1 = MULTIPLY(z2 + z3, FIX_0_541196100); - tmp2 = z1 + MULTIPLY(z2, FIX_0_765366865); - tmp3 = z1 - MULTIPLY(z3, FIX_1_847759065); - - /* Add fudge factor here for final descale. */ - z2 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + + /* Even part: reverse the even part of the forward DCT. + * The rotator is c(-6). + */ + + /* Add range center and fudge factor for final descale and range-limit. */ + z2 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); z3 = (INT32) wsptr[4]; - + tmp0 = (z2 + z3) << CONST_BITS; tmp1 = (z2 - z3) << CONST_BITS; - + + z2 = (INT32) wsptr[2]; + z3 = (INT32) wsptr[6]; + + z1 = MULTIPLY(z2 + z3, FIX_0_541196100); /* c6 */ + tmp2 = z1 + MULTIPLY(z2, FIX_0_765366865); /* c2-c6 */ + tmp3 = z1 - MULTIPLY(z3, FIX_1_847759065); /* c2+c6 */ + tmp10 = tmp0 + tmp2; tmp13 = tmp0 - tmp2; tmp11 = tmp1 + tmp3; tmp12 = tmp1 - tmp3; - + /* Odd part per figure 8; the matrix is unitary and hence its * transpose is its inverse. i0..i3 are y7,y5,y3,y1 respectively. */ - + tmp0 = (INT32) wsptr[7]; tmp1 = (INT32) wsptr[5]; tmp2 = (INT32) wsptr[3]; tmp3 = (INT32) wsptr[1]; - + z2 = tmp0 + tmp2; z3 = tmp1 + tmp3; - z1 = MULTIPLY(z2 + z3, FIX_1_175875602); /* sqrt(2) * c3 */ - z2 = MULTIPLY(z2, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */ - z3 = MULTIPLY(z3, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */ + z1 = MULTIPLY(z2 + z3, FIX_1_175875602); /* c3 */ + z2 = MULTIPLY(z2, - FIX_1_961570560); /* -c3-c5 */ + z3 = MULTIPLY(z3, - FIX_0_390180644); /* -c3+c5 */ z2 += z1; z3 += z1; - z1 = MULTIPLY(tmp0 + tmp3, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */ - tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */ - tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */ + z1 = MULTIPLY(tmp0 + tmp3, - FIX_0_899976223); /* -c3+c7 */ + tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* -c1+c3+c5-c7 */ + tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* c1+c3-c5-c7 */ tmp0 += z1 + z2; tmp3 += z1 + z3; - z1 = MULTIPLY(tmp1 + tmp2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */ - tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */ - tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */ + z1 = MULTIPLY(tmp1 + tmp2, - FIX_2_562915447); /* -c1-c3 */ + tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* c1+c3-c5+c7 */ + tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* c1+c3+c5-c7 */ tmp1 += z1 + z3; tmp2 += z1 + z2; - + /* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */ - + outptr[0] = range_limit[(int) RIGHT_SHIFT(tmp10 + tmp3, CONST_BITS+PASS1_BITS+3) & RANGE_MASK]; @@ -4221,7 +4297,7 @@ jpeg_idct_8x16 (j_decompress_ptr cinfo, jpeg_component_info * compptr, outptr[4] = range_limit[(int) RIGHT_SHIFT(tmp13 - tmp0, CONST_BITS+PASS1_BITS+3) & RANGE_MASK]; - + wsptr += DCTSIZE; /* advance pointer to next row */ } } @@ -4254,6 +4330,7 @@ jpeg_idct_7x14 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 1: process columns from input, store into work array. * 14-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/28). */ + inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; @@ -4341,14 +4418,17 @@ jpeg_idct_7x14 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 2: process 14 rows from work array, store into output array. * 7-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/14). */ + wsptr = workspace; for (ctr = 0; ctr < 14; ctr++) { outptr = output_buf[ctr] + output_col; /* Even part */ - /* Add fudge factor here for final descale. */ - tmp23 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp23 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp23 <<= CONST_BITS; z1 = (INT32) wsptr[2]; @@ -4437,6 +4517,7 @@ jpeg_idct_6x12 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 1: process columns from input, store into work array. * 12-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/24). */ + inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; @@ -4520,14 +4601,17 @@ jpeg_idct_6x12 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 2: process 12 rows from work array, store into output array. * 6-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/12). */ + wsptr = workspace; for (ctr = 0; ctr < 12; ctr++) { outptr = output_buf[ctr] + output_col; /* Even part */ - /* Add fudge factor here for final descale. */ - tmp10 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp10 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp10 <<= CONST_BITS; tmp12 = (INT32) wsptr[4]; tmp20 = MULTIPLY(tmp12, FIX(0.707106781)); /* c4 */ @@ -4601,6 +4685,7 @@ jpeg_idct_5x10 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 1: process columns from input, store into work array. * 10-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/20). */ + inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; @@ -4676,14 +4761,17 @@ jpeg_idct_5x10 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 2: process 10 rows from work array, store into output array. * 5-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/10). */ + wsptr = workspace; for (ctr = 0; ctr < 10; ctr++) { outptr = output_buf[ctr] + output_col; /* Even part */ - /* Add fudge factor here for final descale. */ - tmp12 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp12 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp12 <<= CONST_BITS; tmp13 = (INT32) wsptr[2]; tmp14 = (INT32) wsptr[4]; @@ -4750,9 +4838,11 @@ jpeg_idct_4x8 (j_decompress_ptr cinfo, jpeg_component_info * compptr, int workspace[4*8]; /* buffers data between passes */ SHIFT_TEMPS - /* Pass 1: process columns from input, store into work array. */ - /* Note results are scaled up by sqrt(8) compared to a true IDCT; */ - /* furthermore, we scale the results by 2**PASS1_BITS. */ + /* Pass 1: process columns from input, store into work array. + * Note results are scaled up by sqrt(8) compared to a true IDCT; + * furthermore, we scale the results by 2**PASS1_BITS. + * 8-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/16). + */ inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; @@ -4789,16 +4879,17 @@ jpeg_idct_4x8 (j_decompress_ptr cinfo, jpeg_component_info * compptr, continue; } - /* Even part: reverse the even part of the forward DCT. */ - /* The rotator is sqrt(2)*c(-6). */ + /* Even part: reverse the even part of the forward DCT. + * The rotator is c(-6). + */ z2 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]); z3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]); - - z1 = MULTIPLY(z2 + z3, FIX_0_541196100); - tmp2 = z1 + MULTIPLY(z2, FIX_0_765366865); - tmp3 = z1 - MULTIPLY(z3, FIX_1_847759065); - + + z1 = MULTIPLY(z2 + z3, FIX_0_541196100); /* c6 */ + tmp2 = z1 + MULTIPLY(z2, FIX_0_765366865); /* c2-c6 */ + tmp3 = z1 - MULTIPLY(z3, FIX_1_847759065); /* c2+c6 */ + z2 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]); z3 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]); z2 <<= CONST_BITS; @@ -4808,7 +4899,7 @@ jpeg_idct_4x8 (j_decompress_ptr cinfo, jpeg_component_info * compptr, tmp0 = z2 + z3; tmp1 = z2 - z3; - + tmp10 = tmp0 + tmp2; tmp13 = tmp0 - tmp2; tmp11 = tmp1 + tmp3; @@ -4826,21 +4917,21 @@ jpeg_idct_4x8 (j_decompress_ptr cinfo, jpeg_component_info * compptr, z2 = tmp0 + tmp2; z3 = tmp1 + tmp3; - z1 = MULTIPLY(z2 + z3, FIX_1_175875602); /* sqrt(2) * c3 */ - z2 = MULTIPLY(z2, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */ - z3 = MULTIPLY(z3, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */ + z1 = MULTIPLY(z2 + z3, FIX_1_175875602); /* c3 */ + z2 = MULTIPLY(z2, - FIX_1_961570560); /* -c3-c5 */ + z3 = MULTIPLY(z3, - FIX_0_390180644); /* -c3+c5 */ z2 += z1; z3 += z1; - z1 = MULTIPLY(tmp0 + tmp3, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */ - tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */ - tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */ + z1 = MULTIPLY(tmp0 + tmp3, - FIX_0_899976223); /* -c3+c7 */ + tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* -c1+c3+c5-c7 */ + tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* c1+c3-c5-c7 */ tmp0 += z1 + z2; tmp3 += z1 + z3; - z1 = MULTIPLY(tmp1 + tmp2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */ - tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */ - tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */ + z1 = MULTIPLY(tmp1 + tmp2, - FIX_2_562915447); /* -c1-c3 */ + tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* c1+c3-c5+c7 */ + tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* c1+c3+c5-c7 */ tmp1 += z1 + z3; tmp2 += z1 + z2; @@ -4861,16 +4952,20 @@ jpeg_idct_4x8 (j_decompress_ptr cinfo, jpeg_component_info * compptr, } /* Pass 2: process 8 rows from work array, store into output array. - * 4-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/16). + * 4-point IDCT kernel, + * cK represents sqrt(2) * cos(K*pi/16) [refers to 8-point IDCT]. */ + wsptr = workspace; for (ctr = 0; ctr < 8; ctr++) { outptr = output_buf[ctr] + output_col; /* Even part */ - /* Add fudge factor here for final descale. */ - tmp0 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp0 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp2 = (INT32) wsptr[2]; tmp10 = (tmp0 + tmp2) << CONST_BITS; @@ -4900,7 +4995,7 @@ jpeg_idct_4x8 (j_decompress_ptr cinfo, jpeg_component_info * compptr, outptr[2] = range_limit[(int) RIGHT_SHIFT(tmp12 - tmp2, CONST_BITS+PASS1_BITS+3) & RANGE_MASK]; - + wsptr += 4; /* advance pointer to next row */ } } @@ -4932,6 +5027,7 @@ jpeg_idct_3x6 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 1: process columns from input, store into work array. * 6-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/12). */ + inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; @@ -4974,14 +5070,17 @@ jpeg_idct_3x6 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Pass 2: process 6 rows from work array, store into output array. * 3-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/6). */ + wsptr = workspace; for (ctr = 0; ctr < 6; ctr++) { outptr = output_buf[ctr] + output_col; /* Even part */ - /* Add fudge factor here for final descale. */ - tmp0 = (INT32) wsptr[0] + (ONE << (PASS1_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp0 = (INT32) wsptr[0] + + ((((INT32) RANGE_CENTER) << (PASS1_BITS+3)) + + (ONE << (PASS1_BITS+2))); tmp0 <<= CONST_BITS; tmp2 = (INT32) wsptr[2]; tmp12 = MULTIPLY(tmp2, FIX(0.707106781)); /* c2 */ @@ -5037,6 +5136,7 @@ jpeg_idct_2x4 (j_decompress_ptr cinfo, jpeg_component_info * compptr, * 4-point IDCT kernel, * cK represents sqrt(2) * cos(K*pi/16) [refers to 8-point IDCT]. */ + inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; @@ -5075,8 +5175,10 @@ jpeg_idct_2x4 (j_decompress_ptr cinfo, jpeg_component_info * compptr, /* Even part */ - /* Add fudge factor here for final descale. */ - tmp10 = wsptr[0] + (ONE << (CONST_BITS+2)); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp10 = wsptr[0] + + ((((INT32) RANGE_CENTER) << (CONST_BITS+3)) + + (ONE << (CONST_BITS+2))); /* Odd part */ @@ -5106,31 +5208,31 @@ jpeg_idct_1x2 (j_decompress_ptr cinfo, jpeg_component_info * compptr, JCOEFPTR coef_block, JSAMPARRAY output_buf, JDIMENSION output_col) { - INT32 tmp0, tmp10; + DCTELEM tmp0, tmp1; ISLOW_MULT_TYPE * quantptr; JSAMPLE *range_limit = IDCT_range_limit(cinfo); - SHIFT_TEMPS + ISHIFT_TEMPS /* Process 1 column from input, store into output array. */ quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; /* Even part */ - - tmp10 = DEQUANTIZE(coef_block[DCTSIZE*0], quantptr[DCTSIZE*0]); - /* Add fudge factor here for final descale. */ - tmp10 += ONE << 2; + + tmp0 = DEQUANTIZE(coef_block[DCTSIZE*0], quantptr[DCTSIZE*0]); + /* Add range center and fudge factor for final descale and range-limit. */ + tmp0 += (((DCTELEM) RANGE_CENTER) << 3) + (1 << 2); /* Odd part */ - tmp0 = DEQUANTIZE(coef_block[DCTSIZE*1], quantptr[DCTSIZE*1]); + tmp1 = DEQUANTIZE(coef_block[DCTSIZE*1], quantptr[DCTSIZE*1]); /* Final output stage */ - output_buf[0][output_col] = range_limit[(int) RIGHT_SHIFT(tmp10 + tmp0, 3) - & RANGE_MASK]; - output_buf[1][output_col] = range_limit[(int) RIGHT_SHIFT(tmp10 - tmp0, 3) - & RANGE_MASK]; + output_buf[0][output_col] = + range_limit[(int) IRIGHT_SHIFT(tmp0 + tmp1, 3) & RANGE_MASK]; + output_buf[1][output_col] = + range_limit[(int) IRIGHT_SHIFT(tmp0 - tmp1, 3) & RANGE_MASK]; } #endif /* IDCT_SCALING_SUPPORTED */ |