/src/libjpeg-turbo.2.1.x/jidctint.c
Line | Count | Source (jump to first uncovered line) |
1 | | /* |
2 | | * jidctint.c |
3 | | * |
4 | | * This file was part of the Independent JPEG Group's software: |
5 | | * Copyright (C) 1991-1998, Thomas G. Lane. |
6 | | * Modification developed 2002-2018 by Guido Vollbeding. |
7 | | * libjpeg-turbo Modifications: |
8 | | * Copyright (C) 2015, 2020, D. R. Commander. |
9 | | * For conditions of distribution and use, see the accompanying README.ijg |
10 | | * file. |
11 | | * |
12 | | * This file contains a slower but more accurate integer implementation of the |
13 | | * inverse DCT (Discrete Cosine Transform). In the IJG code, this routine |
14 | | * must also perform dequantization of the input coefficients. |
15 | | * |
16 | | * A 2-D IDCT can be done by 1-D IDCT on each column followed by 1-D IDCT |
17 | | * on each row (or vice versa, but it's more convenient to emit a row at |
18 | | * a time). Direct algorithms are also available, but they are much more |
19 | | * complex and seem not to be any faster when reduced to code. |
20 | | * |
21 | | * This implementation is based on an algorithm described in |
22 | | * C. Loeffler, A. Ligtenberg and G. Moschytz, "Practical Fast 1-D DCT |
23 | | * Algorithms with 11 Multiplications", Proc. Int'l. Conf. on Acoustics, |
24 | | * Speech, and Signal Processing 1989 (ICASSP '89), pp. 988-991. |
25 | | * The primary algorithm described there uses 11 multiplies and 29 adds. |
26 | | * We use their alternate method with 12 multiplies and 32 adds. |
27 | | * The advantage of this method is that no data path contains more than one |
28 | | * multiplication; this allows a very simple and accurate implementation in |
29 | | * scaled fixed-point arithmetic, with a minimal number of shifts. |
30 | | * |
31 | | * We also provide IDCT routines with various output sample block sizes for |
32 | | * direct resolution reduction or enlargement without additional resampling: |
33 | | * NxN (N=1...16) pixels for one 8x8 input DCT block. |
34 | | * |
35 | | * For N<8 we simply take the corresponding low-frequency coefficients of |
36 | | * the 8x8 input DCT block and apply an NxN point IDCT on the sub-block |
37 | | * to yield the downscaled outputs. |
38 | | * This can be seen as direct low-pass downsampling from the DCT domain |
39 | | * point of view rather than the usual spatial domain point of view, |
40 | | * yielding significant computational savings and results at least |
41 | | * as good as common bilinear (averaging) spatial downsampling. |
42 | | * |
43 | | * For N>8 we apply a partial NxN IDCT on the 8 input coefficients as |
44 | | * lower frequencies and higher frequencies assumed to be zero. |
45 | | * It turns out that the computational effort is similar to the 8x8 IDCT |
46 | | * regarding the output size. |
47 | | * Furthermore, the scaling and descaling is the same for all IDCT sizes. |
48 | | * |
49 | | * CAUTION: We rely on the FIX() macro except for the N=1,2,4,8 cases |
50 | | * since there would be too many additional constants to pre-calculate. |
51 | | */ |
52 | | |
53 | | #define JPEG_INTERNALS |
54 | | #include "jinclude.h" |
55 | | #include "jpeglib.h" |
56 | | #include "jdct.h" /* Private declarations for DCT subsystem */ |
57 | | |
58 | | #ifdef DCT_ISLOW_SUPPORTED |
59 | | |
60 | | |
61 | | /* |
62 | | * This module is specialized to the case DCTSIZE = 8. |
63 | | */ |
64 | | |
65 | | #if DCTSIZE != 8 |
66 | | Sorry, this code only copes with 8x8 DCT blocks. /* deliberate syntax err */ |
67 | | #endif |
68 | | |
69 | | |
70 | | /* |
71 | | * The poop on this scaling stuff is as follows: |
72 | | * |
73 | | * Each 1-D IDCT step produces outputs which are a factor of sqrt(N) |
74 | | * larger than the true IDCT outputs. The final outputs are therefore |
75 | | * a factor of N larger than desired; since N=8 this can be cured by |
76 | | * a simple right shift at the end of the algorithm. The advantage of |
77 | | * this arrangement is that we save two multiplications per 1-D IDCT, |
78 | | * because the y0 and y4 inputs need not be divided by sqrt(N). |
79 | | * |
80 | | * We have to do addition and subtraction of the integer inputs, which |
81 | | * is no problem, and multiplication by fractional constants, which is |
82 | | * a problem to do in integer arithmetic. We multiply all the constants |
83 | | * by CONST_SCALE and convert them to integer constants (thus retaining |
84 | | * CONST_BITS bits of precision in the constants). After doing a |
85 | | * multiplication we have to divide the product by CONST_SCALE, with proper |
86 | | * rounding, to produce the correct output. This division can be done |
87 | | * cheaply as a right shift of CONST_BITS bits. We postpone shifting |
88 | | * as long as possible so that partial sums can be added together with |
89 | | * full fractional precision. |
90 | | * |
91 | | * The outputs of the first pass are scaled up by PASS1_BITS bits so that |
92 | | * they are represented to better-than-integral precision. These outputs |
93 | | * require BITS_IN_JSAMPLE + PASS1_BITS + 3 bits; this fits in a 16-bit word |
94 | | * with the recommended scaling. (To scale up 12-bit sample data further, an |
95 | | * intermediate JLONG array would be needed.) |
96 | | * |
97 | | * To avoid overflow of the 32-bit intermediate results in pass 2, we must |
98 | | * have BITS_IN_JSAMPLE + CONST_BITS + PASS1_BITS <= 26. Error analysis |
99 | | * shows that the values given below are the most effective. |
100 | | */ |
101 | | |
102 | | #if BITS_IN_JSAMPLE == 8 |
103 | 0 | #define CONST_BITS 13 |
104 | 0 | #define PASS1_BITS 2 |
105 | | #else |
106 | | #define CONST_BITS 13 |
107 | | #define PASS1_BITS 1 /* lose a little precision to avoid overflow */ |
108 | | #endif |
109 | | |
110 | | /* Some C compilers fail to reduce "FIX(constant)" at compile time, thus |
111 | | * causing a lot of useless floating-point operations at run time. |
112 | | * To get around this we use the following pre-calculated constants. |
113 | | * If you change CONST_BITS you may want to add appropriate values. |
114 | | * (With a reasonable C compiler, you can just rely on the FIX() macro...) |
115 | | */ |
116 | | |
117 | | #if CONST_BITS == 13 |
118 | | #define FIX_0_298631336 ((JLONG)2446) /* FIX(0.298631336) */ |
119 | | #define FIX_0_390180644 ((JLONG)3196) /* FIX(0.390180644) */ |
120 | | #define FIX_0_541196100 ((JLONG)4433) /* FIX(0.541196100) */ |
121 | | #define FIX_0_765366865 ((JLONG)6270) /* FIX(0.765366865) */ |
122 | | #define FIX_0_899976223 ((JLONG)7373) /* FIX(0.899976223) */ |
123 | | #define FIX_1_175875602 ((JLONG)9633) /* FIX(1.175875602) */ |
124 | | #define FIX_1_501321110 ((JLONG)12299) /* FIX(1.501321110) */ |
125 | | #define FIX_1_847759065 ((JLONG)15137) /* FIX(1.847759065) */ |
126 | | #define FIX_1_961570560 ((JLONG)16069) /* FIX(1.961570560) */ |
127 | | #define FIX_2_053119869 ((JLONG)16819) /* FIX(2.053119869) */ |
128 | | #define FIX_2_562915447 ((JLONG)20995) /* FIX(2.562915447) */ |
129 | | #define FIX_3_072711026 ((JLONG)25172) /* FIX(3.072711026) */ |
130 | | #else |
131 | | #define FIX_0_298631336 FIX(0.298631336) |
132 | | #define FIX_0_390180644 FIX(0.390180644) |
133 | | #define FIX_0_541196100 FIX(0.541196100) |
134 | | #define FIX_0_765366865 FIX(0.765366865) |
135 | | #define FIX_0_899976223 FIX(0.899976223) |
136 | | #define FIX_1_175875602 FIX(1.175875602) |
137 | | #define FIX_1_501321110 FIX(1.501321110) |
138 | | #define FIX_1_847759065 FIX(1.847759065) |
139 | | #define FIX_1_961570560 FIX(1.961570560) |
140 | | #define FIX_2_053119869 FIX(2.053119869) |
141 | | #define FIX_2_562915447 FIX(2.562915447) |
142 | | #define FIX_3_072711026 FIX(3.072711026) |
143 | | #endif |
144 | | |
145 | | |
146 | | /* Multiply an JLONG variable by an JLONG constant to yield an JLONG result. |
147 | | * For 8-bit samples with the recommended scaling, all the variable |
148 | | * and constant values involved are no more than 16 bits wide, so a |
149 | | * 16x16->32 bit multiply can be used instead of a full 32x32 multiply. |
150 | | * For 12-bit samples, a full 32-bit multiplication will be needed. |
151 | | */ |
152 | | |
153 | | #if BITS_IN_JSAMPLE == 8 |
154 | 0 | #define MULTIPLY(var, const) MULTIPLY16C16(var, const) |
155 | | #else |
156 | | #define MULTIPLY(var, const) ((var) * (const)) |
157 | | #endif |
158 | | |
159 | | |
160 | | /* Dequantize a coefficient by multiplying it by the multiplier-table |
161 | | * entry; produce an int result. In this module, both inputs and result |
162 | | * are 16 bits or less, so either int or short multiply will work. |
163 | | */ |
164 | | |
165 | 0 | #define DEQUANTIZE(coef, quantval) (((ISLOW_MULT_TYPE)(coef)) * (quantval)) |
166 | | |
167 | | |
168 | | /* |
169 | | * Perform dequantization and inverse DCT on one block of coefficients. |
170 | | */ |
171 | | |
172 | | GLOBAL(void) |
173 | | jpeg_idct_islow(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
174 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
175 | | JDIMENSION output_col) |
176 | 0 | { |
177 | 0 | JLONG tmp0, tmp1, tmp2, tmp3; |
178 | 0 | JLONG tmp10, tmp11, tmp12, tmp13; |
179 | 0 | JLONG z1, z2, z3, z4, z5; |
180 | 0 | JCOEFPTR inptr; |
181 | 0 | ISLOW_MULT_TYPE *quantptr; |
182 | 0 | int *wsptr; |
183 | 0 | JSAMPROW outptr; |
184 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
185 | 0 | int ctr; |
186 | 0 | int workspace[DCTSIZE2]; /* buffers data between passes */ |
187 | | SHIFT_TEMPS |
188 | | |
189 | | /* Pass 1: process columns from input, store into work array. */ |
190 | | /* Note results are scaled up by sqrt(8) compared to a true IDCT; */ |
191 | | /* furthermore, we scale the results by 2**PASS1_BITS. */ |
192 | |
|
193 | 0 | inptr = coef_block; |
194 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
195 | 0 | wsptr = workspace; |
196 | 0 | for (ctr = DCTSIZE; ctr > 0; ctr--) { |
197 | | /* Due to quantization, we will usually find that many of the input |
198 | | * coefficients are zero, especially the AC terms. We can exploit this |
199 | | * by short-circuiting the IDCT calculation for any column in which all |
200 | | * the AC terms are zero. In that case each output is equal to the |
201 | | * DC coefficient (with scale factor as needed). |
202 | | * With typical images and quantization tables, half or more of the |
203 | | * column DCT calculations can be simplified this way. |
204 | | */ |
205 | |
|
206 | 0 | if (inptr[DCTSIZE * 1] == 0 && inptr[DCTSIZE * 2] == 0 && |
207 | 0 | inptr[DCTSIZE * 3] == 0 && inptr[DCTSIZE * 4] == 0 && |
208 | 0 | inptr[DCTSIZE * 5] == 0 && inptr[DCTSIZE * 6] == 0 && |
209 | 0 | inptr[DCTSIZE * 7] == 0) { |
210 | | /* AC terms all zero */ |
211 | 0 | int dcval = LEFT_SHIFT(DEQUANTIZE(inptr[DCTSIZE * 0], |
212 | 0 | quantptr[DCTSIZE * 0]), PASS1_BITS); |
213 | |
|
214 | 0 | wsptr[DCTSIZE * 0] = dcval; |
215 | 0 | wsptr[DCTSIZE * 1] = dcval; |
216 | 0 | wsptr[DCTSIZE * 2] = dcval; |
217 | 0 | wsptr[DCTSIZE * 3] = dcval; |
218 | 0 | wsptr[DCTSIZE * 4] = dcval; |
219 | 0 | wsptr[DCTSIZE * 5] = dcval; |
220 | 0 | wsptr[DCTSIZE * 6] = dcval; |
221 | 0 | wsptr[DCTSIZE * 7] = dcval; |
222 | |
|
223 | 0 | inptr++; /* advance pointers to next column */ |
224 | 0 | quantptr++; |
225 | 0 | wsptr++; |
226 | 0 | continue; |
227 | 0 | } |
228 | | |
229 | | /* Even part: reverse the even part of the forward DCT. */ |
230 | | /* The rotator is sqrt(2)*c(-6). */ |
231 | | |
232 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
233 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 6], quantptr[DCTSIZE * 6]); |
234 | |
|
235 | 0 | z1 = MULTIPLY(z2 + z3, FIX_0_541196100); |
236 | 0 | tmp2 = z1 + MULTIPLY(z3, -FIX_1_847759065); |
237 | 0 | tmp3 = z1 + MULTIPLY(z2, FIX_0_765366865); |
238 | |
|
239 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
240 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 4], quantptr[DCTSIZE * 4]); |
241 | |
|
242 | 0 | tmp0 = LEFT_SHIFT(z2 + z3, CONST_BITS); |
243 | 0 | tmp1 = LEFT_SHIFT(z2 - z3, CONST_BITS); |
244 | |
|
245 | 0 | tmp10 = tmp0 + tmp3; |
246 | 0 | tmp13 = tmp0 - tmp3; |
247 | 0 | tmp11 = tmp1 + tmp2; |
248 | 0 | tmp12 = tmp1 - tmp2; |
249 | | |
250 | | /* Odd part per figure 8; the matrix is unitary and hence its |
251 | | * transpose is its inverse. i0..i3 are y7,y5,y3,y1 respectively. |
252 | | */ |
253 | |
|
254 | 0 | tmp0 = DEQUANTIZE(inptr[DCTSIZE * 7], quantptr[DCTSIZE * 7]); |
255 | 0 | tmp1 = DEQUANTIZE(inptr[DCTSIZE * 5], quantptr[DCTSIZE * 5]); |
256 | 0 | tmp2 = DEQUANTIZE(inptr[DCTSIZE * 3], quantptr[DCTSIZE * 3]); |
257 | 0 | tmp3 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
258 | |
|
259 | 0 | z1 = tmp0 + tmp3; |
260 | 0 | z2 = tmp1 + tmp2; |
261 | 0 | z3 = tmp0 + tmp2; |
262 | 0 | z4 = tmp1 + tmp3; |
263 | 0 | z5 = MULTIPLY(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */ |
264 | |
|
265 | 0 | tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */ |
266 | 0 | tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */ |
267 | 0 | tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */ |
268 | 0 | tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */ |
269 | 0 | z1 = MULTIPLY(z1, -FIX_0_899976223); /* sqrt(2) * ( c7-c3) */ |
270 | 0 | z2 = MULTIPLY(z2, -FIX_2_562915447); /* sqrt(2) * (-c1-c3) */ |
271 | 0 | z3 = MULTIPLY(z3, -FIX_1_961570560); /* sqrt(2) * (-c3-c5) */ |
272 | 0 | z4 = MULTIPLY(z4, -FIX_0_390180644); /* sqrt(2) * ( c5-c3) */ |
273 | |
|
274 | 0 | z3 += z5; |
275 | 0 | z4 += z5; |
276 | |
|
277 | 0 | tmp0 += z1 + z3; |
278 | 0 | tmp1 += z2 + z4; |
279 | 0 | tmp2 += z2 + z3; |
280 | 0 | tmp3 += z1 + z4; |
281 | | |
282 | | /* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */ |
283 | |
|
284 | 0 | wsptr[DCTSIZE * 0] = (int)DESCALE(tmp10 + tmp3, CONST_BITS - PASS1_BITS); |
285 | 0 | wsptr[DCTSIZE * 7] = (int)DESCALE(tmp10 - tmp3, CONST_BITS - PASS1_BITS); |
286 | 0 | wsptr[DCTSIZE * 1] = (int)DESCALE(tmp11 + tmp2, CONST_BITS - PASS1_BITS); |
287 | 0 | wsptr[DCTSIZE * 6] = (int)DESCALE(tmp11 - tmp2, CONST_BITS - PASS1_BITS); |
288 | 0 | wsptr[DCTSIZE * 2] = (int)DESCALE(tmp12 + tmp1, CONST_BITS - PASS1_BITS); |
289 | 0 | wsptr[DCTSIZE * 5] = (int)DESCALE(tmp12 - tmp1, CONST_BITS - PASS1_BITS); |
290 | 0 | wsptr[DCTSIZE * 3] = (int)DESCALE(tmp13 + tmp0, CONST_BITS - PASS1_BITS); |
291 | 0 | wsptr[DCTSIZE * 4] = (int)DESCALE(tmp13 - tmp0, CONST_BITS - PASS1_BITS); |
292 | |
|
293 | 0 | inptr++; /* advance pointers to next column */ |
294 | 0 | quantptr++; |
295 | 0 | wsptr++; |
296 | 0 | } |
297 | | |
298 | | /* Pass 2: process rows from work array, store into output array. */ |
299 | | /* Note that we must descale the results by a factor of 8 == 2**3, */ |
300 | | /* and also undo the PASS1_BITS scaling. */ |
301 | |
|
302 | 0 | wsptr = workspace; |
303 | 0 | for (ctr = 0; ctr < DCTSIZE; ctr++) { |
304 | 0 | outptr = output_buf[ctr] + output_col; |
305 | | /* Rows of zeroes can be exploited in the same way as we did with columns. |
306 | | * However, the column calculation has created many nonzero AC terms, so |
307 | | * the simplification applies less often (typically 5% to 10% of the time). |
308 | | * On machines with very fast multiplication, it's possible that the |
309 | | * test takes more time than it's worth. In that case this section |
310 | | * may be commented out. |
311 | | */ |
312 | |
|
313 | 0 | #ifndef NO_ZERO_ROW_TEST |
314 | 0 | if (wsptr[1] == 0 && wsptr[2] == 0 && wsptr[3] == 0 && wsptr[4] == 0 && |
315 | 0 | wsptr[5] == 0 && wsptr[6] == 0 && wsptr[7] == 0) { |
316 | | /* AC terms all zero */ |
317 | 0 | JSAMPLE dcval = range_limit[(int)DESCALE((JLONG)wsptr[0], |
318 | 0 | PASS1_BITS + 3) & RANGE_MASK]; |
319 | |
|
320 | 0 | outptr[0] = dcval; |
321 | 0 | outptr[1] = dcval; |
322 | 0 | outptr[2] = dcval; |
323 | 0 | outptr[3] = dcval; |
324 | 0 | outptr[4] = dcval; |
325 | 0 | outptr[5] = dcval; |
326 | 0 | outptr[6] = dcval; |
327 | 0 | outptr[7] = dcval; |
328 | |
|
329 | 0 | wsptr += DCTSIZE; /* advance pointer to next row */ |
330 | 0 | continue; |
331 | 0 | } |
332 | 0 | #endif |
333 | | |
334 | | /* Even part: reverse the even part of the forward DCT. */ |
335 | | /* The rotator is sqrt(2)*c(-6). */ |
336 | | |
337 | 0 | z2 = (JLONG)wsptr[2]; |
338 | 0 | z3 = (JLONG)wsptr[6]; |
339 | |
|
340 | 0 | z1 = MULTIPLY(z2 + z3, FIX_0_541196100); |
341 | 0 | tmp2 = z1 + MULTIPLY(z3, -FIX_1_847759065); |
342 | 0 | tmp3 = z1 + MULTIPLY(z2, FIX_0_765366865); |
343 | |
|
344 | 0 | tmp0 = LEFT_SHIFT((JLONG)wsptr[0] + (JLONG)wsptr[4], CONST_BITS); |
345 | 0 | tmp1 = LEFT_SHIFT((JLONG)wsptr[0] - (JLONG)wsptr[4], CONST_BITS); |
346 | |
|
347 | 0 | tmp10 = tmp0 + tmp3; |
348 | 0 | tmp13 = tmp0 - tmp3; |
349 | 0 | tmp11 = tmp1 + tmp2; |
350 | 0 | tmp12 = tmp1 - tmp2; |
351 | | |
352 | | /* Odd part per figure 8; the matrix is unitary and hence its |
353 | | * transpose is its inverse. i0..i3 are y7,y5,y3,y1 respectively. |
354 | | */ |
355 | |
|
356 | 0 | tmp0 = (JLONG)wsptr[7]; |
357 | 0 | tmp1 = (JLONG)wsptr[5]; |
358 | 0 | tmp2 = (JLONG)wsptr[3]; |
359 | 0 | tmp3 = (JLONG)wsptr[1]; |
360 | |
|
361 | 0 | z1 = tmp0 + tmp3; |
362 | 0 | z2 = tmp1 + tmp2; |
363 | 0 | z3 = tmp0 + tmp2; |
364 | 0 | z4 = tmp1 + tmp3; |
365 | 0 | z5 = MULTIPLY(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */ |
366 | |
|
367 | 0 | tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */ |
368 | 0 | tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */ |
369 | 0 | tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */ |
370 | 0 | tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */ |
371 | 0 | z1 = MULTIPLY(z1, -FIX_0_899976223); /* sqrt(2) * ( c7-c3) */ |
372 | 0 | z2 = MULTIPLY(z2, -FIX_2_562915447); /* sqrt(2) * (-c1-c3) */ |
373 | 0 | z3 = MULTIPLY(z3, -FIX_1_961570560); /* sqrt(2) * (-c3-c5) */ |
374 | 0 | z4 = MULTIPLY(z4, -FIX_0_390180644); /* sqrt(2) * ( c5-c3) */ |
375 | |
|
376 | 0 | z3 += z5; |
377 | 0 | z4 += z5; |
378 | |
|
379 | 0 | tmp0 += z1 + z3; |
380 | 0 | tmp1 += z2 + z4; |
381 | 0 | tmp2 += z2 + z3; |
382 | 0 | tmp3 += z1 + z4; |
383 | | |
384 | | /* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */ |
385 | |
|
386 | 0 | outptr[0] = range_limit[(int)DESCALE(tmp10 + tmp3, |
387 | 0 | CONST_BITS + PASS1_BITS + 3) & |
388 | 0 | RANGE_MASK]; |
389 | 0 | outptr[7] = range_limit[(int)DESCALE(tmp10 - tmp3, |
390 | 0 | CONST_BITS + PASS1_BITS + 3) & |
391 | 0 | RANGE_MASK]; |
392 | 0 | outptr[1] = range_limit[(int)DESCALE(tmp11 + tmp2, |
393 | 0 | CONST_BITS + PASS1_BITS + 3) & |
394 | 0 | RANGE_MASK]; |
395 | 0 | outptr[6] = range_limit[(int)DESCALE(tmp11 - tmp2, |
396 | 0 | CONST_BITS + PASS1_BITS + 3) & |
397 | 0 | RANGE_MASK]; |
398 | 0 | outptr[2] = range_limit[(int)DESCALE(tmp12 + tmp1, |
399 | 0 | CONST_BITS + PASS1_BITS + 3) & |
400 | 0 | RANGE_MASK]; |
401 | 0 | outptr[5] = range_limit[(int)DESCALE(tmp12 - tmp1, |
402 | 0 | CONST_BITS + PASS1_BITS + 3) & |
403 | 0 | RANGE_MASK]; |
404 | 0 | outptr[3] = range_limit[(int)DESCALE(tmp13 + tmp0, |
405 | 0 | CONST_BITS + PASS1_BITS + 3) & |
406 | 0 | RANGE_MASK]; |
407 | 0 | outptr[4] = range_limit[(int)DESCALE(tmp13 - tmp0, |
408 | 0 | CONST_BITS + PASS1_BITS + 3) & |
409 | 0 | RANGE_MASK]; |
410 | |
|
411 | 0 | wsptr += DCTSIZE; /* advance pointer to next row */ |
412 | 0 | } |
413 | 0 | } |
414 | | |
415 | | #ifdef IDCT_SCALING_SUPPORTED |
416 | | |
417 | | |
418 | | /* |
419 | | * Perform dequantization and inverse DCT on one block of coefficients, |
420 | | * producing a reduced-size 7x7 output block. |
421 | | * |
422 | | * Optimized algorithm with 12 multiplications in the 1-D kernel. |
423 | | * cK represents sqrt(2) * cos(K*pi/14). |
424 | | */ |
425 | | |
426 | | GLOBAL(void) |
427 | | jpeg_idct_7x7(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
428 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
429 | | JDIMENSION output_col) |
430 | 0 | { |
431 | 0 | JLONG tmp0, tmp1, tmp2, tmp10, tmp11, tmp12, tmp13; |
432 | 0 | JLONG z1, z2, z3; |
433 | 0 | JCOEFPTR inptr; |
434 | 0 | ISLOW_MULT_TYPE *quantptr; |
435 | 0 | int *wsptr; |
436 | 0 | JSAMPROW outptr; |
437 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
438 | 0 | int ctr; |
439 | 0 | int workspace[7 * 7]; /* buffers data between passes */ |
440 | | SHIFT_TEMPS |
441 | | |
442 | | /* Pass 1: process columns from input, store into work array. */ |
443 | |
|
444 | 0 | inptr = coef_block; |
445 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
446 | 0 | wsptr = workspace; |
447 | 0 | for (ctr = 0; ctr < 7; ctr++, inptr++, quantptr++, wsptr++) { |
448 | | /* Even part */ |
449 | |
|
450 | 0 | tmp13 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
451 | 0 | tmp13 = LEFT_SHIFT(tmp13, CONST_BITS); |
452 | | /* Add fudge factor here for final descale. */ |
453 | 0 | tmp13 += ONE << (CONST_BITS - PASS1_BITS - 1); |
454 | |
|
455 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
456 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 4], quantptr[DCTSIZE * 4]); |
457 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 6], quantptr[DCTSIZE * 6]); |
458 | |
|
459 | 0 | tmp10 = MULTIPLY(z2 - z3, FIX(0.881747734)); /* c4 */ |
460 | 0 | tmp12 = MULTIPLY(z1 - z2, FIX(0.314692123)); /* c6 */ |
461 | 0 | tmp11 = tmp10 + tmp12 + tmp13 - MULTIPLY(z2, FIX(1.841218003)); /* c2+c4-c6 */ |
462 | 0 | tmp0 = z1 + z3; |
463 | 0 | z2 -= tmp0; |
464 | 0 | tmp0 = MULTIPLY(tmp0, FIX(1.274162392)) + tmp13; /* c2 */ |
465 | 0 | tmp10 += tmp0 - MULTIPLY(z3, FIX(0.077722536)); /* c2-c4-c6 */ |
466 | 0 | tmp12 += tmp0 - MULTIPLY(z1, FIX(2.470602249)); /* c2+c4+c6 */ |
467 | 0 | tmp13 += MULTIPLY(z2, FIX(1.414213562)); /* c0 */ |
468 | | |
469 | | /* Odd part */ |
470 | |
|
471 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
472 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 3], quantptr[DCTSIZE * 3]); |
473 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 5], quantptr[DCTSIZE * 5]); |
474 | |
|
475 | 0 | tmp1 = MULTIPLY(z1 + z2, FIX(0.935414347)); /* (c3+c1-c5)/2 */ |
476 | 0 | tmp2 = MULTIPLY(z1 - z2, FIX(0.170262339)); /* (c3+c5-c1)/2 */ |
477 | 0 | tmp0 = tmp1 - tmp2; |
478 | 0 | tmp1 += tmp2; |
479 | 0 | tmp2 = MULTIPLY(z2 + z3, -FIX(1.378756276)); /* -c1 */ |
480 | 0 | tmp1 += tmp2; |
481 | 0 | z2 = MULTIPLY(z1 + z3, FIX(0.613604268)); /* c5 */ |
482 | 0 | tmp0 += z2; |
483 | 0 | tmp2 += z2 + MULTIPLY(z3, FIX(1.870828693)); /* c3+c1-c5 */ |
484 | | |
485 | | /* Final output stage */ |
486 | |
|
487 | 0 | wsptr[7 * 0] = (int)RIGHT_SHIFT(tmp10 + tmp0, CONST_BITS - PASS1_BITS); |
488 | 0 | wsptr[7 * 6] = (int)RIGHT_SHIFT(tmp10 - tmp0, CONST_BITS - PASS1_BITS); |
489 | 0 | wsptr[7 * 1] = (int)RIGHT_SHIFT(tmp11 + tmp1, CONST_BITS - PASS1_BITS); |
490 | 0 | wsptr[7 * 5] = (int)RIGHT_SHIFT(tmp11 - tmp1, CONST_BITS - PASS1_BITS); |
491 | 0 | wsptr[7 * 2] = (int)RIGHT_SHIFT(tmp12 + tmp2, CONST_BITS - PASS1_BITS); |
492 | 0 | wsptr[7 * 4] = (int)RIGHT_SHIFT(tmp12 - tmp2, CONST_BITS - PASS1_BITS); |
493 | 0 | wsptr[7 * 3] = (int)RIGHT_SHIFT(tmp13, CONST_BITS - PASS1_BITS); |
494 | 0 | } |
495 | | |
496 | | /* Pass 2: process 7 rows from work array, store into output array. */ |
497 | |
|
498 | 0 | wsptr = workspace; |
499 | 0 | for (ctr = 0; ctr < 7; ctr++) { |
500 | 0 | outptr = output_buf[ctr] + output_col; |
501 | | |
502 | | /* Even part */ |
503 | | |
504 | | /* Add fudge factor here for final descale. */ |
505 | 0 | tmp13 = (JLONG)wsptr[0] + (ONE << (PASS1_BITS + 2)); |
506 | 0 | tmp13 = LEFT_SHIFT(tmp13, CONST_BITS); |
507 | |
|
508 | 0 | z1 = (JLONG)wsptr[2]; |
509 | 0 | z2 = (JLONG)wsptr[4]; |
510 | 0 | z3 = (JLONG)wsptr[6]; |
511 | |
|
512 | 0 | tmp10 = MULTIPLY(z2 - z3, FIX(0.881747734)); /* c4 */ |
513 | 0 | tmp12 = MULTIPLY(z1 - z2, FIX(0.314692123)); /* c6 */ |
514 | 0 | tmp11 = tmp10 + tmp12 + tmp13 - MULTIPLY(z2, FIX(1.841218003)); /* c2+c4-c6 */ |
515 | 0 | tmp0 = z1 + z3; |
516 | 0 | z2 -= tmp0; |
517 | 0 | tmp0 = MULTIPLY(tmp0, FIX(1.274162392)) + tmp13; /* c2 */ |
518 | 0 | tmp10 += tmp0 - MULTIPLY(z3, FIX(0.077722536)); /* c2-c4-c6 */ |
519 | 0 | tmp12 += tmp0 - MULTIPLY(z1, FIX(2.470602249)); /* c2+c4+c6 */ |
520 | 0 | tmp13 += MULTIPLY(z2, FIX(1.414213562)); /* c0 */ |
521 | | |
522 | | /* Odd part */ |
523 | |
|
524 | 0 | z1 = (JLONG)wsptr[1]; |
525 | 0 | z2 = (JLONG)wsptr[3]; |
526 | 0 | z3 = (JLONG)wsptr[5]; |
527 | |
|
528 | 0 | tmp1 = MULTIPLY(z1 + z2, FIX(0.935414347)); /* (c3+c1-c5)/2 */ |
529 | 0 | tmp2 = MULTIPLY(z1 - z2, FIX(0.170262339)); /* (c3+c5-c1)/2 */ |
530 | 0 | tmp0 = tmp1 - tmp2; |
531 | 0 | tmp1 += tmp2; |
532 | 0 | tmp2 = MULTIPLY(z2 + z3, -FIX(1.378756276)); /* -c1 */ |
533 | 0 | tmp1 += tmp2; |
534 | 0 | z2 = MULTIPLY(z1 + z3, FIX(0.613604268)); /* c5 */ |
535 | 0 | tmp0 += z2; |
536 | 0 | tmp2 += z2 + MULTIPLY(z3, FIX(1.870828693)); /* c3+c1-c5 */ |
537 | | |
538 | | /* Final output stage */ |
539 | |
|
540 | 0 | outptr[0] = range_limit[(int)RIGHT_SHIFT(tmp10 + tmp0, |
541 | 0 | CONST_BITS + PASS1_BITS + 3) & |
542 | 0 | RANGE_MASK]; |
543 | 0 | outptr[6] = range_limit[(int)RIGHT_SHIFT(tmp10 - tmp0, |
544 | 0 | CONST_BITS + PASS1_BITS + 3) & |
545 | 0 | RANGE_MASK]; |
546 | 0 | outptr[1] = range_limit[(int)RIGHT_SHIFT(tmp11 + tmp1, |
547 | 0 | CONST_BITS + PASS1_BITS + 3) & |
548 | 0 | RANGE_MASK]; |
549 | 0 | outptr[5] = range_limit[(int)RIGHT_SHIFT(tmp11 - tmp1, |
550 | 0 | CONST_BITS + PASS1_BITS + 3) & |
551 | 0 | RANGE_MASK]; |
552 | 0 | outptr[2] = range_limit[(int)RIGHT_SHIFT(tmp12 + tmp2, |
553 | 0 | CONST_BITS + PASS1_BITS + 3) & |
554 | 0 | RANGE_MASK]; |
555 | 0 | outptr[4] = range_limit[(int)RIGHT_SHIFT(tmp12 - tmp2, |
556 | 0 | CONST_BITS + PASS1_BITS + 3) & |
557 | 0 | RANGE_MASK]; |
558 | 0 | outptr[3] = range_limit[(int)RIGHT_SHIFT(tmp13, |
559 | 0 | CONST_BITS + PASS1_BITS + 3) & |
560 | 0 | RANGE_MASK]; |
561 | |
|
562 | 0 | wsptr += 7; /* advance pointer to next row */ |
563 | 0 | } |
564 | 0 | } |
565 | | |
566 | | |
567 | | /* |
568 | | * Perform dequantization and inverse DCT on one block of coefficients, |
569 | | * producing a reduced-size 6x6 output block. |
570 | | * |
571 | | * Optimized algorithm with 3 multiplications in the 1-D kernel. |
572 | | * cK represents sqrt(2) * cos(K*pi/12). |
573 | | */ |
574 | | |
575 | | GLOBAL(void) |
576 | | jpeg_idct_6x6(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
577 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
578 | | JDIMENSION output_col) |
579 | 0 | { |
580 | 0 | JLONG tmp0, tmp1, tmp2, tmp10, tmp11, tmp12; |
581 | 0 | JLONG z1, z2, z3; |
582 | 0 | JCOEFPTR inptr; |
583 | 0 | ISLOW_MULT_TYPE *quantptr; |
584 | 0 | int *wsptr; |
585 | 0 | JSAMPROW outptr; |
586 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
587 | 0 | int ctr; |
588 | 0 | int workspace[6 * 6]; /* buffers data between passes */ |
589 | | SHIFT_TEMPS |
590 | | |
591 | | /* Pass 1: process columns from input, store into work array. */ |
592 | |
|
593 | 0 | inptr = coef_block; |
594 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
595 | 0 | wsptr = workspace; |
596 | 0 | for (ctr = 0; ctr < 6; ctr++, inptr++, quantptr++, wsptr++) { |
597 | | /* Even part */ |
598 | |
|
599 | 0 | tmp0 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
600 | 0 | tmp0 = LEFT_SHIFT(tmp0, CONST_BITS); |
601 | | /* Add fudge factor here for final descale. */ |
602 | 0 | tmp0 += ONE << (CONST_BITS - PASS1_BITS - 1); |
603 | 0 | tmp2 = DEQUANTIZE(inptr[DCTSIZE * 4], quantptr[DCTSIZE * 4]); |
604 | 0 | tmp10 = MULTIPLY(tmp2, FIX(0.707106781)); /* c4 */ |
605 | 0 | tmp1 = tmp0 + tmp10; |
606 | 0 | tmp11 = RIGHT_SHIFT(tmp0 - tmp10 - tmp10, CONST_BITS - PASS1_BITS); |
607 | 0 | tmp10 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
608 | 0 | tmp0 = MULTIPLY(tmp10, FIX(1.224744871)); /* c2 */ |
609 | 0 | tmp10 = tmp1 + tmp0; |
610 | 0 | tmp12 = tmp1 - tmp0; |
611 | | |
612 | | /* Odd part */ |
613 | |
|
614 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
615 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 3], quantptr[DCTSIZE * 3]); |
616 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 5], quantptr[DCTSIZE * 5]); |
617 | 0 | tmp1 = MULTIPLY(z1 + z3, FIX(0.366025404)); /* c5 */ |
618 | 0 | tmp0 = tmp1 + LEFT_SHIFT(z1 + z2, CONST_BITS); |
619 | 0 | tmp2 = tmp1 + LEFT_SHIFT(z3 - z2, CONST_BITS); |
620 | 0 | tmp1 = LEFT_SHIFT(z1 - z2 - z3, PASS1_BITS); |
621 | | |
622 | | /* Final output stage */ |
623 | |
|
624 | 0 | wsptr[6 * 0] = (int)RIGHT_SHIFT(tmp10 + tmp0, CONST_BITS - PASS1_BITS); |
625 | 0 | wsptr[6 * 5] = (int)RIGHT_SHIFT(tmp10 - tmp0, CONST_BITS - PASS1_BITS); |
626 | 0 | wsptr[6 * 1] = (int)(tmp11 + tmp1); |
627 | 0 | wsptr[6 * 4] = (int)(tmp11 - tmp1); |
628 | 0 | wsptr[6 * 2] = (int)RIGHT_SHIFT(tmp12 + tmp2, CONST_BITS - PASS1_BITS); |
629 | 0 | wsptr[6 * 3] = (int)RIGHT_SHIFT(tmp12 - tmp2, CONST_BITS - PASS1_BITS); |
630 | 0 | } |
631 | | |
632 | | /* Pass 2: process 6 rows from work array, store into output array. */ |
633 | |
|
634 | 0 | wsptr = workspace; |
635 | 0 | for (ctr = 0; ctr < 6; ctr++) { |
636 | 0 | outptr = output_buf[ctr] + output_col; |
637 | | |
638 | | /* Even part */ |
639 | | |
640 | | /* Add fudge factor here for final descale. */ |
641 | 0 | tmp0 = (JLONG)wsptr[0] + (ONE << (PASS1_BITS + 2)); |
642 | 0 | tmp0 = LEFT_SHIFT(tmp0, CONST_BITS); |
643 | 0 | tmp2 = (JLONG)wsptr[4]; |
644 | 0 | tmp10 = MULTIPLY(tmp2, FIX(0.707106781)); /* c4 */ |
645 | 0 | tmp1 = tmp0 + tmp10; |
646 | 0 | tmp11 = tmp0 - tmp10 - tmp10; |
647 | 0 | tmp10 = (JLONG)wsptr[2]; |
648 | 0 | tmp0 = MULTIPLY(tmp10, FIX(1.224744871)); /* c2 */ |
649 | 0 | tmp10 = tmp1 + tmp0; |
650 | 0 | tmp12 = tmp1 - tmp0; |
651 | | |
652 | | /* Odd part */ |
653 | |
|
654 | 0 | z1 = (JLONG)wsptr[1]; |
655 | 0 | z2 = (JLONG)wsptr[3]; |
656 | 0 | z3 = (JLONG)wsptr[5]; |
657 | 0 | tmp1 = MULTIPLY(z1 + z3, FIX(0.366025404)); /* c5 */ |
658 | 0 | tmp0 = tmp1 + LEFT_SHIFT(z1 + z2, CONST_BITS); |
659 | 0 | tmp2 = tmp1 + LEFT_SHIFT(z3 - z2, CONST_BITS); |
660 | 0 | tmp1 = LEFT_SHIFT(z1 - z2 - z3, CONST_BITS); |
661 | | |
662 | | /* Final output stage */ |
663 | |
|
664 | 0 | outptr[0] = range_limit[(int)RIGHT_SHIFT(tmp10 + tmp0, |
665 | 0 | CONST_BITS + PASS1_BITS + 3) & |
666 | 0 | RANGE_MASK]; |
667 | 0 | outptr[5] = range_limit[(int)RIGHT_SHIFT(tmp10 - tmp0, |
668 | 0 | CONST_BITS + PASS1_BITS + 3) & |
669 | 0 | RANGE_MASK]; |
670 | 0 | outptr[1] = range_limit[(int)RIGHT_SHIFT(tmp11 + tmp1, |
671 | 0 | CONST_BITS + PASS1_BITS + 3) & |
672 | 0 | RANGE_MASK]; |
673 | 0 | outptr[4] = range_limit[(int)RIGHT_SHIFT(tmp11 - tmp1, |
674 | 0 | CONST_BITS + PASS1_BITS + 3) & |
675 | 0 | RANGE_MASK]; |
676 | 0 | outptr[2] = range_limit[(int)RIGHT_SHIFT(tmp12 + tmp2, |
677 | 0 | CONST_BITS + PASS1_BITS + 3) & |
678 | 0 | RANGE_MASK]; |
679 | 0 | outptr[3] = range_limit[(int)RIGHT_SHIFT(tmp12 - tmp2, |
680 | 0 | CONST_BITS + PASS1_BITS + 3) & |
681 | 0 | RANGE_MASK]; |
682 | |
|
683 | 0 | wsptr += 6; /* advance pointer to next row */ |
684 | 0 | } |
685 | 0 | } |
686 | | |
687 | | |
688 | | /* |
689 | | * Perform dequantization and inverse DCT on one block of coefficients, |
690 | | * producing a reduced-size 5x5 output block. |
691 | | * |
692 | | * Optimized algorithm with 5 multiplications in the 1-D kernel. |
693 | | * cK represents sqrt(2) * cos(K*pi/10). |
694 | | */ |
695 | | |
696 | | GLOBAL(void) |
697 | | jpeg_idct_5x5(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
698 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
699 | | JDIMENSION output_col) |
700 | 0 | { |
701 | 0 | JLONG tmp0, tmp1, tmp10, tmp11, tmp12; |
702 | 0 | JLONG z1, z2, z3; |
703 | 0 | JCOEFPTR inptr; |
704 | 0 | ISLOW_MULT_TYPE *quantptr; |
705 | 0 | int *wsptr; |
706 | 0 | JSAMPROW outptr; |
707 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
708 | 0 | int ctr; |
709 | 0 | int workspace[5 * 5]; /* buffers data between passes */ |
710 | | SHIFT_TEMPS |
711 | | |
712 | | /* Pass 1: process columns from input, store into work array. */ |
713 | |
|
714 | 0 | inptr = coef_block; |
715 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
716 | 0 | wsptr = workspace; |
717 | 0 | for (ctr = 0; ctr < 5; ctr++, inptr++, quantptr++, wsptr++) { |
718 | | /* Even part */ |
719 | |
|
720 | 0 | tmp12 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
721 | 0 | tmp12 = LEFT_SHIFT(tmp12, CONST_BITS); |
722 | | /* Add fudge factor here for final descale. */ |
723 | 0 | tmp12 += ONE << (CONST_BITS - PASS1_BITS - 1); |
724 | 0 | tmp0 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
725 | 0 | tmp1 = DEQUANTIZE(inptr[DCTSIZE * 4], quantptr[DCTSIZE * 4]); |
726 | 0 | z1 = MULTIPLY(tmp0 + tmp1, FIX(0.790569415)); /* (c2+c4)/2 */ |
727 | 0 | z2 = MULTIPLY(tmp0 - tmp1, FIX(0.353553391)); /* (c2-c4)/2 */ |
728 | 0 | z3 = tmp12 + z2; |
729 | 0 | tmp10 = z3 + z1; |
730 | 0 | tmp11 = z3 - z1; |
731 | 0 | tmp12 -= LEFT_SHIFT(z2, 2); |
732 | | |
733 | | /* Odd part */ |
734 | |
|
735 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
736 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 3], quantptr[DCTSIZE * 3]); |
737 | |
|
738 | 0 | z1 = MULTIPLY(z2 + z3, FIX(0.831253876)); /* c3 */ |
739 | 0 | tmp0 = z1 + MULTIPLY(z2, FIX(0.513743148)); /* c1-c3 */ |
740 | 0 | tmp1 = z1 - MULTIPLY(z3, FIX(2.176250899)); /* c1+c3 */ |
741 | | |
742 | | /* Final output stage */ |
743 | |
|
744 | 0 | wsptr[5 * 0] = (int)RIGHT_SHIFT(tmp10 + tmp0, CONST_BITS - PASS1_BITS); |
745 | 0 | wsptr[5 * 4] = (int)RIGHT_SHIFT(tmp10 - tmp0, CONST_BITS - PASS1_BITS); |
746 | 0 | wsptr[5 * 1] = (int)RIGHT_SHIFT(tmp11 + tmp1, CONST_BITS - PASS1_BITS); |
747 | 0 | wsptr[5 * 3] = (int)RIGHT_SHIFT(tmp11 - tmp1, CONST_BITS - PASS1_BITS); |
748 | 0 | wsptr[5 * 2] = (int)RIGHT_SHIFT(tmp12, CONST_BITS - PASS1_BITS); |
749 | 0 | } |
750 | | |
751 | | /* Pass 2: process 5 rows from work array, store into output array. */ |
752 | |
|
753 | 0 | wsptr = workspace; |
754 | 0 | for (ctr = 0; ctr < 5; ctr++) { |
755 | 0 | outptr = output_buf[ctr] + output_col; |
756 | | |
757 | | /* Even part */ |
758 | | |
759 | | /* Add fudge factor here for final descale. */ |
760 | 0 | tmp12 = (JLONG)wsptr[0] + (ONE << (PASS1_BITS + 2)); |
761 | 0 | tmp12 = LEFT_SHIFT(tmp12, CONST_BITS); |
762 | 0 | tmp0 = (JLONG)wsptr[2]; |
763 | 0 | tmp1 = (JLONG)wsptr[4]; |
764 | 0 | z1 = MULTIPLY(tmp0 + tmp1, FIX(0.790569415)); /* (c2+c4)/2 */ |
765 | 0 | z2 = MULTIPLY(tmp0 - tmp1, FIX(0.353553391)); /* (c2-c4)/2 */ |
766 | 0 | z3 = tmp12 + z2; |
767 | 0 | tmp10 = z3 + z1; |
768 | 0 | tmp11 = z3 - z1; |
769 | 0 | tmp12 -= LEFT_SHIFT(z2, 2); |
770 | | |
771 | | /* Odd part */ |
772 | |
|
773 | 0 | z2 = (JLONG)wsptr[1]; |
774 | 0 | z3 = (JLONG)wsptr[3]; |
775 | |
|
776 | 0 | z1 = MULTIPLY(z2 + z3, FIX(0.831253876)); /* c3 */ |
777 | 0 | tmp0 = z1 + MULTIPLY(z2, FIX(0.513743148)); /* c1-c3 */ |
778 | 0 | tmp1 = z1 - MULTIPLY(z3, FIX(2.176250899)); /* c1+c3 */ |
779 | | |
780 | | /* Final output stage */ |
781 | |
|
782 | 0 | outptr[0] = range_limit[(int)RIGHT_SHIFT(tmp10 + tmp0, |
783 | 0 | CONST_BITS + PASS1_BITS + 3) & |
784 | 0 | RANGE_MASK]; |
785 | 0 | outptr[4] = range_limit[(int)RIGHT_SHIFT(tmp10 - tmp0, |
786 | 0 | CONST_BITS + PASS1_BITS + 3) & |
787 | 0 | RANGE_MASK]; |
788 | 0 | outptr[1] = range_limit[(int)RIGHT_SHIFT(tmp11 + tmp1, |
789 | 0 | CONST_BITS + PASS1_BITS + 3) & |
790 | 0 | RANGE_MASK]; |
791 | 0 | outptr[3] = range_limit[(int)RIGHT_SHIFT(tmp11 - tmp1, |
792 | 0 | CONST_BITS + PASS1_BITS + 3) & |
793 | 0 | RANGE_MASK]; |
794 | 0 | outptr[2] = range_limit[(int)RIGHT_SHIFT(tmp12, |
795 | 0 | CONST_BITS + PASS1_BITS + 3) & |
796 | 0 | RANGE_MASK]; |
797 | |
|
798 | 0 | wsptr += 5; /* advance pointer to next row */ |
799 | 0 | } |
800 | 0 | } |
801 | | |
802 | | |
803 | | /* |
804 | | * Perform dequantization and inverse DCT on one block of coefficients, |
805 | | * producing a reduced-size 3x3 output block. |
806 | | * |
807 | | * Optimized algorithm with 2 multiplications in the 1-D kernel. |
808 | | * cK represents sqrt(2) * cos(K*pi/6). |
809 | | */ |
810 | | |
811 | | GLOBAL(void) |
812 | | jpeg_idct_3x3(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
813 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
814 | | JDIMENSION output_col) |
815 | 0 | { |
816 | 0 | JLONG tmp0, tmp2, tmp10, tmp12; |
817 | 0 | JCOEFPTR inptr; |
818 | 0 | ISLOW_MULT_TYPE *quantptr; |
819 | 0 | int *wsptr; |
820 | 0 | JSAMPROW outptr; |
821 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
822 | 0 | int ctr; |
823 | 0 | int workspace[3 * 3]; /* buffers data between passes */ |
824 | | SHIFT_TEMPS |
825 | | |
826 | | /* Pass 1: process columns from input, store into work array. */ |
827 | |
|
828 | 0 | inptr = coef_block; |
829 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
830 | 0 | wsptr = workspace; |
831 | 0 | for (ctr = 0; ctr < 3; ctr++, inptr++, quantptr++, wsptr++) { |
832 | | /* Even part */ |
833 | |
|
834 | 0 | tmp0 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
835 | 0 | tmp0 = LEFT_SHIFT(tmp0, CONST_BITS); |
836 | | /* Add fudge factor here for final descale. */ |
837 | 0 | tmp0 += ONE << (CONST_BITS - PASS1_BITS - 1); |
838 | 0 | tmp2 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
839 | 0 | tmp12 = MULTIPLY(tmp2, FIX(0.707106781)); /* c2 */ |
840 | 0 | tmp10 = tmp0 + tmp12; |
841 | 0 | tmp2 = tmp0 - tmp12 - tmp12; |
842 | | |
843 | | /* Odd part */ |
844 | |
|
845 | 0 | tmp12 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
846 | 0 | tmp0 = MULTIPLY(tmp12, FIX(1.224744871)); /* c1 */ |
847 | | |
848 | | /* Final output stage */ |
849 | |
|
850 | 0 | wsptr[3 * 0] = (int)RIGHT_SHIFT(tmp10 + tmp0, CONST_BITS - PASS1_BITS); |
851 | 0 | wsptr[3 * 2] = (int)RIGHT_SHIFT(tmp10 - tmp0, CONST_BITS - PASS1_BITS); |
852 | 0 | wsptr[3 * 1] = (int)RIGHT_SHIFT(tmp2, CONST_BITS - PASS1_BITS); |
853 | 0 | } |
854 | | |
855 | | /* Pass 2: process 3 rows from work array, store into output array. */ |
856 | |
|
857 | 0 | wsptr = workspace; |
858 | 0 | for (ctr = 0; ctr < 3; ctr++) { |
859 | 0 | outptr = output_buf[ctr] + output_col; |
860 | | |
861 | | /* Even part */ |
862 | | |
863 | | /* Add fudge factor here for final descale. */ |
864 | 0 | tmp0 = (JLONG)wsptr[0] + (ONE << (PASS1_BITS + 2)); |
865 | 0 | tmp0 = LEFT_SHIFT(tmp0, CONST_BITS); |
866 | 0 | tmp2 = (JLONG)wsptr[2]; |
867 | 0 | tmp12 = MULTIPLY(tmp2, FIX(0.707106781)); /* c2 */ |
868 | 0 | tmp10 = tmp0 + tmp12; |
869 | 0 | tmp2 = tmp0 - tmp12 - tmp12; |
870 | | |
871 | | /* Odd part */ |
872 | |
|
873 | 0 | tmp12 = (JLONG)wsptr[1]; |
874 | 0 | tmp0 = MULTIPLY(tmp12, FIX(1.224744871)); /* c1 */ |
875 | | |
876 | | /* Final output stage */ |
877 | |
|
878 | 0 | outptr[0] = range_limit[(int)RIGHT_SHIFT(tmp10 + tmp0, |
879 | 0 | CONST_BITS + PASS1_BITS + 3) & |
880 | 0 | RANGE_MASK]; |
881 | 0 | outptr[2] = range_limit[(int)RIGHT_SHIFT(tmp10 - tmp0, |
882 | 0 | CONST_BITS + PASS1_BITS + 3) & |
883 | 0 | RANGE_MASK]; |
884 | 0 | outptr[1] = range_limit[(int)RIGHT_SHIFT(tmp2, |
885 | 0 | CONST_BITS + PASS1_BITS + 3) & |
886 | 0 | RANGE_MASK]; |
887 | |
|
888 | 0 | wsptr += 3; /* advance pointer to next row */ |
889 | 0 | } |
890 | 0 | } |
891 | | |
892 | | |
893 | | /* |
894 | | * Perform dequantization and inverse DCT on one block of coefficients, |
895 | | * producing a 9x9 output block. |
896 | | * |
897 | | * Optimized algorithm with 10 multiplications in the 1-D kernel. |
898 | | * cK represents sqrt(2) * cos(K*pi/18). |
899 | | */ |
900 | | |
901 | | GLOBAL(void) |
902 | | jpeg_idct_9x9(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
903 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
904 | | JDIMENSION output_col) |
905 | 0 | { |
906 | 0 | JLONG tmp0, tmp1, tmp2, tmp3, tmp10, tmp11, tmp12, tmp13, tmp14; |
907 | 0 | JLONG z1, z2, z3, z4; |
908 | 0 | JCOEFPTR inptr; |
909 | 0 | ISLOW_MULT_TYPE *quantptr; |
910 | 0 | int *wsptr; |
911 | 0 | JSAMPROW outptr; |
912 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
913 | 0 | int ctr; |
914 | 0 | int workspace[8 * 9]; /* buffers data between passes */ |
915 | | SHIFT_TEMPS |
916 | | |
917 | | /* Pass 1: process columns from input, store into work array. */ |
918 | |
|
919 | 0 | inptr = coef_block; |
920 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
921 | 0 | wsptr = workspace; |
922 | 0 | for (ctr = 0; ctr < 8; ctr++, inptr++, quantptr++, wsptr++) { |
923 | | /* Even part */ |
924 | |
|
925 | 0 | tmp0 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
926 | 0 | tmp0 = LEFT_SHIFT(tmp0, CONST_BITS); |
927 | | /* Add fudge factor here for final descale. */ |
928 | 0 | tmp0 += ONE << (CONST_BITS - PASS1_BITS - 1); |
929 | |
|
930 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
931 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 4], quantptr[DCTSIZE * 4]); |
932 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 6], quantptr[DCTSIZE * 6]); |
933 | |
|
934 | 0 | tmp3 = MULTIPLY(z3, FIX(0.707106781)); /* c6 */ |
935 | 0 | tmp1 = tmp0 + tmp3; |
936 | 0 | tmp2 = tmp0 - tmp3 - tmp3; |
937 | |
|
938 | 0 | tmp0 = MULTIPLY(z1 - z2, FIX(0.707106781)); /* c6 */ |
939 | 0 | tmp11 = tmp2 + tmp0; |
940 | 0 | tmp14 = tmp2 - tmp0 - tmp0; |
941 | |
|
942 | 0 | tmp0 = MULTIPLY(z1 + z2, FIX(1.328926049)); /* c2 */ |
943 | 0 | tmp2 = MULTIPLY(z1, FIX(1.083350441)); /* c4 */ |
944 | 0 | tmp3 = MULTIPLY(z2, FIX(0.245575608)); /* c8 */ |
945 | |
|
946 | 0 | tmp10 = tmp1 + tmp0 - tmp3; |
947 | 0 | tmp12 = tmp1 - tmp0 + tmp2; |
948 | 0 | tmp13 = tmp1 - tmp2 + tmp3; |
949 | | |
950 | | /* Odd part */ |
951 | |
|
952 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
953 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 3], quantptr[DCTSIZE * 3]); |
954 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 5], quantptr[DCTSIZE * 5]); |
955 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 7], quantptr[DCTSIZE * 7]); |
956 | |
|
957 | 0 | z2 = MULTIPLY(z2, -FIX(1.224744871)); /* -c3 */ |
958 | |
|
959 | 0 | tmp2 = MULTIPLY(z1 + z3, FIX(0.909038955)); /* c5 */ |
960 | 0 | tmp3 = MULTIPLY(z1 + z4, FIX(0.483689525)); /* c7 */ |
961 | 0 | tmp0 = tmp2 + tmp3 - z2; |
962 | 0 | tmp1 = MULTIPLY(z3 - z4, FIX(1.392728481)); /* c1 */ |
963 | 0 | tmp2 += z2 - tmp1; |
964 | 0 | tmp3 += z2 + tmp1; |
965 | 0 | tmp1 = MULTIPLY(z1 - z3 - z4, FIX(1.224744871)); /* c3 */ |
966 | | |
967 | | /* Final output stage */ |
968 | |
|
969 | 0 | wsptr[8 * 0] = (int)RIGHT_SHIFT(tmp10 + tmp0, CONST_BITS - PASS1_BITS); |
970 | 0 | wsptr[8 * 8] = (int)RIGHT_SHIFT(tmp10 - tmp0, CONST_BITS - PASS1_BITS); |
971 | 0 | wsptr[8 * 1] = (int)RIGHT_SHIFT(tmp11 + tmp1, CONST_BITS - PASS1_BITS); |
972 | 0 | wsptr[8 * 7] = (int)RIGHT_SHIFT(tmp11 - tmp1, CONST_BITS - PASS1_BITS); |
973 | 0 | wsptr[8 * 2] = (int)RIGHT_SHIFT(tmp12 + tmp2, CONST_BITS - PASS1_BITS); |
974 | 0 | wsptr[8 * 6] = (int)RIGHT_SHIFT(tmp12 - tmp2, CONST_BITS - PASS1_BITS); |
975 | 0 | wsptr[8 * 3] = (int)RIGHT_SHIFT(tmp13 + tmp3, CONST_BITS - PASS1_BITS); |
976 | 0 | wsptr[8 * 5] = (int)RIGHT_SHIFT(tmp13 - tmp3, CONST_BITS - PASS1_BITS); |
977 | 0 | wsptr[8 * 4] = (int)RIGHT_SHIFT(tmp14, CONST_BITS - PASS1_BITS); |
978 | 0 | } |
979 | | |
980 | | /* Pass 2: process 9 rows from work array, store into output array. */ |
981 | |
|
982 | 0 | wsptr = workspace; |
983 | 0 | for (ctr = 0; ctr < 9; ctr++) { |
984 | 0 | outptr = output_buf[ctr] + output_col; |
985 | | |
986 | | /* Even part */ |
987 | | |
988 | | /* Add fudge factor here for final descale. */ |
989 | 0 | tmp0 = (JLONG)wsptr[0] + (ONE << (PASS1_BITS + 2)); |
990 | 0 | tmp0 = LEFT_SHIFT(tmp0, CONST_BITS); |
991 | |
|
992 | 0 | z1 = (JLONG)wsptr[2]; |
993 | 0 | z2 = (JLONG)wsptr[4]; |
994 | 0 | z3 = (JLONG)wsptr[6]; |
995 | |
|
996 | 0 | tmp3 = MULTIPLY(z3, FIX(0.707106781)); /* c6 */ |
997 | 0 | tmp1 = tmp0 + tmp3; |
998 | 0 | tmp2 = tmp0 - tmp3 - tmp3; |
999 | |
|
1000 | 0 | tmp0 = MULTIPLY(z1 - z2, FIX(0.707106781)); /* c6 */ |
1001 | 0 | tmp11 = tmp2 + tmp0; |
1002 | 0 | tmp14 = tmp2 - tmp0 - tmp0; |
1003 | |
|
1004 | 0 | tmp0 = MULTIPLY(z1 + z2, FIX(1.328926049)); /* c2 */ |
1005 | 0 | tmp2 = MULTIPLY(z1, FIX(1.083350441)); /* c4 */ |
1006 | 0 | tmp3 = MULTIPLY(z2, FIX(0.245575608)); /* c8 */ |
1007 | |
|
1008 | 0 | tmp10 = tmp1 + tmp0 - tmp3; |
1009 | 0 | tmp12 = tmp1 - tmp0 + tmp2; |
1010 | 0 | tmp13 = tmp1 - tmp2 + tmp3; |
1011 | | |
1012 | | /* Odd part */ |
1013 | |
|
1014 | 0 | z1 = (JLONG)wsptr[1]; |
1015 | 0 | z2 = (JLONG)wsptr[3]; |
1016 | 0 | z3 = (JLONG)wsptr[5]; |
1017 | 0 | z4 = (JLONG)wsptr[7]; |
1018 | |
|
1019 | 0 | z2 = MULTIPLY(z2, -FIX(1.224744871)); /* -c3 */ |
1020 | |
|
1021 | 0 | tmp2 = MULTIPLY(z1 + z3, FIX(0.909038955)); /* c5 */ |
1022 | 0 | tmp3 = MULTIPLY(z1 + z4, FIX(0.483689525)); /* c7 */ |
1023 | 0 | tmp0 = tmp2 + tmp3 - z2; |
1024 | 0 | tmp1 = MULTIPLY(z3 - z4, FIX(1.392728481)); /* c1 */ |
1025 | 0 | tmp2 += z2 - tmp1; |
1026 | 0 | tmp3 += z2 + tmp1; |
1027 | 0 | tmp1 = MULTIPLY(z1 - z3 - z4, FIX(1.224744871)); /* c3 */ |
1028 | | |
1029 | | /* Final output stage */ |
1030 | |
|
1031 | 0 | outptr[0] = range_limit[(int)RIGHT_SHIFT(tmp10 + tmp0, |
1032 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1033 | 0 | RANGE_MASK]; |
1034 | 0 | outptr[8] = range_limit[(int)RIGHT_SHIFT(tmp10 - tmp0, |
1035 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1036 | 0 | RANGE_MASK]; |
1037 | 0 | outptr[1] = range_limit[(int)RIGHT_SHIFT(tmp11 + tmp1, |
1038 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1039 | 0 | RANGE_MASK]; |
1040 | 0 | outptr[7] = range_limit[(int)RIGHT_SHIFT(tmp11 - tmp1, |
1041 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1042 | 0 | RANGE_MASK]; |
1043 | 0 | outptr[2] = range_limit[(int)RIGHT_SHIFT(tmp12 + tmp2, |
1044 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1045 | 0 | RANGE_MASK]; |
1046 | 0 | outptr[6] = range_limit[(int)RIGHT_SHIFT(tmp12 - tmp2, |
1047 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1048 | 0 | RANGE_MASK]; |
1049 | 0 | outptr[3] = range_limit[(int)RIGHT_SHIFT(tmp13 + tmp3, |
1050 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1051 | 0 | RANGE_MASK]; |
1052 | 0 | outptr[5] = range_limit[(int)RIGHT_SHIFT(tmp13 - tmp3, |
1053 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1054 | 0 | RANGE_MASK]; |
1055 | 0 | outptr[4] = range_limit[(int)RIGHT_SHIFT(tmp14, |
1056 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1057 | 0 | RANGE_MASK]; |
1058 | |
|
1059 | 0 | wsptr += 8; /* advance pointer to next row */ |
1060 | 0 | } |
1061 | 0 | } |
1062 | | |
1063 | | |
1064 | | /* |
1065 | | * Perform dequantization and inverse DCT on one block of coefficients, |
1066 | | * producing a 10x10 output block. |
1067 | | * |
1068 | | * Optimized algorithm with 12 multiplications in the 1-D kernel. |
1069 | | * cK represents sqrt(2) * cos(K*pi/20). |
1070 | | */ |
1071 | | |
1072 | | GLOBAL(void) |
1073 | | jpeg_idct_10x10(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
1074 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
1075 | | JDIMENSION output_col) |
1076 | 0 | { |
1077 | 0 | JLONG tmp10, tmp11, tmp12, tmp13, tmp14; |
1078 | 0 | JLONG tmp20, tmp21, tmp22, tmp23, tmp24; |
1079 | 0 | JLONG z1, z2, z3, z4, z5; |
1080 | 0 | JCOEFPTR inptr; |
1081 | 0 | ISLOW_MULT_TYPE *quantptr; |
1082 | 0 | int *wsptr; |
1083 | 0 | JSAMPROW outptr; |
1084 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
1085 | 0 | int ctr; |
1086 | 0 | int workspace[8 * 10]; /* buffers data between passes */ |
1087 | | SHIFT_TEMPS |
1088 | | |
1089 | | /* Pass 1: process columns from input, store into work array. */ |
1090 | |
|
1091 | 0 | inptr = coef_block; |
1092 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
1093 | 0 | wsptr = workspace; |
1094 | 0 | for (ctr = 0; ctr < 8; ctr++, inptr++, quantptr++, wsptr++) { |
1095 | | /* Even part */ |
1096 | |
|
1097 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
1098 | 0 | z3 = LEFT_SHIFT(z3, CONST_BITS); |
1099 | | /* Add fudge factor here for final descale. */ |
1100 | 0 | z3 += ONE << (CONST_BITS - PASS1_BITS - 1); |
1101 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 4], quantptr[DCTSIZE * 4]); |
1102 | 0 | z1 = MULTIPLY(z4, FIX(1.144122806)); /* c4 */ |
1103 | 0 | z2 = MULTIPLY(z4, FIX(0.437016024)); /* c8 */ |
1104 | 0 | tmp10 = z3 + z1; |
1105 | 0 | tmp11 = z3 - z2; |
1106 | |
|
1107 | 0 | tmp22 = RIGHT_SHIFT(z3 - LEFT_SHIFT(z1 - z2, 1), |
1108 | 0 | CONST_BITS - PASS1_BITS); /* c0 = (c4-c8)*2 */ |
1109 | |
|
1110 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
1111 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 6], quantptr[DCTSIZE * 6]); |
1112 | |
|
1113 | 0 | z1 = MULTIPLY(z2 + z3, FIX(0.831253876)); /* c6 */ |
1114 | 0 | tmp12 = z1 + MULTIPLY(z2, FIX(0.513743148)); /* c2-c6 */ |
1115 | 0 | tmp13 = z1 - MULTIPLY(z3, FIX(2.176250899)); /* c2+c6 */ |
1116 | |
|
1117 | 0 | tmp20 = tmp10 + tmp12; |
1118 | 0 | tmp24 = tmp10 - tmp12; |
1119 | 0 | tmp21 = tmp11 + tmp13; |
1120 | 0 | tmp23 = tmp11 - tmp13; |
1121 | | |
1122 | | /* Odd part */ |
1123 | |
|
1124 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
1125 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 3], quantptr[DCTSIZE * 3]); |
1126 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 5], quantptr[DCTSIZE * 5]); |
1127 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 7], quantptr[DCTSIZE * 7]); |
1128 | |
|
1129 | 0 | tmp11 = z2 + z4; |
1130 | 0 | tmp13 = z2 - z4; |
1131 | |
|
1132 | 0 | tmp12 = MULTIPLY(tmp13, FIX(0.309016994)); /* (c3-c7)/2 */ |
1133 | 0 | z5 = LEFT_SHIFT(z3, CONST_BITS); |
1134 | |
|
1135 | 0 | z2 = MULTIPLY(tmp11, FIX(0.951056516)); /* (c3+c7)/2 */ |
1136 | 0 | z4 = z5 + tmp12; |
1137 | |
|
1138 | 0 | tmp10 = MULTIPLY(z1, FIX(1.396802247)) + z2 + z4; /* c1 */ |
1139 | 0 | tmp14 = MULTIPLY(z1, FIX(0.221231742)) - z2 + z4; /* c9 */ |
1140 | |
|
1141 | 0 | z2 = MULTIPLY(tmp11, FIX(0.587785252)); /* (c1-c9)/2 */ |
1142 | 0 | z4 = z5 - tmp12 - LEFT_SHIFT(tmp13, CONST_BITS - 1); |
1143 | |
|
1144 | 0 | tmp12 = LEFT_SHIFT(z1 - tmp13 - z3, PASS1_BITS); |
1145 | |
|
1146 | 0 | tmp11 = MULTIPLY(z1, FIX(1.260073511)) - z2 - z4; /* c3 */ |
1147 | 0 | tmp13 = MULTIPLY(z1, FIX(0.642039522)) - z2 + z4; /* c7 */ |
1148 | | |
1149 | | /* Final output stage */ |
1150 | |
|
1151 | 0 | wsptr[8 * 0] = (int)RIGHT_SHIFT(tmp20 + tmp10, CONST_BITS - PASS1_BITS); |
1152 | 0 | wsptr[8 * 9] = (int)RIGHT_SHIFT(tmp20 - tmp10, CONST_BITS - PASS1_BITS); |
1153 | 0 | wsptr[8 * 1] = (int)RIGHT_SHIFT(tmp21 + tmp11, CONST_BITS - PASS1_BITS); |
1154 | 0 | wsptr[8 * 8] = (int)RIGHT_SHIFT(tmp21 - tmp11, CONST_BITS - PASS1_BITS); |
1155 | 0 | wsptr[8 * 2] = (int)(tmp22 + tmp12); |
1156 | 0 | wsptr[8 * 7] = (int)(tmp22 - tmp12); |
1157 | 0 | wsptr[8 * 3] = (int)RIGHT_SHIFT(tmp23 + tmp13, CONST_BITS - PASS1_BITS); |
1158 | 0 | wsptr[8 * 6] = (int)RIGHT_SHIFT(tmp23 - tmp13, CONST_BITS - PASS1_BITS); |
1159 | 0 | wsptr[8 * 4] = (int)RIGHT_SHIFT(tmp24 + tmp14, CONST_BITS - PASS1_BITS); |
1160 | 0 | wsptr[8 * 5] = (int)RIGHT_SHIFT(tmp24 - tmp14, CONST_BITS - PASS1_BITS); |
1161 | 0 | } |
1162 | | |
1163 | | /* Pass 2: process 10 rows from work array, store into output array. */ |
1164 | |
|
1165 | 0 | wsptr = workspace; |
1166 | 0 | for (ctr = 0; ctr < 10; ctr++) { |
1167 | 0 | outptr = output_buf[ctr] + output_col; |
1168 | | |
1169 | | /* Even part */ |
1170 | | |
1171 | | /* Add fudge factor here for final descale. */ |
1172 | 0 | z3 = (JLONG)wsptr[0] + (ONE << (PASS1_BITS + 2)); |
1173 | 0 | z3 = LEFT_SHIFT(z3, CONST_BITS); |
1174 | 0 | z4 = (JLONG)wsptr[4]; |
1175 | 0 | z1 = MULTIPLY(z4, FIX(1.144122806)); /* c4 */ |
1176 | 0 | z2 = MULTIPLY(z4, FIX(0.437016024)); /* c8 */ |
1177 | 0 | tmp10 = z3 + z1; |
1178 | 0 | tmp11 = z3 - z2; |
1179 | |
|
1180 | 0 | tmp22 = z3 - LEFT_SHIFT(z1 - z2, 1); /* c0 = (c4-c8)*2 */ |
1181 | |
|
1182 | 0 | z2 = (JLONG)wsptr[2]; |
1183 | 0 | z3 = (JLONG)wsptr[6]; |
1184 | |
|
1185 | 0 | z1 = MULTIPLY(z2 + z3, FIX(0.831253876)); /* c6 */ |
1186 | 0 | tmp12 = z1 + MULTIPLY(z2, FIX(0.513743148)); /* c2-c6 */ |
1187 | 0 | tmp13 = z1 - MULTIPLY(z3, FIX(2.176250899)); /* c2+c6 */ |
1188 | |
|
1189 | 0 | tmp20 = tmp10 + tmp12; |
1190 | 0 | tmp24 = tmp10 - tmp12; |
1191 | 0 | tmp21 = tmp11 + tmp13; |
1192 | 0 | tmp23 = tmp11 - tmp13; |
1193 | | |
1194 | | /* Odd part */ |
1195 | |
|
1196 | 0 | z1 = (JLONG)wsptr[1]; |
1197 | 0 | z2 = (JLONG)wsptr[3]; |
1198 | 0 | z3 = (JLONG)wsptr[5]; |
1199 | 0 | z3 = LEFT_SHIFT(z3, CONST_BITS); |
1200 | 0 | z4 = (JLONG)wsptr[7]; |
1201 | |
|
1202 | 0 | tmp11 = z2 + z4; |
1203 | 0 | tmp13 = z2 - z4; |
1204 | |
|
1205 | 0 | tmp12 = MULTIPLY(tmp13, FIX(0.309016994)); /* (c3-c7)/2 */ |
1206 | |
|
1207 | 0 | z2 = MULTIPLY(tmp11, FIX(0.951056516)); /* (c3+c7)/2 */ |
1208 | 0 | z4 = z3 + tmp12; |
1209 | |
|
1210 | 0 | tmp10 = MULTIPLY(z1, FIX(1.396802247)) + z2 + z4; /* c1 */ |
1211 | 0 | tmp14 = MULTIPLY(z1, FIX(0.221231742)) - z2 + z4; /* c9 */ |
1212 | |
|
1213 | 0 | z2 = MULTIPLY(tmp11, FIX(0.587785252)); /* (c1-c9)/2 */ |
1214 | 0 | z4 = z3 - tmp12 - LEFT_SHIFT(tmp13, CONST_BITS - 1); |
1215 | |
|
1216 | 0 | tmp12 = LEFT_SHIFT(z1 - tmp13, CONST_BITS) - z3; |
1217 | |
|
1218 | 0 | tmp11 = MULTIPLY(z1, FIX(1.260073511)) - z2 - z4; /* c3 */ |
1219 | 0 | tmp13 = MULTIPLY(z1, FIX(0.642039522)) - z2 + z4; /* c7 */ |
1220 | | |
1221 | | /* Final output stage */ |
1222 | |
|
1223 | 0 | outptr[0] = range_limit[(int)RIGHT_SHIFT(tmp20 + tmp10, |
1224 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1225 | 0 | RANGE_MASK]; |
1226 | 0 | outptr[9] = range_limit[(int)RIGHT_SHIFT(tmp20 - tmp10, |
1227 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1228 | 0 | RANGE_MASK]; |
1229 | 0 | outptr[1] = range_limit[(int)RIGHT_SHIFT(tmp21 + tmp11, |
1230 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1231 | 0 | RANGE_MASK]; |
1232 | 0 | outptr[8] = range_limit[(int)RIGHT_SHIFT(tmp21 - tmp11, |
1233 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1234 | 0 | RANGE_MASK]; |
1235 | 0 | outptr[2] = range_limit[(int)RIGHT_SHIFT(tmp22 + tmp12, |
1236 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1237 | 0 | RANGE_MASK]; |
1238 | 0 | outptr[7] = range_limit[(int)RIGHT_SHIFT(tmp22 - tmp12, |
1239 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1240 | 0 | RANGE_MASK]; |
1241 | 0 | outptr[3] = range_limit[(int)RIGHT_SHIFT(tmp23 + tmp13, |
1242 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1243 | 0 | RANGE_MASK]; |
1244 | 0 | outptr[6] = range_limit[(int)RIGHT_SHIFT(tmp23 - tmp13, |
1245 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1246 | 0 | RANGE_MASK]; |
1247 | 0 | outptr[4] = range_limit[(int)RIGHT_SHIFT(tmp24 + tmp14, |
1248 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1249 | 0 | RANGE_MASK]; |
1250 | 0 | outptr[5] = range_limit[(int)RIGHT_SHIFT(tmp24 - tmp14, |
1251 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1252 | 0 | RANGE_MASK]; |
1253 | |
|
1254 | 0 | wsptr += 8; /* advance pointer to next row */ |
1255 | 0 | } |
1256 | 0 | } |
1257 | | |
1258 | | |
1259 | | /* |
1260 | | * Perform dequantization and inverse DCT on one block of coefficients, |
1261 | | * producing an 11x11 output block. |
1262 | | * |
1263 | | * Optimized algorithm with 24 multiplications in the 1-D kernel. |
1264 | | * cK represents sqrt(2) * cos(K*pi/22). |
1265 | | */ |
1266 | | |
1267 | | GLOBAL(void) |
1268 | | jpeg_idct_11x11(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
1269 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
1270 | | JDIMENSION output_col) |
1271 | 0 | { |
1272 | 0 | JLONG tmp10, tmp11, tmp12, tmp13, tmp14; |
1273 | 0 | JLONG tmp20, tmp21, tmp22, tmp23, tmp24, tmp25; |
1274 | 0 | JLONG z1, z2, z3, z4; |
1275 | 0 | JCOEFPTR inptr; |
1276 | 0 | ISLOW_MULT_TYPE *quantptr; |
1277 | 0 | int *wsptr; |
1278 | 0 | JSAMPROW outptr; |
1279 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
1280 | 0 | int ctr; |
1281 | 0 | int workspace[8 * 11]; /* buffers data between passes */ |
1282 | | SHIFT_TEMPS |
1283 | | |
1284 | | /* Pass 1: process columns from input, store into work array. */ |
1285 | |
|
1286 | 0 | inptr = coef_block; |
1287 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
1288 | 0 | wsptr = workspace; |
1289 | 0 | for (ctr = 0; ctr < 8; ctr++, inptr++, quantptr++, wsptr++) { |
1290 | | /* Even part */ |
1291 | |
|
1292 | 0 | tmp10 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
1293 | 0 | tmp10 = LEFT_SHIFT(tmp10, CONST_BITS); |
1294 | | /* Add fudge factor here for final descale. */ |
1295 | 0 | tmp10 += ONE << (CONST_BITS - PASS1_BITS - 1); |
1296 | |
|
1297 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
1298 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 4], quantptr[DCTSIZE * 4]); |
1299 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 6], quantptr[DCTSIZE * 6]); |
1300 | |
|
1301 | 0 | tmp20 = MULTIPLY(z2 - z3, FIX(2.546640132)); /* c2+c4 */ |
1302 | 0 | tmp23 = MULTIPLY(z2 - z1, FIX(0.430815045)); /* c2-c6 */ |
1303 | 0 | z4 = z1 + z3; |
1304 | 0 | tmp24 = MULTIPLY(z4, -FIX(1.155664402)); /* -(c2-c10) */ |
1305 | 0 | z4 -= z2; |
1306 | 0 | tmp25 = tmp10 + MULTIPLY(z4, FIX(1.356927976)); /* c2 */ |
1307 | 0 | tmp21 = tmp20 + tmp23 + tmp25 - |
1308 | 0 | MULTIPLY(z2, FIX(1.821790775)); /* c2+c4+c10-c6 */ |
1309 | 0 | tmp20 += tmp25 + MULTIPLY(z3, FIX(2.115825087)); /* c4+c6 */ |
1310 | 0 | tmp23 += tmp25 - MULTIPLY(z1, FIX(1.513598477)); /* c6+c8 */ |
1311 | 0 | tmp24 += tmp25; |
1312 | 0 | tmp22 = tmp24 - MULTIPLY(z3, FIX(0.788749120)); /* c8+c10 */ |
1313 | 0 | tmp24 += MULTIPLY(z2, FIX(1.944413522)) - /* c2+c8 */ |
1314 | 0 | MULTIPLY(z1, FIX(1.390975730)); /* c4+c10 */ |
1315 | 0 | tmp25 = tmp10 - MULTIPLY(z4, FIX(1.414213562)); /* c0 */ |
1316 | | |
1317 | | /* Odd part */ |
1318 | |
|
1319 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
1320 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 3], quantptr[DCTSIZE * 3]); |
1321 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 5], quantptr[DCTSIZE * 5]); |
1322 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 7], quantptr[DCTSIZE * 7]); |
1323 | |
|
1324 | 0 | tmp11 = z1 + z2; |
1325 | 0 | tmp14 = MULTIPLY(tmp11 + z3 + z4, FIX(0.398430003)); /* c9 */ |
1326 | 0 | tmp11 = MULTIPLY(tmp11, FIX(0.887983902)); /* c3-c9 */ |
1327 | 0 | tmp12 = MULTIPLY(z1 + z3, FIX(0.670361295)); /* c5-c9 */ |
1328 | 0 | tmp13 = tmp14 + MULTIPLY(z1 + z4, FIX(0.366151574)); /* c7-c9 */ |
1329 | 0 | tmp10 = tmp11 + tmp12 + tmp13 - |
1330 | 0 | MULTIPLY(z1, FIX(0.923107866)); /* c7+c5+c3-c1-2*c9 */ |
1331 | 0 | z1 = tmp14 - MULTIPLY(z2 + z3, FIX(1.163011579)); /* c7+c9 */ |
1332 | 0 | tmp11 += z1 + MULTIPLY(z2, FIX(2.073276588)); /* c1+c7+3*c9-c3 */ |
1333 | 0 | tmp12 += z1 - MULTIPLY(z3, FIX(1.192193623)); /* c3+c5-c7-c9 */ |
1334 | 0 | z1 = MULTIPLY(z2 + z4, -FIX(1.798248910)); /* -(c1+c9) */ |
1335 | 0 | tmp11 += z1; |
1336 | 0 | tmp13 += z1 + MULTIPLY(z4, FIX(2.102458632)); /* c1+c5+c9-c7 */ |
1337 | 0 | tmp14 += MULTIPLY(z2, -FIX(1.467221301)) + /* -(c5+c9) */ |
1338 | 0 | MULTIPLY(z3, FIX(1.001388905)) - /* c1-c9 */ |
1339 | 0 | MULTIPLY(z4, FIX(1.684843907)); /* c3+c9 */ |
1340 | | |
1341 | | /* Final output stage */ |
1342 | |
|
1343 | 0 | wsptr[8 * 0] = (int)RIGHT_SHIFT(tmp20 + tmp10, CONST_BITS - PASS1_BITS); |
1344 | 0 | wsptr[8 * 10] = (int)RIGHT_SHIFT(tmp20 - tmp10, CONST_BITS - PASS1_BITS); |
1345 | 0 | wsptr[8 * 1] = (int)RIGHT_SHIFT(tmp21 + tmp11, CONST_BITS - PASS1_BITS); |
1346 | 0 | wsptr[8 * 9] = (int)RIGHT_SHIFT(tmp21 - tmp11, CONST_BITS - PASS1_BITS); |
1347 | 0 | wsptr[8 * 2] = (int)RIGHT_SHIFT(tmp22 + tmp12, CONST_BITS - PASS1_BITS); |
1348 | 0 | wsptr[8 * 8] = (int)RIGHT_SHIFT(tmp22 - tmp12, CONST_BITS - PASS1_BITS); |
1349 | 0 | wsptr[8 * 3] = (int)RIGHT_SHIFT(tmp23 + tmp13, CONST_BITS - PASS1_BITS); |
1350 | 0 | wsptr[8 * 7] = (int)RIGHT_SHIFT(tmp23 - tmp13, CONST_BITS - PASS1_BITS); |
1351 | 0 | wsptr[8 * 4] = (int)RIGHT_SHIFT(tmp24 + tmp14, CONST_BITS - PASS1_BITS); |
1352 | 0 | wsptr[8 * 6] = (int)RIGHT_SHIFT(tmp24 - tmp14, CONST_BITS - PASS1_BITS); |
1353 | 0 | wsptr[8 * 5] = (int)RIGHT_SHIFT(tmp25, CONST_BITS - PASS1_BITS); |
1354 | 0 | } |
1355 | | |
1356 | | /* Pass 2: process 11 rows from work array, store into output array. */ |
1357 | |
|
1358 | 0 | wsptr = workspace; |
1359 | 0 | for (ctr = 0; ctr < 11; ctr++) { |
1360 | 0 | outptr = output_buf[ctr] + output_col; |
1361 | | |
1362 | | /* Even part */ |
1363 | | |
1364 | | /* Add fudge factor here for final descale. */ |
1365 | 0 | tmp10 = (JLONG)wsptr[0] + (ONE << (PASS1_BITS + 2)); |
1366 | 0 | tmp10 = LEFT_SHIFT(tmp10, CONST_BITS); |
1367 | |
|
1368 | 0 | z1 = (JLONG)wsptr[2]; |
1369 | 0 | z2 = (JLONG)wsptr[4]; |
1370 | 0 | z3 = (JLONG)wsptr[6]; |
1371 | |
|
1372 | 0 | tmp20 = MULTIPLY(z2 - z3, FIX(2.546640132)); /* c2+c4 */ |
1373 | 0 | tmp23 = MULTIPLY(z2 - z1, FIX(0.430815045)); /* c2-c6 */ |
1374 | 0 | z4 = z1 + z3; |
1375 | 0 | tmp24 = MULTIPLY(z4, -FIX(1.155664402)); /* -(c2-c10) */ |
1376 | 0 | z4 -= z2; |
1377 | 0 | tmp25 = tmp10 + MULTIPLY(z4, FIX(1.356927976)); /* c2 */ |
1378 | 0 | tmp21 = tmp20 + tmp23 + tmp25 - |
1379 | 0 | MULTIPLY(z2, FIX(1.821790775)); /* c2+c4+c10-c6 */ |
1380 | 0 | tmp20 += tmp25 + MULTIPLY(z3, FIX(2.115825087)); /* c4+c6 */ |
1381 | 0 | tmp23 += tmp25 - MULTIPLY(z1, FIX(1.513598477)); /* c6+c8 */ |
1382 | 0 | tmp24 += tmp25; |
1383 | 0 | tmp22 = tmp24 - MULTIPLY(z3, FIX(0.788749120)); /* c8+c10 */ |
1384 | 0 | tmp24 += MULTIPLY(z2, FIX(1.944413522)) - /* c2+c8 */ |
1385 | 0 | MULTIPLY(z1, FIX(1.390975730)); /* c4+c10 */ |
1386 | 0 | tmp25 = tmp10 - MULTIPLY(z4, FIX(1.414213562)); /* c0 */ |
1387 | | |
1388 | | /* Odd part */ |
1389 | |
|
1390 | 0 | z1 = (JLONG)wsptr[1]; |
1391 | 0 | z2 = (JLONG)wsptr[3]; |
1392 | 0 | z3 = (JLONG)wsptr[5]; |
1393 | 0 | z4 = (JLONG)wsptr[7]; |
1394 | |
|
1395 | 0 | tmp11 = z1 + z2; |
1396 | 0 | tmp14 = MULTIPLY(tmp11 + z3 + z4, FIX(0.398430003)); /* c9 */ |
1397 | 0 | tmp11 = MULTIPLY(tmp11, FIX(0.887983902)); /* c3-c9 */ |
1398 | 0 | tmp12 = MULTIPLY(z1 + z3, FIX(0.670361295)); /* c5-c9 */ |
1399 | 0 | tmp13 = tmp14 + MULTIPLY(z1 + z4, FIX(0.366151574)); /* c7-c9 */ |
1400 | 0 | tmp10 = tmp11 + tmp12 + tmp13 - |
1401 | 0 | MULTIPLY(z1, FIX(0.923107866)); /* c7+c5+c3-c1-2*c9 */ |
1402 | 0 | z1 = tmp14 - MULTIPLY(z2 + z3, FIX(1.163011579)); /* c7+c9 */ |
1403 | 0 | tmp11 += z1 + MULTIPLY(z2, FIX(2.073276588)); /* c1+c7+3*c9-c3 */ |
1404 | 0 | tmp12 += z1 - MULTIPLY(z3, FIX(1.192193623)); /* c3+c5-c7-c9 */ |
1405 | 0 | z1 = MULTIPLY(z2 + z4, -FIX(1.798248910)); /* -(c1+c9) */ |
1406 | 0 | tmp11 += z1; |
1407 | 0 | tmp13 += z1 + MULTIPLY(z4, FIX(2.102458632)); /* c1+c5+c9-c7 */ |
1408 | 0 | tmp14 += MULTIPLY(z2, -FIX(1.467221301)) + /* -(c5+c9) */ |
1409 | 0 | MULTIPLY(z3, FIX(1.001388905)) - /* c1-c9 */ |
1410 | 0 | MULTIPLY(z4, FIX(1.684843907)); /* c3+c9 */ |
1411 | | |
1412 | | /* Final output stage */ |
1413 | |
|
1414 | 0 | outptr[0] = range_limit[(int)RIGHT_SHIFT(tmp20 + tmp10, |
1415 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1416 | 0 | RANGE_MASK]; |
1417 | 0 | outptr[10] = range_limit[(int)RIGHT_SHIFT(tmp20 - tmp10, |
1418 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1419 | 0 | RANGE_MASK]; |
1420 | 0 | outptr[1] = range_limit[(int)RIGHT_SHIFT(tmp21 + tmp11, |
1421 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1422 | 0 | RANGE_MASK]; |
1423 | 0 | outptr[9] = range_limit[(int)RIGHT_SHIFT(tmp21 - tmp11, |
1424 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1425 | 0 | RANGE_MASK]; |
1426 | 0 | outptr[2] = range_limit[(int)RIGHT_SHIFT(tmp22 + tmp12, |
1427 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1428 | 0 | RANGE_MASK]; |
1429 | 0 | outptr[8] = range_limit[(int)RIGHT_SHIFT(tmp22 - tmp12, |
1430 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1431 | 0 | RANGE_MASK]; |
1432 | 0 | outptr[3] = range_limit[(int)RIGHT_SHIFT(tmp23 + tmp13, |
1433 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1434 | 0 | RANGE_MASK]; |
1435 | 0 | outptr[7] = range_limit[(int)RIGHT_SHIFT(tmp23 - tmp13, |
1436 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1437 | 0 | RANGE_MASK]; |
1438 | 0 | outptr[4] = range_limit[(int)RIGHT_SHIFT(tmp24 + tmp14, |
1439 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1440 | 0 | RANGE_MASK]; |
1441 | 0 | outptr[6] = range_limit[(int)RIGHT_SHIFT(tmp24 - tmp14, |
1442 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1443 | 0 | RANGE_MASK]; |
1444 | 0 | outptr[5] = range_limit[(int)RIGHT_SHIFT(tmp25, |
1445 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1446 | 0 | RANGE_MASK]; |
1447 | |
|
1448 | 0 | wsptr += 8; /* advance pointer to next row */ |
1449 | 0 | } |
1450 | 0 | } |
1451 | | |
1452 | | |
1453 | | /* |
1454 | | * Perform dequantization and inverse DCT on one block of coefficients, |
1455 | | * producing a 12x12 output block. |
1456 | | * |
1457 | | * Optimized algorithm with 15 multiplications in the 1-D kernel. |
1458 | | * cK represents sqrt(2) * cos(K*pi/24). |
1459 | | */ |
1460 | | |
1461 | | GLOBAL(void) |
1462 | | jpeg_idct_12x12(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
1463 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
1464 | | JDIMENSION output_col) |
1465 | 0 | { |
1466 | 0 | JLONG tmp10, tmp11, tmp12, tmp13, tmp14, tmp15; |
1467 | 0 | JLONG tmp20, tmp21, tmp22, tmp23, tmp24, tmp25; |
1468 | 0 | JLONG z1, z2, z3, z4; |
1469 | 0 | JCOEFPTR inptr; |
1470 | 0 | ISLOW_MULT_TYPE *quantptr; |
1471 | 0 | int *wsptr; |
1472 | 0 | JSAMPROW outptr; |
1473 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
1474 | 0 | int ctr; |
1475 | 0 | int workspace[8 * 12]; /* buffers data between passes */ |
1476 | | SHIFT_TEMPS |
1477 | | |
1478 | | /* Pass 1: process columns from input, store into work array. */ |
1479 | |
|
1480 | 0 | inptr = coef_block; |
1481 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
1482 | 0 | wsptr = workspace; |
1483 | 0 | for (ctr = 0; ctr < 8; ctr++, inptr++, quantptr++, wsptr++) { |
1484 | | /* Even part */ |
1485 | |
|
1486 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
1487 | 0 | z3 = LEFT_SHIFT(z3, CONST_BITS); |
1488 | | /* Add fudge factor here for final descale. */ |
1489 | 0 | z3 += ONE << (CONST_BITS - PASS1_BITS - 1); |
1490 | |
|
1491 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 4], quantptr[DCTSIZE * 4]); |
1492 | 0 | z4 = MULTIPLY(z4, FIX(1.224744871)); /* c4 */ |
1493 | |
|
1494 | 0 | tmp10 = z3 + z4; |
1495 | 0 | tmp11 = z3 - z4; |
1496 | |
|
1497 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
1498 | 0 | z4 = MULTIPLY(z1, FIX(1.366025404)); /* c2 */ |
1499 | 0 | z1 = LEFT_SHIFT(z1, CONST_BITS); |
1500 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 6], quantptr[DCTSIZE * 6]); |
1501 | 0 | z2 = LEFT_SHIFT(z2, CONST_BITS); |
1502 | |
|
1503 | 0 | tmp12 = z1 - z2; |
1504 | |
|
1505 | 0 | tmp21 = z3 + tmp12; |
1506 | 0 | tmp24 = z3 - tmp12; |
1507 | |
|
1508 | 0 | tmp12 = z4 + z2; |
1509 | |
|
1510 | 0 | tmp20 = tmp10 + tmp12; |
1511 | 0 | tmp25 = tmp10 - tmp12; |
1512 | |
|
1513 | 0 | tmp12 = z4 - z1 - z2; |
1514 | |
|
1515 | 0 | tmp22 = tmp11 + tmp12; |
1516 | 0 | tmp23 = tmp11 - tmp12; |
1517 | | |
1518 | | /* Odd part */ |
1519 | |
|
1520 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
1521 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 3], quantptr[DCTSIZE * 3]); |
1522 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 5], quantptr[DCTSIZE * 5]); |
1523 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 7], quantptr[DCTSIZE * 7]); |
1524 | |
|
1525 | 0 | tmp11 = MULTIPLY(z2, FIX(1.306562965)); /* c3 */ |
1526 | 0 | tmp14 = MULTIPLY(z2, -FIX_0_541196100); /* -c9 */ |
1527 | |
|
1528 | 0 | tmp10 = z1 + z3; |
1529 | 0 | tmp15 = MULTIPLY(tmp10 + z4, FIX(0.860918669)); /* c7 */ |
1530 | 0 | tmp12 = tmp15 + MULTIPLY(tmp10, FIX(0.261052384)); /* c5-c7 */ |
1531 | 0 | tmp10 = tmp12 + tmp11 + MULTIPLY(z1, FIX(0.280143716)); /* c1-c5 */ |
1532 | 0 | tmp13 = MULTIPLY(z3 + z4, -FIX(1.045510580)); /* -(c7+c11) */ |
1533 | 0 | tmp12 += tmp13 + tmp14 - MULTIPLY(z3, FIX(1.478575242)); /* c1+c5-c7-c11 */ |
1534 | 0 | tmp13 += tmp15 - tmp11 + MULTIPLY(z4, FIX(1.586706681)); /* c1+c11 */ |
1535 | 0 | tmp15 += tmp14 - MULTIPLY(z1, FIX(0.676326758)) - /* c7-c11 */ |
1536 | 0 | MULTIPLY(z4, FIX(1.982889723)); /* c5+c7 */ |
1537 | |
|
1538 | 0 | z1 -= z4; |
1539 | 0 | z2 -= z3; |
1540 | 0 | z3 = MULTIPLY(z1 + z2, FIX_0_541196100); /* c9 */ |
1541 | 0 | tmp11 = z3 + MULTIPLY(z1, FIX_0_765366865); /* c3-c9 */ |
1542 | 0 | tmp14 = z3 - MULTIPLY(z2, FIX_1_847759065); /* c3+c9 */ |
1543 | | |
1544 | | /* Final output stage */ |
1545 | |
|
1546 | 0 | wsptr[8 * 0] = (int)RIGHT_SHIFT(tmp20 + tmp10, CONST_BITS - PASS1_BITS); |
1547 | 0 | wsptr[8 * 11] = (int)RIGHT_SHIFT(tmp20 - tmp10, CONST_BITS - PASS1_BITS); |
1548 | 0 | wsptr[8 * 1] = (int)RIGHT_SHIFT(tmp21 + tmp11, CONST_BITS - PASS1_BITS); |
1549 | 0 | wsptr[8 * 10] = (int)RIGHT_SHIFT(tmp21 - tmp11, CONST_BITS - PASS1_BITS); |
1550 | 0 | wsptr[8 * 2] = (int)RIGHT_SHIFT(tmp22 + tmp12, CONST_BITS - PASS1_BITS); |
1551 | 0 | wsptr[8 * 9] = (int)RIGHT_SHIFT(tmp22 - tmp12, CONST_BITS - PASS1_BITS); |
1552 | 0 | wsptr[8 * 3] = (int)RIGHT_SHIFT(tmp23 + tmp13, CONST_BITS - PASS1_BITS); |
1553 | 0 | wsptr[8 * 8] = (int)RIGHT_SHIFT(tmp23 - tmp13, CONST_BITS - PASS1_BITS); |
1554 | 0 | wsptr[8 * 4] = (int)RIGHT_SHIFT(tmp24 + tmp14, CONST_BITS - PASS1_BITS); |
1555 | 0 | wsptr[8 * 7] = (int)RIGHT_SHIFT(tmp24 - tmp14, CONST_BITS - PASS1_BITS); |
1556 | 0 | wsptr[8 * 5] = (int)RIGHT_SHIFT(tmp25 + tmp15, CONST_BITS - PASS1_BITS); |
1557 | 0 | wsptr[8 * 6] = (int)RIGHT_SHIFT(tmp25 - tmp15, CONST_BITS - PASS1_BITS); |
1558 | 0 | } |
1559 | | |
1560 | | /* Pass 2: process 12 rows from work array, store into output array. */ |
1561 | |
|
1562 | 0 | wsptr = workspace; |
1563 | 0 | for (ctr = 0; ctr < 12; ctr++) { |
1564 | 0 | outptr = output_buf[ctr] + output_col; |
1565 | | |
1566 | | /* Even part */ |
1567 | | |
1568 | | /* Add fudge factor here for final descale. */ |
1569 | 0 | z3 = (JLONG)wsptr[0] + (ONE << (PASS1_BITS + 2)); |
1570 | 0 | z3 = LEFT_SHIFT(z3, CONST_BITS); |
1571 | |
|
1572 | 0 | z4 = (JLONG)wsptr[4]; |
1573 | 0 | z4 = MULTIPLY(z4, FIX(1.224744871)); /* c4 */ |
1574 | |
|
1575 | 0 | tmp10 = z3 + z4; |
1576 | 0 | tmp11 = z3 - z4; |
1577 | |
|
1578 | 0 | z1 = (JLONG)wsptr[2]; |
1579 | 0 | z4 = MULTIPLY(z1, FIX(1.366025404)); /* c2 */ |
1580 | 0 | z1 = LEFT_SHIFT(z1, CONST_BITS); |
1581 | 0 | z2 = (JLONG)wsptr[6]; |
1582 | 0 | z2 = LEFT_SHIFT(z2, CONST_BITS); |
1583 | |
|
1584 | 0 | tmp12 = z1 - z2; |
1585 | |
|
1586 | 0 | tmp21 = z3 + tmp12; |
1587 | 0 | tmp24 = z3 - tmp12; |
1588 | |
|
1589 | 0 | tmp12 = z4 + z2; |
1590 | |
|
1591 | 0 | tmp20 = tmp10 + tmp12; |
1592 | 0 | tmp25 = tmp10 - tmp12; |
1593 | |
|
1594 | 0 | tmp12 = z4 - z1 - z2; |
1595 | |
|
1596 | 0 | tmp22 = tmp11 + tmp12; |
1597 | 0 | tmp23 = tmp11 - tmp12; |
1598 | | |
1599 | | /* Odd part */ |
1600 | |
|
1601 | 0 | z1 = (JLONG)wsptr[1]; |
1602 | 0 | z2 = (JLONG)wsptr[3]; |
1603 | 0 | z3 = (JLONG)wsptr[5]; |
1604 | 0 | z4 = (JLONG)wsptr[7]; |
1605 | |
|
1606 | 0 | tmp11 = MULTIPLY(z2, FIX(1.306562965)); /* c3 */ |
1607 | 0 | tmp14 = MULTIPLY(z2, -FIX_0_541196100); /* -c9 */ |
1608 | |
|
1609 | 0 | tmp10 = z1 + z3; |
1610 | 0 | tmp15 = MULTIPLY(tmp10 + z4, FIX(0.860918669)); /* c7 */ |
1611 | 0 | tmp12 = tmp15 + MULTIPLY(tmp10, FIX(0.261052384)); /* c5-c7 */ |
1612 | 0 | tmp10 = tmp12 + tmp11 + MULTIPLY(z1, FIX(0.280143716)); /* c1-c5 */ |
1613 | 0 | tmp13 = MULTIPLY(z3 + z4, -FIX(1.045510580)); /* -(c7+c11) */ |
1614 | 0 | tmp12 += tmp13 + tmp14 - MULTIPLY(z3, FIX(1.478575242)); /* c1+c5-c7-c11 */ |
1615 | 0 | tmp13 += tmp15 - tmp11 + MULTIPLY(z4, FIX(1.586706681)); /* c1+c11 */ |
1616 | 0 | tmp15 += tmp14 - MULTIPLY(z1, FIX(0.676326758)) - /* c7-c11 */ |
1617 | 0 | MULTIPLY(z4, FIX(1.982889723)); /* c5+c7 */ |
1618 | |
|
1619 | 0 | z1 -= z4; |
1620 | 0 | z2 -= z3; |
1621 | 0 | z3 = MULTIPLY(z1 + z2, FIX_0_541196100); /* c9 */ |
1622 | 0 | tmp11 = z3 + MULTIPLY(z1, FIX_0_765366865); /* c3-c9 */ |
1623 | 0 | tmp14 = z3 - MULTIPLY(z2, FIX_1_847759065); /* c3+c9 */ |
1624 | | |
1625 | | /* Final output stage */ |
1626 | |
|
1627 | 0 | outptr[0] = range_limit[(int)RIGHT_SHIFT(tmp20 + tmp10, |
1628 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1629 | 0 | RANGE_MASK]; |
1630 | 0 | outptr[11] = range_limit[(int)RIGHT_SHIFT(tmp20 - tmp10, |
1631 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1632 | 0 | RANGE_MASK]; |
1633 | 0 | outptr[1] = range_limit[(int)RIGHT_SHIFT(tmp21 + tmp11, |
1634 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1635 | 0 | RANGE_MASK]; |
1636 | 0 | outptr[10] = range_limit[(int)RIGHT_SHIFT(tmp21 - tmp11, |
1637 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1638 | 0 | RANGE_MASK]; |
1639 | 0 | outptr[2] = range_limit[(int)RIGHT_SHIFT(tmp22 + tmp12, |
1640 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1641 | 0 | RANGE_MASK]; |
1642 | 0 | outptr[9] = range_limit[(int)RIGHT_SHIFT(tmp22 - tmp12, |
1643 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1644 | 0 | RANGE_MASK]; |
1645 | 0 | outptr[3] = range_limit[(int)RIGHT_SHIFT(tmp23 + tmp13, |
1646 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1647 | 0 | RANGE_MASK]; |
1648 | 0 | outptr[8] = range_limit[(int)RIGHT_SHIFT(tmp23 - tmp13, |
1649 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1650 | 0 | RANGE_MASK]; |
1651 | 0 | outptr[4] = range_limit[(int)RIGHT_SHIFT(tmp24 + tmp14, |
1652 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1653 | 0 | RANGE_MASK]; |
1654 | 0 | outptr[7] = range_limit[(int)RIGHT_SHIFT(tmp24 - tmp14, |
1655 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1656 | 0 | RANGE_MASK]; |
1657 | 0 | outptr[5] = range_limit[(int)RIGHT_SHIFT(tmp25 + tmp15, |
1658 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1659 | 0 | RANGE_MASK]; |
1660 | 0 | outptr[6] = range_limit[(int)RIGHT_SHIFT(tmp25 - tmp15, |
1661 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1662 | 0 | RANGE_MASK]; |
1663 | |
|
1664 | 0 | wsptr += 8; /* advance pointer to next row */ |
1665 | 0 | } |
1666 | 0 | } |
1667 | | |
1668 | | |
1669 | | /* |
1670 | | * Perform dequantization and inverse DCT on one block of coefficients, |
1671 | | * producing a 13x13 output block. |
1672 | | * |
1673 | | * Optimized algorithm with 29 multiplications in the 1-D kernel. |
1674 | | * cK represents sqrt(2) * cos(K*pi/26). |
1675 | | */ |
1676 | | |
1677 | | GLOBAL(void) |
1678 | | jpeg_idct_13x13(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
1679 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
1680 | | JDIMENSION output_col) |
1681 | 0 | { |
1682 | 0 | JLONG tmp10, tmp11, tmp12, tmp13, tmp14, tmp15; |
1683 | 0 | JLONG tmp20, tmp21, tmp22, tmp23, tmp24, tmp25, tmp26; |
1684 | 0 | JLONG z1, z2, z3, z4; |
1685 | 0 | JCOEFPTR inptr; |
1686 | 0 | ISLOW_MULT_TYPE *quantptr; |
1687 | 0 | int *wsptr; |
1688 | 0 | JSAMPROW outptr; |
1689 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
1690 | 0 | int ctr; |
1691 | 0 | int workspace[8 * 13]; /* buffers data between passes */ |
1692 | | SHIFT_TEMPS |
1693 | | |
1694 | | /* Pass 1: process columns from input, store into work array. */ |
1695 | |
|
1696 | 0 | inptr = coef_block; |
1697 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
1698 | 0 | wsptr = workspace; |
1699 | 0 | for (ctr = 0; ctr < 8; ctr++, inptr++, quantptr++, wsptr++) { |
1700 | | /* Even part */ |
1701 | |
|
1702 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
1703 | 0 | z1 = LEFT_SHIFT(z1, CONST_BITS); |
1704 | | /* Add fudge factor here for final descale. */ |
1705 | 0 | z1 += ONE << (CONST_BITS - PASS1_BITS - 1); |
1706 | |
|
1707 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
1708 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 4], quantptr[DCTSIZE * 4]); |
1709 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 6], quantptr[DCTSIZE * 6]); |
1710 | |
|
1711 | 0 | tmp10 = z3 + z4; |
1712 | 0 | tmp11 = z3 - z4; |
1713 | |
|
1714 | 0 | tmp12 = MULTIPLY(tmp10, FIX(1.155388986)); /* (c4+c6)/2 */ |
1715 | 0 | tmp13 = MULTIPLY(tmp11, FIX(0.096834934)) + z1; /* (c4-c6)/2 */ |
1716 | |
|
1717 | 0 | tmp20 = MULTIPLY(z2, FIX(1.373119086)) + tmp12 + tmp13; /* c2 */ |
1718 | 0 | tmp22 = MULTIPLY(z2, FIX(0.501487041)) - tmp12 + tmp13; /* c10 */ |
1719 | |
|
1720 | 0 | tmp12 = MULTIPLY(tmp10, FIX(0.316450131)); /* (c8-c12)/2 */ |
1721 | 0 | tmp13 = MULTIPLY(tmp11, FIX(0.486914739)) + z1; /* (c8+c12)/2 */ |
1722 | |
|
1723 | 0 | tmp21 = MULTIPLY(z2, FIX(1.058554052)) - tmp12 + tmp13; /* c6 */ |
1724 | 0 | tmp25 = MULTIPLY(z2, -FIX(1.252223920)) + tmp12 + tmp13; /* c4 */ |
1725 | |
|
1726 | 0 | tmp12 = MULTIPLY(tmp10, FIX(0.435816023)); /* (c2-c10)/2 */ |
1727 | 0 | tmp13 = MULTIPLY(tmp11, FIX(0.937303064)) - z1; /* (c2+c10)/2 */ |
1728 | |
|
1729 | 0 | tmp23 = MULTIPLY(z2, -FIX(0.170464608)) - tmp12 - tmp13; /* c12 */ |
1730 | 0 | tmp24 = MULTIPLY(z2, -FIX(0.803364869)) + tmp12 - tmp13; /* c8 */ |
1731 | |
|
1732 | 0 | tmp26 = MULTIPLY(tmp11 - z2, FIX(1.414213562)) + z1; /* c0 */ |
1733 | | |
1734 | | /* Odd part */ |
1735 | |
|
1736 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
1737 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 3], quantptr[DCTSIZE * 3]); |
1738 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 5], quantptr[DCTSIZE * 5]); |
1739 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 7], quantptr[DCTSIZE * 7]); |
1740 | |
|
1741 | 0 | tmp11 = MULTIPLY(z1 + z2, FIX(1.322312651)); /* c3 */ |
1742 | 0 | tmp12 = MULTIPLY(z1 + z3, FIX(1.163874945)); /* c5 */ |
1743 | 0 | tmp15 = z1 + z4; |
1744 | 0 | tmp13 = MULTIPLY(tmp15, FIX(0.937797057)); /* c7 */ |
1745 | 0 | tmp10 = tmp11 + tmp12 + tmp13 - |
1746 | 0 | MULTIPLY(z1, FIX(2.020082300)); /* c7+c5+c3-c1 */ |
1747 | 0 | tmp14 = MULTIPLY(z2 + z3, -FIX(0.338443458)); /* -c11 */ |
1748 | 0 | tmp11 += tmp14 + MULTIPLY(z2, FIX(0.837223564)); /* c5+c9+c11-c3 */ |
1749 | 0 | tmp12 += tmp14 - MULTIPLY(z3, FIX(1.572116027)); /* c1+c5-c9-c11 */ |
1750 | 0 | tmp14 = MULTIPLY(z2 + z4, -FIX(1.163874945)); /* -c5 */ |
1751 | 0 | tmp11 += tmp14; |
1752 | 0 | tmp13 += tmp14 + MULTIPLY(z4, FIX(2.205608352)); /* c3+c5+c9-c7 */ |
1753 | 0 | tmp14 = MULTIPLY(z3 + z4, -FIX(0.657217813)); /* -c9 */ |
1754 | 0 | tmp12 += tmp14; |
1755 | 0 | tmp13 += tmp14; |
1756 | 0 | tmp15 = MULTIPLY(tmp15, FIX(0.338443458)); /* c11 */ |
1757 | 0 | tmp14 = tmp15 + MULTIPLY(z1, FIX(0.318774355)) - /* c9-c11 */ |
1758 | 0 | MULTIPLY(z2, FIX(0.466105296)); /* c1-c7 */ |
1759 | 0 | z1 = MULTIPLY(z3 - z2, FIX(0.937797057)); /* c7 */ |
1760 | 0 | tmp14 += z1; |
1761 | 0 | tmp15 += z1 + MULTIPLY(z3, FIX(0.384515595)) - /* c3-c7 */ |
1762 | 0 | MULTIPLY(z4, FIX(1.742345811)); /* c1+c11 */ |
1763 | | |
1764 | | /* Final output stage */ |
1765 | |
|
1766 | 0 | wsptr[8 * 0] = (int)RIGHT_SHIFT(tmp20 + tmp10, CONST_BITS - PASS1_BITS); |
1767 | 0 | wsptr[8 * 12] = (int)RIGHT_SHIFT(tmp20 - tmp10, CONST_BITS - PASS1_BITS); |
1768 | 0 | wsptr[8 * 1] = (int)RIGHT_SHIFT(tmp21 + tmp11, CONST_BITS - PASS1_BITS); |
1769 | 0 | wsptr[8 * 11] = (int)RIGHT_SHIFT(tmp21 - tmp11, CONST_BITS - PASS1_BITS); |
1770 | 0 | wsptr[8 * 2] = (int)RIGHT_SHIFT(tmp22 + tmp12, CONST_BITS - PASS1_BITS); |
1771 | 0 | wsptr[8 * 10] = (int)RIGHT_SHIFT(tmp22 - tmp12, CONST_BITS - PASS1_BITS); |
1772 | 0 | wsptr[8 * 3] = (int)RIGHT_SHIFT(tmp23 + tmp13, CONST_BITS - PASS1_BITS); |
1773 | 0 | wsptr[8 * 9] = (int)RIGHT_SHIFT(tmp23 - tmp13, CONST_BITS - PASS1_BITS); |
1774 | 0 | wsptr[8 * 4] = (int)RIGHT_SHIFT(tmp24 + tmp14, CONST_BITS - PASS1_BITS); |
1775 | 0 | wsptr[8 * 8] = (int)RIGHT_SHIFT(tmp24 - tmp14, CONST_BITS - PASS1_BITS); |
1776 | 0 | wsptr[8 * 5] = (int)RIGHT_SHIFT(tmp25 + tmp15, CONST_BITS - PASS1_BITS); |
1777 | 0 | wsptr[8 * 7] = (int)RIGHT_SHIFT(tmp25 - tmp15, CONST_BITS - PASS1_BITS); |
1778 | 0 | wsptr[8 * 6] = (int)RIGHT_SHIFT(tmp26, CONST_BITS - PASS1_BITS); |
1779 | 0 | } |
1780 | | |
1781 | | /* Pass 2: process 13 rows from work array, store into output array. */ |
1782 | |
|
1783 | 0 | wsptr = workspace; |
1784 | 0 | for (ctr = 0; ctr < 13; ctr++) { |
1785 | 0 | outptr = output_buf[ctr] + output_col; |
1786 | | |
1787 | | /* Even part */ |
1788 | | |
1789 | | /* Add fudge factor here for final descale. */ |
1790 | 0 | z1 = (JLONG)wsptr[0] + (ONE << (PASS1_BITS + 2)); |
1791 | 0 | z1 = LEFT_SHIFT(z1, CONST_BITS); |
1792 | |
|
1793 | 0 | z2 = (JLONG)wsptr[2]; |
1794 | 0 | z3 = (JLONG)wsptr[4]; |
1795 | 0 | z4 = (JLONG)wsptr[6]; |
1796 | |
|
1797 | 0 | tmp10 = z3 + z4; |
1798 | 0 | tmp11 = z3 - z4; |
1799 | |
|
1800 | 0 | tmp12 = MULTIPLY(tmp10, FIX(1.155388986)); /* (c4+c6)/2 */ |
1801 | 0 | tmp13 = MULTIPLY(tmp11, FIX(0.096834934)) + z1; /* (c4-c6)/2 */ |
1802 | |
|
1803 | 0 | tmp20 = MULTIPLY(z2, FIX(1.373119086)) + tmp12 + tmp13; /* c2 */ |
1804 | 0 | tmp22 = MULTIPLY(z2, FIX(0.501487041)) - tmp12 + tmp13; /* c10 */ |
1805 | |
|
1806 | 0 | tmp12 = MULTIPLY(tmp10, FIX(0.316450131)); /* (c8-c12)/2 */ |
1807 | 0 | tmp13 = MULTIPLY(tmp11, FIX(0.486914739)) + z1; /* (c8+c12)/2 */ |
1808 | |
|
1809 | 0 | tmp21 = MULTIPLY(z2, FIX(1.058554052)) - tmp12 + tmp13; /* c6 */ |
1810 | 0 | tmp25 = MULTIPLY(z2, -FIX(1.252223920)) + tmp12 + tmp13; /* c4 */ |
1811 | |
|
1812 | 0 | tmp12 = MULTIPLY(tmp10, FIX(0.435816023)); /* (c2-c10)/2 */ |
1813 | 0 | tmp13 = MULTIPLY(tmp11, FIX(0.937303064)) - z1; /* (c2+c10)/2 */ |
1814 | |
|
1815 | 0 | tmp23 = MULTIPLY(z2, -FIX(0.170464608)) - tmp12 - tmp13; /* c12 */ |
1816 | 0 | tmp24 = MULTIPLY(z2, -FIX(0.803364869)) + tmp12 - tmp13; /* c8 */ |
1817 | |
|
1818 | 0 | tmp26 = MULTIPLY(tmp11 - z2, FIX(1.414213562)) + z1; /* c0 */ |
1819 | | |
1820 | | /* Odd part */ |
1821 | |
|
1822 | 0 | z1 = (JLONG)wsptr[1]; |
1823 | 0 | z2 = (JLONG)wsptr[3]; |
1824 | 0 | z3 = (JLONG)wsptr[5]; |
1825 | 0 | z4 = (JLONG)wsptr[7]; |
1826 | |
|
1827 | 0 | tmp11 = MULTIPLY(z1 + z2, FIX(1.322312651)); /* c3 */ |
1828 | 0 | tmp12 = MULTIPLY(z1 + z3, FIX(1.163874945)); /* c5 */ |
1829 | 0 | tmp15 = z1 + z4; |
1830 | 0 | tmp13 = MULTIPLY(tmp15, FIX(0.937797057)); /* c7 */ |
1831 | 0 | tmp10 = tmp11 + tmp12 + tmp13 - |
1832 | 0 | MULTIPLY(z1, FIX(2.020082300)); /* c7+c5+c3-c1 */ |
1833 | 0 | tmp14 = MULTIPLY(z2 + z3, -FIX(0.338443458)); /* -c11 */ |
1834 | 0 | tmp11 += tmp14 + MULTIPLY(z2, FIX(0.837223564)); /* c5+c9+c11-c3 */ |
1835 | 0 | tmp12 += tmp14 - MULTIPLY(z3, FIX(1.572116027)); /* c1+c5-c9-c11 */ |
1836 | 0 | tmp14 = MULTIPLY(z2 + z4, -FIX(1.163874945)); /* -c5 */ |
1837 | 0 | tmp11 += tmp14; |
1838 | 0 | tmp13 += tmp14 + MULTIPLY(z4, FIX(2.205608352)); /* c3+c5+c9-c7 */ |
1839 | 0 | tmp14 = MULTIPLY(z3 + z4, -FIX(0.657217813)); /* -c9 */ |
1840 | 0 | tmp12 += tmp14; |
1841 | 0 | tmp13 += tmp14; |
1842 | 0 | tmp15 = MULTIPLY(tmp15, FIX(0.338443458)); /* c11 */ |
1843 | 0 | tmp14 = tmp15 + MULTIPLY(z1, FIX(0.318774355)) - /* c9-c11 */ |
1844 | 0 | MULTIPLY(z2, FIX(0.466105296)); /* c1-c7 */ |
1845 | 0 | z1 = MULTIPLY(z3 - z2, FIX(0.937797057)); /* c7 */ |
1846 | 0 | tmp14 += z1; |
1847 | 0 | tmp15 += z1 + MULTIPLY(z3, FIX(0.384515595)) - /* c3-c7 */ |
1848 | 0 | MULTIPLY(z4, FIX(1.742345811)); /* c1+c11 */ |
1849 | | |
1850 | | /* Final output stage */ |
1851 | |
|
1852 | 0 | outptr[0] = range_limit[(int)RIGHT_SHIFT(tmp20 + tmp10, |
1853 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1854 | 0 | RANGE_MASK]; |
1855 | 0 | outptr[12] = range_limit[(int)RIGHT_SHIFT(tmp20 - tmp10, |
1856 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1857 | 0 | RANGE_MASK]; |
1858 | 0 | outptr[1] = range_limit[(int)RIGHT_SHIFT(tmp21 + tmp11, |
1859 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1860 | 0 | RANGE_MASK]; |
1861 | 0 | outptr[11] = range_limit[(int)RIGHT_SHIFT(tmp21 - tmp11, |
1862 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1863 | 0 | RANGE_MASK]; |
1864 | 0 | outptr[2] = range_limit[(int)RIGHT_SHIFT(tmp22 + tmp12, |
1865 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1866 | 0 | RANGE_MASK]; |
1867 | 0 | outptr[10] = range_limit[(int)RIGHT_SHIFT(tmp22 - tmp12, |
1868 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1869 | 0 | RANGE_MASK]; |
1870 | 0 | outptr[3] = range_limit[(int)RIGHT_SHIFT(tmp23 + tmp13, |
1871 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1872 | 0 | RANGE_MASK]; |
1873 | 0 | outptr[9] = range_limit[(int)RIGHT_SHIFT(tmp23 - tmp13, |
1874 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1875 | 0 | RANGE_MASK]; |
1876 | 0 | outptr[4] = range_limit[(int)RIGHT_SHIFT(tmp24 + tmp14, |
1877 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1878 | 0 | RANGE_MASK]; |
1879 | 0 | outptr[8] = range_limit[(int)RIGHT_SHIFT(tmp24 - tmp14, |
1880 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1881 | 0 | RANGE_MASK]; |
1882 | 0 | outptr[5] = range_limit[(int)RIGHT_SHIFT(tmp25 + tmp15, |
1883 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1884 | 0 | RANGE_MASK]; |
1885 | 0 | outptr[7] = range_limit[(int)RIGHT_SHIFT(tmp25 - tmp15, |
1886 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1887 | 0 | RANGE_MASK]; |
1888 | 0 | outptr[6] = range_limit[(int)RIGHT_SHIFT(tmp26, |
1889 | 0 | CONST_BITS + PASS1_BITS + 3) & |
1890 | 0 | RANGE_MASK]; |
1891 | |
|
1892 | 0 | wsptr += 8; /* advance pointer to next row */ |
1893 | 0 | } |
1894 | 0 | } |
1895 | | |
1896 | | |
1897 | | /* |
1898 | | * Perform dequantization and inverse DCT on one block of coefficients, |
1899 | | * producing a 14x14 output block. |
1900 | | * |
1901 | | * Optimized algorithm with 20 multiplications in the 1-D kernel. |
1902 | | * cK represents sqrt(2) * cos(K*pi/28). |
1903 | | */ |
1904 | | |
1905 | | GLOBAL(void) |
1906 | | jpeg_idct_14x14(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
1907 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
1908 | | JDIMENSION output_col) |
1909 | 0 | { |
1910 | 0 | JLONG tmp10, tmp11, tmp12, tmp13, tmp14, tmp15, tmp16; |
1911 | 0 | JLONG tmp20, tmp21, tmp22, tmp23, tmp24, tmp25, tmp26; |
1912 | 0 | JLONG z1, z2, z3, z4; |
1913 | 0 | JCOEFPTR inptr; |
1914 | 0 | ISLOW_MULT_TYPE *quantptr; |
1915 | 0 | int *wsptr; |
1916 | 0 | JSAMPROW outptr; |
1917 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
1918 | 0 | int ctr; |
1919 | 0 | int workspace[8 * 14]; /* buffers data between passes */ |
1920 | | SHIFT_TEMPS |
1921 | | |
1922 | | /* Pass 1: process columns from input, store into work array. */ |
1923 | |
|
1924 | 0 | inptr = coef_block; |
1925 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
1926 | 0 | wsptr = workspace; |
1927 | 0 | for (ctr = 0; ctr < 8; ctr++, inptr++, quantptr++, wsptr++) { |
1928 | | /* Even part */ |
1929 | |
|
1930 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
1931 | 0 | z1 = LEFT_SHIFT(z1, CONST_BITS); |
1932 | | /* Add fudge factor here for final descale. */ |
1933 | 0 | z1 += ONE << (CONST_BITS - PASS1_BITS - 1); |
1934 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 4], quantptr[DCTSIZE * 4]); |
1935 | 0 | z2 = MULTIPLY(z4, FIX(1.274162392)); /* c4 */ |
1936 | 0 | z3 = MULTIPLY(z4, FIX(0.314692123)); /* c12 */ |
1937 | 0 | z4 = MULTIPLY(z4, FIX(0.881747734)); /* c8 */ |
1938 | |
|
1939 | 0 | tmp10 = z1 + z2; |
1940 | 0 | tmp11 = z1 + z3; |
1941 | 0 | tmp12 = z1 - z4; |
1942 | |
|
1943 | 0 | tmp23 = RIGHT_SHIFT(z1 - LEFT_SHIFT(z2 + z3 - z4, 1), |
1944 | 0 | CONST_BITS - PASS1_BITS); /* c0 = (c4+c12-c8)*2 */ |
1945 | |
|
1946 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
1947 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 6], quantptr[DCTSIZE * 6]); |
1948 | |
|
1949 | 0 | z3 = MULTIPLY(z1 + z2, FIX(1.105676686)); /* c6 */ |
1950 | |
|
1951 | 0 | tmp13 = z3 + MULTIPLY(z1, FIX(0.273079590)); /* c2-c6 */ |
1952 | 0 | tmp14 = z3 - MULTIPLY(z2, FIX(1.719280954)); /* c6+c10 */ |
1953 | 0 | tmp15 = MULTIPLY(z1, FIX(0.613604268)) - /* c10 */ |
1954 | 0 | MULTIPLY(z2, FIX(1.378756276)); /* c2 */ |
1955 | |
|
1956 | 0 | tmp20 = tmp10 + tmp13; |
1957 | 0 | tmp26 = tmp10 - tmp13; |
1958 | 0 | tmp21 = tmp11 + tmp14; |
1959 | 0 | tmp25 = tmp11 - tmp14; |
1960 | 0 | tmp22 = tmp12 + tmp15; |
1961 | 0 | tmp24 = tmp12 - tmp15; |
1962 | | |
1963 | | /* Odd part */ |
1964 | |
|
1965 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
1966 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 3], quantptr[DCTSIZE * 3]); |
1967 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 5], quantptr[DCTSIZE * 5]); |
1968 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 7], quantptr[DCTSIZE * 7]); |
1969 | 0 | tmp13 = LEFT_SHIFT(z4, CONST_BITS); |
1970 | |
|
1971 | 0 | tmp14 = z1 + z3; |
1972 | 0 | tmp11 = MULTIPLY(z1 + z2, FIX(1.334852607)); /* c3 */ |
1973 | 0 | tmp12 = MULTIPLY(tmp14, FIX(1.197448846)); /* c5 */ |
1974 | 0 | tmp10 = tmp11 + tmp12 + tmp13 - MULTIPLY(z1, FIX(1.126980169)); /* c3+c5-c1 */ |
1975 | 0 | tmp14 = MULTIPLY(tmp14, FIX(0.752406978)); /* c9 */ |
1976 | 0 | tmp16 = tmp14 - MULTIPLY(z1, FIX(1.061150426)); /* c9+c11-c13 */ |
1977 | 0 | z1 -= z2; |
1978 | 0 | tmp15 = MULTIPLY(z1, FIX(0.467085129)) - tmp13; /* c11 */ |
1979 | 0 | tmp16 += tmp15; |
1980 | 0 | z1 += z4; |
1981 | 0 | z4 = MULTIPLY(z2 + z3, -FIX(0.158341681)) - tmp13; /* -c13 */ |
1982 | 0 | tmp11 += z4 - MULTIPLY(z2, FIX(0.424103948)); /* c3-c9-c13 */ |
1983 | 0 | tmp12 += z4 - MULTIPLY(z3, FIX(2.373959773)); /* c3+c5-c13 */ |
1984 | 0 | z4 = MULTIPLY(z3 - z2, FIX(1.405321284)); /* c1 */ |
1985 | 0 | tmp14 += z4 + tmp13 - MULTIPLY(z3, FIX(1.6906431334)); /* c1+c9-c11 */ |
1986 | 0 | tmp15 += z4 + MULTIPLY(z2, FIX(0.674957567)); /* c1+c11-c5 */ |
1987 | |
|
1988 | 0 | tmp13 = LEFT_SHIFT(z1 - z3, PASS1_BITS); |
1989 | | |
1990 | | /* Final output stage */ |
1991 | |
|
1992 | 0 | wsptr[8 * 0] = (int)RIGHT_SHIFT(tmp20 + tmp10, CONST_BITS - PASS1_BITS); |
1993 | 0 | wsptr[8 * 13] = (int)RIGHT_SHIFT(tmp20 - tmp10, CONST_BITS - PASS1_BITS); |
1994 | 0 | wsptr[8 * 1] = (int)RIGHT_SHIFT(tmp21 + tmp11, CONST_BITS - PASS1_BITS); |
1995 | 0 | wsptr[8 * 12] = (int)RIGHT_SHIFT(tmp21 - tmp11, CONST_BITS - PASS1_BITS); |
1996 | 0 | wsptr[8 * 2] = (int)RIGHT_SHIFT(tmp22 + tmp12, CONST_BITS - PASS1_BITS); |
1997 | 0 | wsptr[8 * 11] = (int)RIGHT_SHIFT(tmp22 - tmp12, CONST_BITS - PASS1_BITS); |
1998 | 0 | wsptr[8 * 3] = (int)(tmp23 + tmp13); |
1999 | 0 | wsptr[8 * 10] = (int)(tmp23 - tmp13); |
2000 | 0 | wsptr[8 * 4] = (int)RIGHT_SHIFT(tmp24 + tmp14, CONST_BITS - PASS1_BITS); |
2001 | 0 | wsptr[8 * 9] = (int)RIGHT_SHIFT(tmp24 - tmp14, CONST_BITS - PASS1_BITS); |
2002 | 0 | wsptr[8 * 5] = (int)RIGHT_SHIFT(tmp25 + tmp15, CONST_BITS - PASS1_BITS); |
2003 | 0 | wsptr[8 * 8] = (int)RIGHT_SHIFT(tmp25 - tmp15, CONST_BITS - PASS1_BITS); |
2004 | 0 | wsptr[8 * 6] = (int)RIGHT_SHIFT(tmp26 + tmp16, CONST_BITS - PASS1_BITS); |
2005 | 0 | wsptr[8 * 7] = (int)RIGHT_SHIFT(tmp26 - tmp16, CONST_BITS - PASS1_BITS); |
2006 | 0 | } |
2007 | | |
2008 | | /* Pass 2: process 14 rows from work array, store into output array. */ |
2009 | |
|
2010 | 0 | wsptr = workspace; |
2011 | 0 | for (ctr = 0; ctr < 14; ctr++) { |
2012 | 0 | outptr = output_buf[ctr] + output_col; |
2013 | | |
2014 | | /* Even part */ |
2015 | | |
2016 | | /* Add fudge factor here for final descale. */ |
2017 | 0 | z1 = (JLONG)wsptr[0] + (ONE << (PASS1_BITS + 2)); |
2018 | 0 | z1 = LEFT_SHIFT(z1, CONST_BITS); |
2019 | 0 | z4 = (JLONG)wsptr[4]; |
2020 | 0 | z2 = MULTIPLY(z4, FIX(1.274162392)); /* c4 */ |
2021 | 0 | z3 = MULTIPLY(z4, FIX(0.314692123)); /* c12 */ |
2022 | 0 | z4 = MULTIPLY(z4, FIX(0.881747734)); /* c8 */ |
2023 | |
|
2024 | 0 | tmp10 = z1 + z2; |
2025 | 0 | tmp11 = z1 + z3; |
2026 | 0 | tmp12 = z1 - z4; |
2027 | |
|
2028 | 0 | tmp23 = z1 - LEFT_SHIFT(z2 + z3 - z4, 1); /* c0 = (c4+c12-c8)*2 */ |
2029 | |
|
2030 | 0 | z1 = (JLONG)wsptr[2]; |
2031 | 0 | z2 = (JLONG)wsptr[6]; |
2032 | |
|
2033 | 0 | z3 = MULTIPLY(z1 + z2, FIX(1.105676686)); /* c6 */ |
2034 | |
|
2035 | 0 | tmp13 = z3 + MULTIPLY(z1, FIX(0.273079590)); /* c2-c6 */ |
2036 | 0 | tmp14 = z3 - MULTIPLY(z2, FIX(1.719280954)); /* c6+c10 */ |
2037 | 0 | tmp15 = MULTIPLY(z1, FIX(0.613604268)) - /* c10 */ |
2038 | 0 | MULTIPLY(z2, FIX(1.378756276)); /* c2 */ |
2039 | |
|
2040 | 0 | tmp20 = tmp10 + tmp13; |
2041 | 0 | tmp26 = tmp10 - tmp13; |
2042 | 0 | tmp21 = tmp11 + tmp14; |
2043 | 0 | tmp25 = tmp11 - tmp14; |
2044 | 0 | tmp22 = tmp12 + tmp15; |
2045 | 0 | tmp24 = tmp12 - tmp15; |
2046 | | |
2047 | | /* Odd part */ |
2048 | |
|
2049 | 0 | z1 = (JLONG)wsptr[1]; |
2050 | 0 | z2 = (JLONG)wsptr[3]; |
2051 | 0 | z3 = (JLONG)wsptr[5]; |
2052 | 0 | z4 = (JLONG)wsptr[7]; |
2053 | 0 | z4 = LEFT_SHIFT(z4, CONST_BITS); |
2054 | |
|
2055 | 0 | tmp14 = z1 + z3; |
2056 | 0 | tmp11 = MULTIPLY(z1 + z2, FIX(1.334852607)); /* c3 */ |
2057 | 0 | tmp12 = MULTIPLY(tmp14, FIX(1.197448846)); /* c5 */ |
2058 | 0 | tmp10 = tmp11 + tmp12 + z4 - MULTIPLY(z1, FIX(1.126980169)); /* c3+c5-c1 */ |
2059 | 0 | tmp14 = MULTIPLY(tmp14, FIX(0.752406978)); /* c9 */ |
2060 | 0 | tmp16 = tmp14 - MULTIPLY(z1, FIX(1.061150426)); /* c9+c11-c13 */ |
2061 | 0 | z1 -= z2; |
2062 | 0 | tmp15 = MULTIPLY(z1, FIX(0.467085129)) - z4; /* c11 */ |
2063 | 0 | tmp16 += tmp15; |
2064 | 0 | tmp13 = MULTIPLY(z2 + z3, -FIX(0.158341681)) - z4; /* -c13 */ |
2065 | 0 | tmp11 += tmp13 - MULTIPLY(z2, FIX(0.424103948)); /* c3-c9-c13 */ |
2066 | 0 | tmp12 += tmp13 - MULTIPLY(z3, FIX(2.373959773)); /* c3+c5-c13 */ |
2067 | 0 | tmp13 = MULTIPLY(z3 - z2, FIX(1.405321284)); /* c1 */ |
2068 | 0 | tmp14 += tmp13 + z4 - MULTIPLY(z3, FIX(1.6906431334)); /* c1+c9-c11 */ |
2069 | 0 | tmp15 += tmp13 + MULTIPLY(z2, FIX(0.674957567)); /* c1+c11-c5 */ |
2070 | |
|
2071 | 0 | tmp13 = LEFT_SHIFT(z1 - z3, CONST_BITS) + z4; |
2072 | | |
2073 | | /* Final output stage */ |
2074 | |
|
2075 | 0 | outptr[0] = range_limit[(int)RIGHT_SHIFT(tmp20 + tmp10, |
2076 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2077 | 0 | RANGE_MASK]; |
2078 | 0 | outptr[13] = range_limit[(int)RIGHT_SHIFT(tmp20 - tmp10, |
2079 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2080 | 0 | RANGE_MASK]; |
2081 | 0 | outptr[1] = range_limit[(int)RIGHT_SHIFT(tmp21 + tmp11, |
2082 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2083 | 0 | RANGE_MASK]; |
2084 | 0 | outptr[12] = range_limit[(int)RIGHT_SHIFT(tmp21 - tmp11, |
2085 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2086 | 0 | RANGE_MASK]; |
2087 | 0 | outptr[2] = range_limit[(int)RIGHT_SHIFT(tmp22 + tmp12, |
2088 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2089 | 0 | RANGE_MASK]; |
2090 | 0 | outptr[11] = range_limit[(int)RIGHT_SHIFT(tmp22 - tmp12, |
2091 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2092 | 0 | RANGE_MASK]; |
2093 | 0 | outptr[3] = range_limit[(int)RIGHT_SHIFT(tmp23 + tmp13, |
2094 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2095 | 0 | RANGE_MASK]; |
2096 | 0 | outptr[10] = range_limit[(int)RIGHT_SHIFT(tmp23 - tmp13, |
2097 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2098 | 0 | RANGE_MASK]; |
2099 | 0 | outptr[4] = range_limit[(int)RIGHT_SHIFT(tmp24 + tmp14, |
2100 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2101 | 0 | RANGE_MASK]; |
2102 | 0 | outptr[9] = range_limit[(int)RIGHT_SHIFT(tmp24 - tmp14, |
2103 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2104 | 0 | RANGE_MASK]; |
2105 | 0 | outptr[5] = range_limit[(int)RIGHT_SHIFT(tmp25 + tmp15, |
2106 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2107 | 0 | RANGE_MASK]; |
2108 | 0 | outptr[8] = range_limit[(int)RIGHT_SHIFT(tmp25 - tmp15, |
2109 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2110 | 0 | RANGE_MASK]; |
2111 | 0 | outptr[6] = range_limit[(int)RIGHT_SHIFT(tmp26 + tmp16, |
2112 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2113 | 0 | RANGE_MASK]; |
2114 | 0 | outptr[7] = range_limit[(int)RIGHT_SHIFT(tmp26 - tmp16, |
2115 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2116 | 0 | RANGE_MASK]; |
2117 | |
|
2118 | 0 | wsptr += 8; /* advance pointer to next row */ |
2119 | 0 | } |
2120 | 0 | } |
2121 | | |
2122 | | |
2123 | | /* |
2124 | | * Perform dequantization and inverse DCT on one block of coefficients, |
2125 | | * producing a 15x15 output block. |
2126 | | * |
2127 | | * Optimized algorithm with 22 multiplications in the 1-D kernel. |
2128 | | * cK represents sqrt(2) * cos(K*pi/30). |
2129 | | */ |
2130 | | |
2131 | | GLOBAL(void) |
2132 | | jpeg_idct_15x15(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
2133 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
2134 | | JDIMENSION output_col) |
2135 | 0 | { |
2136 | 0 | JLONG tmp10, tmp11, tmp12, tmp13, tmp14, tmp15, tmp16; |
2137 | 0 | JLONG tmp20, tmp21, tmp22, tmp23, tmp24, tmp25, tmp26, tmp27; |
2138 | 0 | JLONG z1, z2, z3, z4; |
2139 | 0 | JCOEFPTR inptr; |
2140 | 0 | ISLOW_MULT_TYPE *quantptr; |
2141 | 0 | int *wsptr; |
2142 | 0 | JSAMPROW outptr; |
2143 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
2144 | 0 | int ctr; |
2145 | 0 | int workspace[8 * 15]; /* buffers data between passes */ |
2146 | | SHIFT_TEMPS |
2147 | | |
2148 | | /* Pass 1: process columns from input, store into work array. */ |
2149 | |
|
2150 | 0 | inptr = coef_block; |
2151 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
2152 | 0 | wsptr = workspace; |
2153 | 0 | for (ctr = 0; ctr < 8; ctr++, inptr++, quantptr++, wsptr++) { |
2154 | | /* Even part */ |
2155 | |
|
2156 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
2157 | 0 | z1 = LEFT_SHIFT(z1, CONST_BITS); |
2158 | | /* Add fudge factor here for final descale. */ |
2159 | 0 | z1 += ONE << (CONST_BITS - PASS1_BITS - 1); |
2160 | |
|
2161 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
2162 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 4], quantptr[DCTSIZE * 4]); |
2163 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 6], quantptr[DCTSIZE * 6]); |
2164 | |
|
2165 | 0 | tmp10 = MULTIPLY(z4, FIX(0.437016024)); /* c12 */ |
2166 | 0 | tmp11 = MULTIPLY(z4, FIX(1.144122806)); /* c6 */ |
2167 | |
|
2168 | 0 | tmp12 = z1 - tmp10; |
2169 | 0 | tmp13 = z1 + tmp11; |
2170 | 0 | z1 -= LEFT_SHIFT(tmp11 - tmp10, 1); /* c0 = (c6-c12)*2 */ |
2171 | |
|
2172 | 0 | z4 = z2 - z3; |
2173 | 0 | z3 += z2; |
2174 | 0 | tmp10 = MULTIPLY(z3, FIX(1.337628990)); /* (c2+c4)/2 */ |
2175 | 0 | tmp11 = MULTIPLY(z4, FIX(0.045680613)); /* (c2-c4)/2 */ |
2176 | 0 | z2 = MULTIPLY(z2, FIX(1.439773946)); /* c4+c14 */ |
2177 | |
|
2178 | 0 | tmp20 = tmp13 + tmp10 + tmp11; |
2179 | 0 | tmp23 = tmp12 - tmp10 + tmp11 + z2; |
2180 | |
|
2181 | 0 | tmp10 = MULTIPLY(z3, FIX(0.547059574)); /* (c8+c14)/2 */ |
2182 | 0 | tmp11 = MULTIPLY(z4, FIX(0.399234004)); /* (c8-c14)/2 */ |
2183 | |
|
2184 | 0 | tmp25 = tmp13 - tmp10 - tmp11; |
2185 | 0 | tmp26 = tmp12 + tmp10 - tmp11 - z2; |
2186 | |
|
2187 | 0 | tmp10 = MULTIPLY(z3, FIX(0.790569415)); /* (c6+c12)/2 */ |
2188 | 0 | tmp11 = MULTIPLY(z4, FIX(0.353553391)); /* (c6-c12)/2 */ |
2189 | |
|
2190 | 0 | tmp21 = tmp12 + tmp10 + tmp11; |
2191 | 0 | tmp24 = tmp13 - tmp10 + tmp11; |
2192 | 0 | tmp11 += tmp11; |
2193 | 0 | tmp22 = z1 + tmp11; /* c10 = c6-c12 */ |
2194 | 0 | tmp27 = z1 - tmp11 - tmp11; /* c0 = (c6-c12)*2 */ |
2195 | | |
2196 | | /* Odd part */ |
2197 | |
|
2198 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
2199 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 3], quantptr[DCTSIZE * 3]); |
2200 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 5], quantptr[DCTSIZE * 5]); |
2201 | 0 | z3 = MULTIPLY(z4, FIX(1.224744871)); /* c5 */ |
2202 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 7], quantptr[DCTSIZE * 7]); |
2203 | |
|
2204 | 0 | tmp13 = z2 - z4; |
2205 | 0 | tmp15 = MULTIPLY(z1 + tmp13, FIX(0.831253876)); /* c9 */ |
2206 | 0 | tmp11 = tmp15 + MULTIPLY(z1, FIX(0.513743148)); /* c3-c9 */ |
2207 | 0 | tmp14 = tmp15 - MULTIPLY(tmp13, FIX(2.176250899)); /* c3+c9 */ |
2208 | |
|
2209 | 0 | tmp13 = MULTIPLY(z2, -FIX(0.831253876)); /* -c9 */ |
2210 | 0 | tmp15 = MULTIPLY(z2, -FIX(1.344997024)); /* -c3 */ |
2211 | 0 | z2 = z1 - z4; |
2212 | 0 | tmp12 = z3 + MULTIPLY(z2, FIX(1.406466353)); /* c1 */ |
2213 | |
|
2214 | 0 | tmp10 = tmp12 + MULTIPLY(z4, FIX(2.457431844)) - tmp15; /* c1+c7 */ |
2215 | 0 | tmp16 = tmp12 - MULTIPLY(z1, FIX(1.112434820)) + tmp13; /* c1-c13 */ |
2216 | 0 | tmp12 = MULTIPLY(z2, FIX(1.224744871)) - z3; /* c5 */ |
2217 | 0 | z2 = MULTIPLY(z1 + z4, FIX(0.575212477)); /* c11 */ |
2218 | 0 | tmp13 += z2 + MULTIPLY(z1, FIX(0.475753014)) - z3; /* c7-c11 */ |
2219 | 0 | tmp15 += z2 - MULTIPLY(z4, FIX(0.869244010)) + z3; /* c11+c13 */ |
2220 | | |
2221 | | /* Final output stage */ |
2222 | |
|
2223 | 0 | wsptr[8 * 0] = (int)RIGHT_SHIFT(tmp20 + tmp10, CONST_BITS - PASS1_BITS); |
2224 | 0 | wsptr[8 * 14] = (int)RIGHT_SHIFT(tmp20 - tmp10, CONST_BITS - PASS1_BITS); |
2225 | 0 | wsptr[8 * 1] = (int)RIGHT_SHIFT(tmp21 + tmp11, CONST_BITS - PASS1_BITS); |
2226 | 0 | wsptr[8 * 13] = (int)RIGHT_SHIFT(tmp21 - tmp11, CONST_BITS - PASS1_BITS); |
2227 | 0 | wsptr[8 * 2] = (int)RIGHT_SHIFT(tmp22 + tmp12, CONST_BITS - PASS1_BITS); |
2228 | 0 | wsptr[8 * 12] = (int)RIGHT_SHIFT(tmp22 - tmp12, CONST_BITS - PASS1_BITS); |
2229 | 0 | wsptr[8 * 3] = (int)RIGHT_SHIFT(tmp23 + tmp13, CONST_BITS - PASS1_BITS); |
2230 | 0 | wsptr[8 * 11] = (int)RIGHT_SHIFT(tmp23 - tmp13, CONST_BITS - PASS1_BITS); |
2231 | 0 | wsptr[8 * 4] = (int)RIGHT_SHIFT(tmp24 + tmp14, CONST_BITS - PASS1_BITS); |
2232 | 0 | wsptr[8 * 10] = (int)RIGHT_SHIFT(tmp24 - tmp14, CONST_BITS - PASS1_BITS); |
2233 | 0 | wsptr[8 * 5] = (int)RIGHT_SHIFT(tmp25 + tmp15, CONST_BITS - PASS1_BITS); |
2234 | 0 | wsptr[8 * 9] = (int)RIGHT_SHIFT(tmp25 - tmp15, CONST_BITS - PASS1_BITS); |
2235 | 0 | wsptr[8 * 6] = (int)RIGHT_SHIFT(tmp26 + tmp16, CONST_BITS - PASS1_BITS); |
2236 | 0 | wsptr[8 * 8] = (int)RIGHT_SHIFT(tmp26 - tmp16, CONST_BITS - PASS1_BITS); |
2237 | 0 | wsptr[8 * 7] = (int)RIGHT_SHIFT(tmp27, CONST_BITS - PASS1_BITS); |
2238 | 0 | } |
2239 | | |
2240 | | /* Pass 2: process 15 rows from work array, store into output array. */ |
2241 | |
|
2242 | 0 | wsptr = workspace; |
2243 | 0 | for (ctr = 0; ctr < 15; ctr++) { |
2244 | 0 | outptr = output_buf[ctr] + output_col; |
2245 | | |
2246 | | /* Even part */ |
2247 | | |
2248 | | /* Add fudge factor here for final descale. */ |
2249 | 0 | z1 = (JLONG)wsptr[0] + (ONE << (PASS1_BITS + 2)); |
2250 | 0 | z1 = LEFT_SHIFT(z1, CONST_BITS); |
2251 | |
|
2252 | 0 | z2 = (JLONG)wsptr[2]; |
2253 | 0 | z3 = (JLONG)wsptr[4]; |
2254 | 0 | z4 = (JLONG)wsptr[6]; |
2255 | |
|
2256 | 0 | tmp10 = MULTIPLY(z4, FIX(0.437016024)); /* c12 */ |
2257 | 0 | tmp11 = MULTIPLY(z4, FIX(1.144122806)); /* c6 */ |
2258 | |
|
2259 | 0 | tmp12 = z1 - tmp10; |
2260 | 0 | tmp13 = z1 + tmp11; |
2261 | 0 | z1 -= LEFT_SHIFT(tmp11 - tmp10, 1); /* c0 = (c6-c12)*2 */ |
2262 | |
|
2263 | 0 | z4 = z2 - z3; |
2264 | 0 | z3 += z2; |
2265 | 0 | tmp10 = MULTIPLY(z3, FIX(1.337628990)); /* (c2+c4)/2 */ |
2266 | 0 | tmp11 = MULTIPLY(z4, FIX(0.045680613)); /* (c2-c4)/2 */ |
2267 | 0 | z2 = MULTIPLY(z2, FIX(1.439773946)); /* c4+c14 */ |
2268 | |
|
2269 | 0 | tmp20 = tmp13 + tmp10 + tmp11; |
2270 | 0 | tmp23 = tmp12 - tmp10 + tmp11 + z2; |
2271 | |
|
2272 | 0 | tmp10 = MULTIPLY(z3, FIX(0.547059574)); /* (c8+c14)/2 */ |
2273 | 0 | tmp11 = MULTIPLY(z4, FIX(0.399234004)); /* (c8-c14)/2 */ |
2274 | |
|
2275 | 0 | tmp25 = tmp13 - tmp10 - tmp11; |
2276 | 0 | tmp26 = tmp12 + tmp10 - tmp11 - z2; |
2277 | |
|
2278 | 0 | tmp10 = MULTIPLY(z3, FIX(0.790569415)); /* (c6+c12)/2 */ |
2279 | 0 | tmp11 = MULTIPLY(z4, FIX(0.353553391)); /* (c6-c12)/2 */ |
2280 | |
|
2281 | 0 | tmp21 = tmp12 + tmp10 + tmp11; |
2282 | 0 | tmp24 = tmp13 - tmp10 + tmp11; |
2283 | 0 | tmp11 += tmp11; |
2284 | 0 | tmp22 = z1 + tmp11; /* c10 = c6-c12 */ |
2285 | 0 | tmp27 = z1 - tmp11 - tmp11; /* c0 = (c6-c12)*2 */ |
2286 | | |
2287 | | /* Odd part */ |
2288 | |
|
2289 | 0 | z1 = (JLONG)wsptr[1]; |
2290 | 0 | z2 = (JLONG)wsptr[3]; |
2291 | 0 | z4 = (JLONG)wsptr[5]; |
2292 | 0 | z3 = MULTIPLY(z4, FIX(1.224744871)); /* c5 */ |
2293 | 0 | z4 = (JLONG)wsptr[7]; |
2294 | |
|
2295 | 0 | tmp13 = z2 - z4; |
2296 | 0 | tmp15 = MULTIPLY(z1 + tmp13, FIX(0.831253876)); /* c9 */ |
2297 | 0 | tmp11 = tmp15 + MULTIPLY(z1, FIX(0.513743148)); /* c3-c9 */ |
2298 | 0 | tmp14 = tmp15 - MULTIPLY(tmp13, FIX(2.176250899)); /* c3+c9 */ |
2299 | |
|
2300 | 0 | tmp13 = MULTIPLY(z2, -FIX(0.831253876)); /* -c9 */ |
2301 | 0 | tmp15 = MULTIPLY(z2, -FIX(1.344997024)); /* -c3 */ |
2302 | 0 | z2 = z1 - z4; |
2303 | 0 | tmp12 = z3 + MULTIPLY(z2, FIX(1.406466353)); /* c1 */ |
2304 | |
|
2305 | 0 | tmp10 = tmp12 + MULTIPLY(z4, FIX(2.457431844)) - tmp15; /* c1+c7 */ |
2306 | 0 | tmp16 = tmp12 - MULTIPLY(z1, FIX(1.112434820)) + tmp13; /* c1-c13 */ |
2307 | 0 | tmp12 = MULTIPLY(z2, FIX(1.224744871)) - z3; /* c5 */ |
2308 | 0 | z2 = MULTIPLY(z1 + z4, FIX(0.575212477)); /* c11 */ |
2309 | 0 | tmp13 += z2 + MULTIPLY(z1, FIX(0.475753014)) - z3; /* c7-c11 */ |
2310 | 0 | tmp15 += z2 - MULTIPLY(z4, FIX(0.869244010)) + z3; /* c11+c13 */ |
2311 | | |
2312 | | /* Final output stage */ |
2313 | |
|
2314 | 0 | outptr[0] = range_limit[(int)RIGHT_SHIFT(tmp20 + tmp10, |
2315 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2316 | 0 | RANGE_MASK]; |
2317 | 0 | outptr[14] = range_limit[(int)RIGHT_SHIFT(tmp20 - tmp10, |
2318 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2319 | 0 | RANGE_MASK]; |
2320 | 0 | outptr[1] = range_limit[(int)RIGHT_SHIFT(tmp21 + tmp11, |
2321 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2322 | 0 | RANGE_MASK]; |
2323 | 0 | outptr[13] = range_limit[(int)RIGHT_SHIFT(tmp21 - tmp11, |
2324 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2325 | 0 | RANGE_MASK]; |
2326 | 0 | outptr[2] = range_limit[(int)RIGHT_SHIFT(tmp22 + tmp12, |
2327 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2328 | 0 | RANGE_MASK]; |
2329 | 0 | outptr[12] = range_limit[(int)RIGHT_SHIFT(tmp22 - tmp12, |
2330 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2331 | 0 | RANGE_MASK]; |
2332 | 0 | outptr[3] = range_limit[(int)RIGHT_SHIFT(tmp23 + tmp13, |
2333 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2334 | 0 | RANGE_MASK]; |
2335 | 0 | outptr[11] = range_limit[(int)RIGHT_SHIFT(tmp23 - tmp13, |
2336 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2337 | 0 | RANGE_MASK]; |
2338 | 0 | outptr[4] = range_limit[(int)RIGHT_SHIFT(tmp24 + tmp14, |
2339 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2340 | 0 | RANGE_MASK]; |
2341 | 0 | outptr[10] = range_limit[(int)RIGHT_SHIFT(tmp24 - tmp14, |
2342 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2343 | 0 | RANGE_MASK]; |
2344 | 0 | outptr[5] = range_limit[(int)RIGHT_SHIFT(tmp25 + tmp15, |
2345 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2346 | 0 | RANGE_MASK]; |
2347 | 0 | outptr[9] = range_limit[(int)RIGHT_SHIFT(tmp25 - tmp15, |
2348 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2349 | 0 | RANGE_MASK]; |
2350 | 0 | outptr[6] = range_limit[(int)RIGHT_SHIFT(tmp26 + tmp16, |
2351 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2352 | 0 | RANGE_MASK]; |
2353 | 0 | outptr[8] = range_limit[(int)RIGHT_SHIFT(tmp26 - tmp16, |
2354 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2355 | 0 | RANGE_MASK]; |
2356 | 0 | outptr[7] = range_limit[(int)RIGHT_SHIFT(tmp27, |
2357 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2358 | 0 | RANGE_MASK]; |
2359 | |
|
2360 | 0 | wsptr += 8; /* advance pointer to next row */ |
2361 | 0 | } |
2362 | 0 | } |
2363 | | |
2364 | | |
2365 | | /* |
2366 | | * Perform dequantization and inverse DCT on one block of coefficients, |
2367 | | * producing a 16x16 output block. |
2368 | | * |
2369 | | * Optimized algorithm with 28 multiplications in the 1-D kernel. |
2370 | | * cK represents sqrt(2) * cos(K*pi/32). |
2371 | | */ |
2372 | | |
2373 | | GLOBAL(void) |
2374 | | jpeg_idct_16x16(j_decompress_ptr cinfo, jpeg_component_info *compptr, |
2375 | | JCOEFPTR coef_block, JSAMPARRAY output_buf, |
2376 | | JDIMENSION output_col) |
2377 | 0 | { |
2378 | 0 | JLONG tmp0, tmp1, tmp2, tmp3, tmp10, tmp11, tmp12, tmp13; |
2379 | 0 | JLONG tmp20, tmp21, tmp22, tmp23, tmp24, tmp25, tmp26, tmp27; |
2380 | 0 | JLONG z1, z2, z3, z4; |
2381 | 0 | JCOEFPTR inptr; |
2382 | 0 | ISLOW_MULT_TYPE *quantptr; |
2383 | 0 | int *wsptr; |
2384 | 0 | JSAMPROW outptr; |
2385 | 0 | JSAMPLE *range_limit = IDCT_range_limit(cinfo); |
2386 | 0 | int ctr; |
2387 | 0 | int workspace[8 * 16]; /* buffers data between passes */ |
2388 | | SHIFT_TEMPS |
2389 | | |
2390 | | /* Pass 1: process columns from input, store into work array. */ |
2391 | |
|
2392 | 0 | inptr = coef_block; |
2393 | 0 | quantptr = (ISLOW_MULT_TYPE *)compptr->dct_table; |
2394 | 0 | wsptr = workspace; |
2395 | 0 | for (ctr = 0; ctr < 8; ctr++, inptr++, quantptr++, wsptr++) { |
2396 | | /* Even part */ |
2397 | |
|
2398 | 0 | tmp0 = DEQUANTIZE(inptr[DCTSIZE * 0], quantptr[DCTSIZE * 0]); |
2399 | 0 | tmp0 = LEFT_SHIFT(tmp0, CONST_BITS); |
2400 | | /* Add fudge factor here for final descale. */ |
2401 | 0 | tmp0 += ONE << (CONST_BITS - PASS1_BITS - 1); |
2402 | |
|
2403 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 4], quantptr[DCTSIZE * 4]); |
2404 | 0 | tmp1 = MULTIPLY(z1, FIX(1.306562965)); /* c4[16] = c2[8] */ |
2405 | 0 | tmp2 = MULTIPLY(z1, FIX_0_541196100); /* c12[16] = c6[8] */ |
2406 | |
|
2407 | 0 | tmp10 = tmp0 + tmp1; |
2408 | 0 | tmp11 = tmp0 - tmp1; |
2409 | 0 | tmp12 = tmp0 + tmp2; |
2410 | 0 | tmp13 = tmp0 - tmp2; |
2411 | |
|
2412 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 2], quantptr[DCTSIZE * 2]); |
2413 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 6], quantptr[DCTSIZE * 6]); |
2414 | 0 | z3 = z1 - z2; |
2415 | 0 | z4 = MULTIPLY(z3, FIX(0.275899379)); /* c14[16] = c7[8] */ |
2416 | 0 | z3 = MULTIPLY(z3, FIX(1.387039845)); /* c2[16] = c1[8] */ |
2417 | |
|
2418 | 0 | tmp0 = z3 + MULTIPLY(z2, FIX_2_562915447); /* (c6+c2)[16] = (c3+c1)[8] */ |
2419 | 0 | tmp1 = z4 + MULTIPLY(z1, FIX_0_899976223); /* (c6-c14)[16] = (c3-c7)[8] */ |
2420 | 0 | tmp2 = z3 - MULTIPLY(z1, FIX(0.601344887)); /* (c2-c10)[16] = (c1-c5)[8] */ |
2421 | 0 | tmp3 = z4 - MULTIPLY(z2, FIX(0.509795579)); /* (c10-c14)[16] = (c5-c7)[8] */ |
2422 | |
|
2423 | 0 | tmp20 = tmp10 + tmp0; |
2424 | 0 | tmp27 = tmp10 - tmp0; |
2425 | 0 | tmp21 = tmp12 + tmp1; |
2426 | 0 | tmp26 = tmp12 - tmp1; |
2427 | 0 | tmp22 = tmp13 + tmp2; |
2428 | 0 | tmp25 = tmp13 - tmp2; |
2429 | 0 | tmp23 = tmp11 + tmp3; |
2430 | 0 | tmp24 = tmp11 - tmp3; |
2431 | | |
2432 | | /* Odd part */ |
2433 | |
|
2434 | 0 | z1 = DEQUANTIZE(inptr[DCTSIZE * 1], quantptr[DCTSIZE * 1]); |
2435 | 0 | z2 = DEQUANTIZE(inptr[DCTSIZE * 3], quantptr[DCTSIZE * 3]); |
2436 | 0 | z3 = DEQUANTIZE(inptr[DCTSIZE * 5], quantptr[DCTSIZE * 5]); |
2437 | 0 | z4 = DEQUANTIZE(inptr[DCTSIZE * 7], quantptr[DCTSIZE * 7]); |
2438 | |
|
2439 | 0 | tmp11 = z1 + z3; |
2440 | |
|
2441 | 0 | tmp1 = MULTIPLY(z1 + z2, FIX(1.353318001)); /* c3 */ |
2442 | 0 | tmp2 = MULTIPLY(tmp11, FIX(1.247225013)); /* c5 */ |
2443 | 0 | tmp3 = MULTIPLY(z1 + z4, FIX(1.093201867)); /* c7 */ |
2444 | 0 | tmp10 = MULTIPLY(z1 - z4, FIX(0.897167586)); /* c9 */ |
2445 | 0 | tmp11 = MULTIPLY(tmp11, FIX(0.666655658)); /* c11 */ |
2446 | 0 | tmp12 = MULTIPLY(z1 - z2, FIX(0.410524528)); /* c13 */ |
2447 | 0 | tmp0 = tmp1 + tmp2 + tmp3 - |
2448 | 0 | MULTIPLY(z1, FIX(2.286341144)); /* c7+c5+c3-c1 */ |
2449 | 0 | tmp13 = tmp10 + tmp11 + tmp12 - |
2450 | 0 | MULTIPLY(z1, FIX(1.835730603)); /* c9+c11+c13-c15 */ |
2451 | 0 | z1 = MULTIPLY(z2 + z3, FIX(0.138617169)); /* c15 */ |
2452 | 0 | tmp1 += z1 + MULTIPLY(z2, FIX(0.071888074)); /* c9+c11-c3-c15 */ |
2453 | 0 | tmp2 += z1 - MULTIPLY(z3, FIX(1.125726048)); /* c5+c7+c15-c3 */ |
2454 | 0 | z1 = MULTIPLY(z3 - z2, FIX(1.407403738)); /* c1 */ |
2455 | 0 | tmp11 += z1 - MULTIPLY(z3, FIX(0.766367282)); /* c1+c11-c9-c13 */ |
2456 | 0 | tmp12 += z1 + MULTIPLY(z2, FIX(1.971951411)); /* c1+c5+c13-c7 */ |
2457 | 0 | z2 += z4; |
2458 | 0 | z1 = MULTIPLY(z2, -FIX(0.666655658)); /* -c11 */ |
2459 | 0 | tmp1 += z1; |
2460 | 0 | tmp3 += z1 + MULTIPLY(z4, FIX(1.065388962)); /* c3+c11+c15-c7 */ |
2461 | 0 | z2 = MULTIPLY(z2, -FIX(1.247225013)); /* -c5 */ |
2462 | 0 | tmp10 += z2 + MULTIPLY(z4, FIX(3.141271809)); /* c1+c5+c9-c13 */ |
2463 | 0 | tmp12 += z2; |
2464 | 0 | z2 = MULTIPLY(z3 + z4, -FIX(1.353318001)); /* -c3 */ |
2465 | 0 | tmp2 += z2; |
2466 | 0 | tmp3 += z2; |
2467 | 0 | z2 = MULTIPLY(z4 - z3, FIX(0.410524528)); /* c13 */ |
2468 | 0 | tmp10 += z2; |
2469 | 0 | tmp11 += z2; |
2470 | | |
2471 | | /* Final output stage */ |
2472 | |
|
2473 | 0 | wsptr[8 * 0] = (int)RIGHT_SHIFT(tmp20 + tmp0, CONST_BITS - PASS1_BITS); |
2474 | 0 | wsptr[8 * 15] = (int)RIGHT_SHIFT(tmp20 - tmp0, CONST_BITS - PASS1_BITS); |
2475 | 0 | wsptr[8 * 1] = (int)RIGHT_SHIFT(tmp21 + tmp1, CONST_BITS - PASS1_BITS); |
2476 | 0 | wsptr[8 * 14] = (int)RIGHT_SHIFT(tmp21 - tmp1, CONST_BITS - PASS1_BITS); |
2477 | 0 | wsptr[8 * 2] = (int)RIGHT_SHIFT(tmp22 + tmp2, CONST_BITS - PASS1_BITS); |
2478 | 0 | wsptr[8 * 13] = (int)RIGHT_SHIFT(tmp22 - tmp2, CONST_BITS - PASS1_BITS); |
2479 | 0 | wsptr[8 * 3] = (int)RIGHT_SHIFT(tmp23 + tmp3, CONST_BITS - PASS1_BITS); |
2480 | 0 | wsptr[8 * 12] = (int)RIGHT_SHIFT(tmp23 - tmp3, CONST_BITS - PASS1_BITS); |
2481 | 0 | wsptr[8 * 4] = (int)RIGHT_SHIFT(tmp24 + tmp10, CONST_BITS - PASS1_BITS); |
2482 | 0 | wsptr[8 * 11] = (int)RIGHT_SHIFT(tmp24 - tmp10, CONST_BITS - PASS1_BITS); |
2483 | 0 | wsptr[8 * 5] = (int)RIGHT_SHIFT(tmp25 + tmp11, CONST_BITS - PASS1_BITS); |
2484 | 0 | wsptr[8 * 10] = (int)RIGHT_SHIFT(tmp25 - tmp11, CONST_BITS - PASS1_BITS); |
2485 | 0 | wsptr[8 * 6] = (int)RIGHT_SHIFT(tmp26 + tmp12, CONST_BITS - PASS1_BITS); |
2486 | 0 | wsptr[8 * 9] = (int)RIGHT_SHIFT(tmp26 - tmp12, CONST_BITS - PASS1_BITS); |
2487 | 0 | wsptr[8 * 7] = (int)RIGHT_SHIFT(tmp27 + tmp13, CONST_BITS - PASS1_BITS); |
2488 | 0 | wsptr[8 * 8] = (int)RIGHT_SHIFT(tmp27 - tmp13, CONST_BITS - PASS1_BITS); |
2489 | 0 | } |
2490 | | |
2491 | | /* Pass 2: process 16 rows from work array, store into output array. */ |
2492 | |
|
2493 | 0 | wsptr = workspace; |
2494 | 0 | for (ctr = 0; ctr < 16; ctr++) { |
2495 | 0 | outptr = output_buf[ctr] + output_col; |
2496 | | |
2497 | | /* Even part */ |
2498 | | |
2499 | | /* Add fudge factor here for final descale. */ |
2500 | 0 | tmp0 = (JLONG)wsptr[0] + (ONE << (PASS1_BITS + 2)); |
2501 | 0 | tmp0 = LEFT_SHIFT(tmp0, CONST_BITS); |
2502 | |
|
2503 | 0 | z1 = (JLONG)wsptr[4]; |
2504 | 0 | tmp1 = MULTIPLY(z1, FIX(1.306562965)); /* c4[16] = c2[8] */ |
2505 | 0 | tmp2 = MULTIPLY(z1, FIX_0_541196100); /* c12[16] = c6[8] */ |
2506 | |
|
2507 | 0 | tmp10 = tmp0 + tmp1; |
2508 | 0 | tmp11 = tmp0 - tmp1; |
2509 | 0 | tmp12 = tmp0 + tmp2; |
2510 | 0 | tmp13 = tmp0 - tmp2; |
2511 | |
|
2512 | 0 | z1 = (JLONG)wsptr[2]; |
2513 | 0 | z2 = (JLONG)wsptr[6]; |
2514 | 0 | z3 = z1 - z2; |
2515 | 0 | z4 = MULTIPLY(z3, FIX(0.275899379)); /* c14[16] = c7[8] */ |
2516 | 0 | z3 = MULTIPLY(z3, FIX(1.387039845)); /* c2[16] = c1[8] */ |
2517 | |
|
2518 | 0 | tmp0 = z3 + MULTIPLY(z2, FIX_2_562915447); /* (c6+c2)[16] = (c3+c1)[8] */ |
2519 | 0 | tmp1 = z4 + MULTIPLY(z1, FIX_0_899976223); /* (c6-c14)[16] = (c3-c7)[8] */ |
2520 | 0 | tmp2 = z3 - MULTIPLY(z1, FIX(0.601344887)); /* (c2-c10)[16] = (c1-c5)[8] */ |
2521 | 0 | tmp3 = z4 - MULTIPLY(z2, FIX(0.509795579)); /* (c10-c14)[16] = (c5-c7)[8] */ |
2522 | |
|
2523 | 0 | tmp20 = tmp10 + tmp0; |
2524 | 0 | tmp27 = tmp10 - tmp0; |
2525 | 0 | tmp21 = tmp12 + tmp1; |
2526 | 0 | tmp26 = tmp12 - tmp1; |
2527 | 0 | tmp22 = tmp13 + tmp2; |
2528 | 0 | tmp25 = tmp13 - tmp2; |
2529 | 0 | tmp23 = tmp11 + tmp3; |
2530 | 0 | tmp24 = tmp11 - tmp3; |
2531 | | |
2532 | | /* Odd part */ |
2533 | |
|
2534 | 0 | z1 = (JLONG)wsptr[1]; |
2535 | 0 | z2 = (JLONG)wsptr[3]; |
2536 | 0 | z3 = (JLONG)wsptr[5]; |
2537 | 0 | z4 = (JLONG)wsptr[7]; |
2538 | |
|
2539 | 0 | tmp11 = z1 + z3; |
2540 | |
|
2541 | 0 | tmp1 = MULTIPLY(z1 + z2, FIX(1.353318001)); /* c3 */ |
2542 | 0 | tmp2 = MULTIPLY(tmp11, FIX(1.247225013)); /* c5 */ |
2543 | 0 | tmp3 = MULTIPLY(z1 + z4, FIX(1.093201867)); /* c7 */ |
2544 | 0 | tmp10 = MULTIPLY(z1 - z4, FIX(0.897167586)); /* c9 */ |
2545 | 0 | tmp11 = MULTIPLY(tmp11, FIX(0.666655658)); /* c11 */ |
2546 | 0 | tmp12 = MULTIPLY(z1 - z2, FIX(0.410524528)); /* c13 */ |
2547 | 0 | tmp0 = tmp1 + tmp2 + tmp3 - |
2548 | 0 | MULTIPLY(z1, FIX(2.286341144)); /* c7+c5+c3-c1 */ |
2549 | 0 | tmp13 = tmp10 + tmp11 + tmp12 - |
2550 | 0 | MULTIPLY(z1, FIX(1.835730603)); /* c9+c11+c13-c15 */ |
2551 | 0 | z1 = MULTIPLY(z2 + z3, FIX(0.138617169)); /* c15 */ |
2552 | 0 | tmp1 += z1 + MULTIPLY(z2, FIX(0.071888074)); /* c9+c11-c3-c15 */ |
2553 | 0 | tmp2 += z1 - MULTIPLY(z3, FIX(1.125726048)); /* c5+c7+c15-c3 */ |
2554 | 0 | z1 = MULTIPLY(z3 - z2, FIX(1.407403738)); /* c1 */ |
2555 | 0 | tmp11 += z1 - MULTIPLY(z3, FIX(0.766367282)); /* c1+c11-c9-c13 */ |
2556 | 0 | tmp12 += z1 + MULTIPLY(z2, FIX(1.971951411)); /* c1+c5+c13-c7 */ |
2557 | 0 | z2 += z4; |
2558 | 0 | z1 = MULTIPLY(z2, -FIX(0.666655658)); /* -c11 */ |
2559 | 0 | tmp1 += z1; |
2560 | 0 | tmp3 += z1 + MULTIPLY(z4, FIX(1.065388962)); /* c3+c11+c15-c7 */ |
2561 | 0 | z2 = MULTIPLY(z2, -FIX(1.247225013)); /* -c5 */ |
2562 | 0 | tmp10 += z2 + MULTIPLY(z4, FIX(3.141271809)); /* c1+c5+c9-c13 */ |
2563 | 0 | tmp12 += z2; |
2564 | 0 | z2 = MULTIPLY(z3 + z4, -FIX(1.353318001)); /* -c3 */ |
2565 | 0 | tmp2 += z2; |
2566 | 0 | tmp3 += z2; |
2567 | 0 | z2 = MULTIPLY(z4 - z3, FIX(0.410524528)); /* c13 */ |
2568 | 0 | tmp10 += z2; |
2569 | 0 | tmp11 += z2; |
2570 | | |
2571 | | /* Final output stage */ |
2572 | |
|
2573 | 0 | outptr[0] = range_limit[(int)RIGHT_SHIFT(tmp20 + tmp0, |
2574 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2575 | 0 | RANGE_MASK]; |
2576 | 0 | outptr[15] = range_limit[(int)RIGHT_SHIFT(tmp20 - tmp0, |
2577 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2578 | 0 | RANGE_MASK]; |
2579 | 0 | outptr[1] = range_limit[(int)RIGHT_SHIFT(tmp21 + tmp1, |
2580 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2581 | 0 | RANGE_MASK]; |
2582 | 0 | outptr[14] = range_limit[(int)RIGHT_SHIFT(tmp21 - tmp1, |
2583 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2584 | 0 | RANGE_MASK]; |
2585 | 0 | outptr[2] = range_limit[(int)RIGHT_SHIFT(tmp22 + tmp2, |
2586 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2587 | 0 | RANGE_MASK]; |
2588 | 0 | outptr[13] = range_limit[(int)RIGHT_SHIFT(tmp22 - tmp2, |
2589 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2590 | 0 | RANGE_MASK]; |
2591 | 0 | outptr[3] = range_limit[(int)RIGHT_SHIFT(tmp23 + tmp3, |
2592 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2593 | 0 | RANGE_MASK]; |
2594 | 0 | outptr[12] = range_limit[(int)RIGHT_SHIFT(tmp23 - tmp3, |
2595 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2596 | 0 | RANGE_MASK]; |
2597 | 0 | outptr[4] = range_limit[(int)RIGHT_SHIFT(tmp24 + tmp10, |
2598 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2599 | 0 | RANGE_MASK]; |
2600 | 0 | outptr[11] = range_limit[(int)RIGHT_SHIFT(tmp24 - tmp10, |
2601 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2602 | 0 | RANGE_MASK]; |
2603 | 0 | outptr[5] = range_limit[(int)RIGHT_SHIFT(tmp25 + tmp11, |
2604 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2605 | 0 | RANGE_MASK]; |
2606 | 0 | outptr[10] = range_limit[(int)RIGHT_SHIFT(tmp25 - tmp11, |
2607 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2608 | 0 | RANGE_MASK]; |
2609 | 0 | outptr[6] = range_limit[(int)RIGHT_SHIFT(tmp26 + tmp12, |
2610 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2611 | 0 | RANGE_MASK]; |
2612 | 0 | outptr[9] = range_limit[(int)RIGHT_SHIFT(tmp26 - tmp12, |
2613 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2614 | 0 | RANGE_MASK]; |
2615 | 0 | outptr[7] = range_limit[(int)RIGHT_SHIFT(tmp27 + tmp13, |
2616 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2617 | 0 | RANGE_MASK]; |
2618 | 0 | outptr[8] = range_limit[(int)RIGHT_SHIFT(tmp27 - tmp13, |
2619 | 0 | CONST_BITS + PASS1_BITS + 3) & |
2620 | 0 | RANGE_MASK]; |
2621 | |
|
2622 | 0 | wsptr += 8; /* advance pointer to next row */ |
2623 | 0 | } |
2624 | 0 | } |
2625 | | |
2626 | | #endif /* IDCT_SCALING_SUPPORTED */ |
2627 | | #endif /* DCT_ISLOW_SUPPORTED */ |