Mercurial > libavcodec.hg
annotate mlpdsp.c @ 11352:6e0af2cfdcfe libavcodec
Do MC and IDCT in coding (hilbert) order
This increases the slice size to 64 pixels, due to having to decode an
entire chroma superblock row per slice.
This can be up to 6% slower depending on clip and CPU, but is necessary
for future optimizations that gain significantly more than was lost.
author | conrad |
---|---|
date | Wed, 03 Mar 2010 23:27:40 +0000 |
parents | 1db34b8dcf15 |
children | 0b220468ba0d |
rev | line source |
---|---|
9585 | 1 /* |
2 * Copyright (c) 2007-2008 Ian Caulfield | |
3 * 2009 Ramiro Polla | |
4 * | |
5 * This file is part of FFmpeg. | |
6 * | |
7 * FFmpeg is free software; you can redistribute it and/or | |
8 * modify it under the terms of the GNU Lesser General Public | |
9 * License as published by the Free Software Foundation; either | |
10 * version 2.1 of the License, or (at your option) any later version. | |
11 * | |
12 * FFmpeg is distributed in the hope that it will be useful, | |
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of | |
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | |
15 * Lesser General Public License for more details. | |
16 * | |
17 * You should have received a copy of the GNU Lesser General Public | |
18 * License along with FFmpeg; if not, write to the Free Software | |
19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA | |
20 */ | |
21 | |
9646
b8b9ff6fa077
mlp: include mlp.h and use MAX_CHANNELS instead of hardcoding value 8.
ramiro
parents:
9585
diff
changeset
|
22 #include "libavcodec/mlp.h" |
9585 | 23 #include "dsputil.h" |
24 | |
9647
d0fe5dc427f0
mlp: Simplify adressing of state and coeffs arrays for both filters by making
ramiro
parents:
9646
diff
changeset
|
25 static void ff_mlp_filter_channel(int32_t *state, const int32_t *coeff, |
d0fe5dc427f0
mlp: Simplify adressing of state and coeffs arrays for both filters by making
ramiro
parents:
9646
diff
changeset
|
26 int firorder, int iirorder, |
9585 | 27 unsigned int filter_shift, int32_t mask, int blocksize, |
28 int32_t *sample_buffer) | |
29 { | |
9647
d0fe5dc427f0
mlp: Simplify adressing of state and coeffs arrays for both filters by making
ramiro
parents:
9646
diff
changeset
|
30 int32_t *firbuf = state; |
d0fe5dc427f0
mlp: Simplify adressing of state and coeffs arrays for both filters by making
ramiro
parents:
9646
diff
changeset
|
31 int32_t *iirbuf = state + MAX_BLOCKSIZE + MAX_FIR_ORDER; |
d0fe5dc427f0
mlp: Simplify adressing of state and coeffs arrays for both filters by making
ramiro
parents:
9646
diff
changeset
|
32 const int32_t *fircoeff = coeff; |
d0fe5dc427f0
mlp: Simplify adressing of state and coeffs arrays for both filters by making
ramiro
parents:
9646
diff
changeset
|
33 const int32_t *iircoeff = coeff + MAX_FIR_ORDER; |
9585 | 34 int i; |
35 | |
36 for (i = 0; i < blocksize; i++) { | |
37 int32_t residual = *sample_buffer; | |
38 unsigned int order; | |
39 int64_t accum = 0; | |
40 int32_t result; | |
41 | |
42 for (order = 0; order < firorder; order++) | |
43 accum += (int64_t) firbuf[order] * fircoeff[order]; | |
44 for (order = 0; order < iirorder; order++) | |
45 accum += (int64_t) iirbuf[order] * iircoeff[order]; | |
46 | |
47 accum = accum >> filter_shift; | |
48 result = (accum + residual) & mask; | |
49 | |
50 *--firbuf = result; | |
51 *--iirbuf = result - accum; | |
52 | |
53 *sample_buffer = result; | |
9646
b8b9ff6fa077
mlp: include mlp.h and use MAX_CHANNELS instead of hardcoding value 8.
ramiro
parents:
9585
diff
changeset
|
54 sample_buffer += MAX_CHANNELS; |
9585 | 55 } |
56 } | |
57 | |
9705 | 58 void ff_mlp_init_x86(DSPContext* c, AVCodecContext *avctx); |
59 | |
9585 | 60 void ff_mlp_init(DSPContext* c, AVCodecContext *avctx) |
61 { | |
62 c->mlp_filter_channel = ff_mlp_filter_channel; | |
9705 | 63 if (ARCH_X86) |
64 ff_mlp_init_x86(c, avctx); | |
9585 | 65 } |