view mjpeg.c @ 12197:fbf4d5b1b664 libavcodec

Remove FF_MM_SSE2/3 flags for CPUs where this is generally not faster than regular MMX code. Examples of this are the Core1 CPU. Instead, set a new flag, FF_MM_SSE2/3SLOW, which can be checked for particular SSE2/3 functions that have been checked specifically on such CPUs and are actually faster than their MMX counterparts. In addition, use this flag to enable particular VP8 and LPC SSE2 functions that are faster than their MMX counterparts. Based on a patch by Loren Merritt <lorenm AT u washington edu>.

/*
 * MJPEG encoder and decoder
 * Copyright (c) 2000, 2001 Fabrice Bellard
 * Copyright (c) 2003 Alex Beregszaszi
 * Copyright (c) 2003-2004 Michael Niedermayer
 *
 * Support for external huffman table, various fixes (AVID workaround),
 * aspecting, new decode_frame mechanism and apple mjpeg-b support
 *                                  by Alex Beregszaszi
 *
 * This file is part of FFmpeg.
 *
 * FFmpeg is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * FFmpeg is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with FFmpeg; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

/**
 * @file
 * MJPEG encoder and decoder.
 */

#include "mjpeg.h"


#if 0
/* These are the sample quantization tables given in JPEG spec section K.1.
 * The spec says that the values given produce "good" quality, and
 * when divided by 2, "very good" quality.
 */
const unsigned char std_luminance_quant_tbl[64] = {
    16,  11,  10,  16,  24,  40,  51,  61,
    12,  12,  14,  19,  26,  58,  60,  55,
    14,  13,  16,  24,  40,  57,  69,  56,
    14,  17,  22,  29,  51,  87,  80,  62,
    18,  22,  37,  56,  68, 109, 103,  77,
    24,  35,  55,  64,  81, 104, 113,  92,
    49,  64,  78,  87, 103, 121, 120, 101,
    72,  92,  95,  98, 112, 100, 103,  99
};
const unsigned char std_chrominance_quant_tbl[64] = {
    17,  18,  24,  47,  99,  99,  99,  99,
    18,  21,  26,  66,  99,  99,  99,  99,
    24,  26,  56,  99,  99,  99,  99,  99,
    47,  66,  99,  99,  99,  99,  99,  99,
    99,  99,  99,  99,  99,  99,  99,  99,
    99,  99,  99,  99,  99,  99,  99,  99,
    99,  99,  99,  99,  99,  99,  99,  99,
    99,  99,  99,  99,  99,  99,  99,  99
};
#endif

/* Set up the standard Huffman tables (cf. JPEG standard section K.3) */
/* IMPORTANT: these are only valid for 8-bit data precision! */
const uint8_t ff_mjpeg_bits_dc_luminance[17] =
{ /* 0-base */ 0, 0, 1, 5, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0 };
const uint8_t ff_mjpeg_val_dc[12] =
{ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 };

const uint8_t ff_mjpeg_bits_dc_chrominance[17] =
{ /* 0-base */ 0, 0, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0 };

const uint8_t ff_mjpeg_bits_ac_luminance[17] =
{ /* 0-base */ 0, 0, 2, 1, 3, 3, 2, 4, 3, 5, 5, 4, 4, 0, 0, 1, 0x7d };
const uint8_t ff_mjpeg_val_ac_luminance[] =
{ 0x01, 0x02, 0x03, 0x00, 0x04, 0x11, 0x05, 0x12,
  0x21, 0x31, 0x41, 0x06, 0x13, 0x51, 0x61, 0x07,
  0x22, 0x71, 0x14, 0x32, 0x81, 0x91, 0xa1, 0x08,
  0x23, 0x42, 0xb1, 0xc1, 0x15, 0x52, 0xd1, 0xf0,
  0x24, 0x33, 0x62, 0x72, 0x82, 0x09, 0x0a, 0x16,
  0x17, 0x18, 0x19, 0x1a, 0x25, 0x26, 0x27, 0x28,
  0x29, 0x2a, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39,
  0x3a, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49,
  0x4a, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59,
  0x5a, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69,
  0x6a, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79,
  0x7a, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89,
  0x8a, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98,
  0x99, 0x9a, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7,
  0xa8, 0xa9, 0xaa, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6,
  0xb7, 0xb8, 0xb9, 0xba, 0xc2, 0xc3, 0xc4, 0xc5,
  0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xd2, 0xd3, 0xd4,
  0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xe1, 0xe2,
  0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea,
  0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8,
  0xf9, 0xfa
};

const uint8_t ff_mjpeg_bits_ac_chrominance[17] =
{ /* 0-base */ 0, 0, 2, 1, 2, 4, 4, 3, 4, 7, 5, 4, 4, 0, 1, 2, 0x77 };

const uint8_t ff_mjpeg_val_ac_chrominance[] =
{ 0x00, 0x01, 0x02, 0x03, 0x11, 0x04, 0x05, 0x21,
  0x31, 0x06, 0x12, 0x41, 0x51, 0x07, 0x61, 0x71,
  0x13, 0x22, 0x32, 0x81, 0x08, 0x14, 0x42, 0x91,
  0xa1, 0xb1, 0xc1, 0x09, 0x23, 0x33, 0x52, 0xf0,
  0x15, 0x62, 0x72, 0xd1, 0x0a, 0x16, 0x24, 0x34,
  0xe1, 0x25, 0xf1, 0x17, 0x18, 0x19, 0x1a, 0x26,
  0x27, 0x28, 0x29, 0x2a, 0x35, 0x36, 0x37, 0x38,
  0x39, 0x3a, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48,
  0x49, 0x4a, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58,
  0x59, 0x5a, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68,
  0x69, 0x6a, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78,
  0x79, 0x7a, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
  0x88, 0x89, 0x8a, 0x92, 0x93, 0x94, 0x95, 0x96,
  0x97, 0x98, 0x99, 0x9a, 0xa2, 0xa3, 0xa4, 0xa5,
  0xa6, 0xa7, 0xa8, 0xa9, 0xaa, 0xb2, 0xb3, 0xb4,
  0xb5, 0xb6, 0xb7, 0xb8, 0xb9, 0xba, 0xc2, 0xc3,
  0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xd2,
  0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda,
  0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9,
  0xea, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8,
  0xf9, 0xfa
};

/* isn't this function nicer than the one in the libjpeg ? */
void ff_mjpeg_build_huffman_codes(uint8_t *huff_size, uint16_t *huff_code,
                                  const uint8_t *bits_table,
                                  const uint8_t *val_table)
{
    int i, j, k,nb, code, sym;

    code = 0;
    k = 0;
    for(i=1;i<=16;i++) {
        nb = bits_table[i];
        for(j=0;j<nb;j++) {
            sym = val_table[k++];
            huff_size[sym] = i;
            huff_code[sym] = code;
            code++;
        }
        code <<= 1;
    }
}