--- mem_transfer.c 2002/11/17 00:51:11 1.7 +++ mem_transfer.c 2005/06/14 13:58:21 1.14 @@ -1,56 +1,25 @@ /***************************************************************************** * * XVID MPEG-4 VIDEO CODEC - * - 8bit<->16bit transfer - + * - 8bit<->16bit transfer - * - * Copyright(C) 2001-2002 Peter Ross + * Copyright(C) 2001-2003 Peter Ross * - * This file is part of XviD, a free MPEG-4 video encoder/decoder - * - * XviD is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or + * This program is free software ; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation ; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of + * but WITHOUT ANY WARRANTY ; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software + * along with this program ; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * - * Under section 8 of the GNU General Public License, the copyright - * holders of XVID explicitly forbid distribution in the following - * countries: - * - * - Japan - * - United States of America - * - * Linking XviD statically or dynamically with other modules is making a - * combined work based on XviD. Thus, the terms and conditions of the - * GNU General Public License cover the whole combination. - * - * As a special exception, the copyright holders of XviD give you - * permission to link XviD with independent modules that communicate with - * XviD solely through the VFW1.1 and DShow interfaces, regardless of the - * license terms of these independent modules, and to copy and distribute - * the resulting combined work under terms of your choice, provided that - * every copy of the combined work is accompanied by a complete copy of - * the source code of XviD (the version of XviD used to produce the - * combined work), being distributed under the terms of the GNU General - * Public License plus this exception. An independent module is a module - * which is not derived from or based on XviD. - * - * Note that people who make modified versions of XviD are not obligated - * to grant this special exception for their modified versions; it is - * their choice whether to do so. The GNU General Public License gives - * permission to release a modified version without this exception; this - * exception also makes it possible to release a modified version which - * carries forward this exception. - * - * $Id: mem_transfer.c,v 1.7 2002/11/17 00:51:11 edgomez Exp $ + * $Id: mem_transfer.c,v 1.14 2005/06/14 13:58:21 Skal Exp $ * ****************************************************************************/ @@ -63,11 +32,14 @@ TRANSFER_16TO8COPY_PTR transfer_16to8copy; TRANSFER_8TO16SUB_PTR transfer_8to16sub; +TRANSFER_8TO16SUBRO_PTR transfer_8to16subro; TRANSFER_8TO16SUB2_PTR transfer_8to16sub2; +TRANSFER_8TO16SUB2RO_PTR transfer_8to16sub2ro; TRANSFER_16TO8ADD_PTR transfer_16to8add; TRANSFER8X8_COPY_PTR transfer8x8_copy; +#define USE_REFERENCE_C /***************************************************************************** * @@ -94,12 +66,11 @@ const uint8_t * const src, uint32_t stride) { - uint32_t i, j; - + int i, j; for (j = 0; j < 8; j++) { for (i = 0; i < 8; i++) { dst[j * 8 + i] = (int16_t) src[j * stride + i]; - } + } } } @@ -117,10 +88,11 @@ const int16_t * const src, uint32_t stride) { - uint32_t i, j; + int i, j; for (j = 0; j < 8; j++) { for (i = 0; i < 8; i++) { +#ifdef USE_REFERENCE_C int16_t pixel = src[j * 8 + i]; if (pixel < 0) { @@ -129,7 +101,12 @@ pixel = 255; } dst[j * stride + i] = (uint8_t) pixel; - } +#else + const int16_t pixel = src[j * 8 + i]; + const uint8_t value = (uint8_t)( (pixel&~255) ? (-pixel)>>(8*sizeof(pixel)-1) : pixel ); + dst[j*stride + i] = value; +#endif + } } } @@ -153,12 +130,12 @@ const uint8_t * ref, const uint32_t stride) { - uint32_t i, j; + int i, j; for (j = 0; j < 8; j++) { for (i = 0; i < 8; i++) { - uint8_t c = cur[j * stride + i]; - uint8_t r = ref[j * stride + i]; + const uint8_t c = cur[j * stride + i]; + const uint8_t r = ref[j * stride + i]; cur[j * stride + i] = r; dct[j * 8 + i] = (int16_t) c - (int16_t) r; @@ -167,6 +144,25 @@ } +void +transfer_8to16subro_c(int16_t * const dct, + const uint8_t * const cur, + const uint8_t * ref, + const uint32_t stride) +{ + int i, j; + + for (j = 0; j < 8; j++) { + for (i = 0; i < 8; i++) { + const uint8_t c = cur[j * stride + i]; + const uint8_t r = ref[j * stride + i]; + dct[j * 8 + i] = (int16_t) c - (int16_t) r; + } + } +} + + + /* * C - the current buffer * R1 - the 1st reference buffer @@ -177,8 +173,9 @@ * * R1 (8bit) = R1 * R2 (8bit) = R2 - * C (8bit) = C - * DCT (16bit)= C - min((R1 + R2)/2, 255) + * R (temp) = min((R1 + R2)/2, 255) + * DCT (16bit)= C - R + * C (8bit) = R */ void transfer_8to16sub2_c(int16_t * const dct, @@ -191,13 +188,27 @@ for (j = 0; j < 8; j++) { for (i = 0; i < 8; i++) { - uint8_t c = cur[j * stride + i]; - int r = (ref1[j * stride + i] + ref2[j * stride + i] + 1) / 2; + const uint8_t c = cur[j * stride + i]; + const uint8_t r = (ref1[j * stride + i] + ref2[j * stride + i] + 1) >> 1; + cur[j * stride + i] = r; + dct[j * 8 + i] = (int16_t) c - (int16_t) r; + } + } +} - if (r > 255) { - r = 255; - } - //cur[j * stride + i] = r; +void +transfer_8to16sub2ro_c(int16_t * const dct, + const uint8_t * const cur, + const uint8_t * ref1, + const uint8_t * ref2, + const uint32_t stride) +{ + uint32_t i, j; + + for (j = 0; j < 8; j++) { + for (i = 0; i < 8; i++) { + const uint8_t c = cur[j * stride + i]; + const uint8_t r = (ref1[j * stride + i] + ref2[j * stride + i] + 1) >> 1; dct[j * 8 + i] = (int16_t) c - (int16_t) r; } } @@ -218,10 +229,11 @@ const int16_t * const src, uint32_t stride) { - uint32_t i, j; + int i, j; for (j = 0; j < 8; j++) { for (i = 0; i < 8; i++) { +#ifdef USE_REFERENCE_C int16_t pixel = (int16_t) dst[j * stride + i] + src[j * 8 + i]; if (pixel < 0) { @@ -230,6 +242,12 @@ pixel = 255; } dst[j * stride + i] = (uint8_t) pixel; +#else + const int16_t pixel = (int16_t) dst[j * stride + i] + src[j * 8 + i]; + const uint8_t value = (uint8_t)( (pixel&~255) ? (-pixel)>>(8*sizeof(pixel)-1) : pixel ); + dst[j*stride + i] = value; +#endif + } } } @@ -248,11 +266,15 @@ const uint8_t * const src, const uint32_t stride) { - uint32_t i, j; + int j, i; - for (j = 0; j < 8; j++) { - for (i = 0; i < 8; i++) { - dst[j * stride + i] = src[j * stride + i]; + for (j = 0; j < 8; ++j) { + uint8_t *d = dst + j*stride; + const uint8_t *s = src + j*stride; + + for (i = 0; i < 8; ++i) + { + *d++ = *s++; } } }