/*****************************************************************************
- * dct.h: h264 encoder library
+ * dct.h: transform and zigzag
*****************************************************************************
- * Copyright (C) 2003 Laurent Aimar
- * $Id: dct.h,v 1.1 2004/06/03 19:27:06 fenrir Exp $
+ * Copyright (C) 2004-2011 x264 project
*
- * Authors: Laurent Aimar <fenrir@via.ecp.fr>
+ * Authors: Loren Merritt <lorenm@u.washington.edu>
*
* 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
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111, USA.
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
+ *
+ * This program is also available under a commercial proprietary license.
+ * For more information, contact us at licensing@x264.com.
*****************************************************************************/
-#ifndef _DCT_H
-#define _DCT_H 1
+#ifndef X264_DCT_H
+#define X264_DCT_H
/* the inverse of the scaling factors introduced by 8x8 fdct */
#define W(i) (i==0 ? FIX8(1.0000) :\
i==3 ? FIX8(0.9415) :\
i==4 ? FIX8(1.2651) :\
i==5 ? FIX8(1.1910) :0)
-static const int x264_dct8_weight_tab[64] = {
+static const uint16_t x264_dct8_weight_tab[64] = {
W(0), W(3), W(4), W(3), W(0), W(3), W(4), W(3),
W(3), W(1), W(5), W(1), W(3), W(1), W(5), W(1),
W(4), W(5), W(2), W(5), W(4), W(5), W(2), W(5),
};
#undef W
+#define W(i) (i==0 ? FIX8(1.76777) :\
+ i==1 ? FIX8(1.11803) :\
+ i==2 ? FIX8(0.70711) :0)
+static const uint16_t x264_dct4_weight_tab[16] = {
+ W(0), W(1), W(0), W(1),
+ W(1), W(2), W(1), W(2),
+ W(0), W(1), W(0), W(1),
+ W(1), W(2), W(1), W(2)
+};
+#undef W
+
/* inverse squared */
#define W(i) (i==0 ? FIX8(3.125) :\
i==1 ? FIX8(1.25) :\
i==2 ? FIX8(0.5) :0)
-static const int x264_dct4_weight2_tab[16] = {
+static const uint16_t x264_dct4_weight2_tab[16] = {
W(0), W(1), W(0), W(1),
W(1), W(2), W(1), W(2),
W(0), W(1), W(0), W(1),
W(1), W(2), W(1), W(2)
};
-static const int x264_dct4_weight2_zigzag[16] = {
- W(0), W(1), W(1), W(0), W(2), W(0), W(1), W(1),
- W(1), W(1), W(2), W(0), W(2), W(1), W(1), W(2)
-};
#undef W
#define W(i) (i==0 ? FIX8(1.00000) :\
i==3 ? FIX8(0.88637) :\
i==4 ? FIX8(1.60040) :\
i==5 ? FIX8(1.41850) :0)
-static const int x264_dct8_weight2_tab[64] = {
+static const uint16_t x264_dct8_weight2_tab[64] = {
W(0), W(3), W(4), W(3), W(0), W(3), W(4), W(3),
W(3), W(1), W(5), W(1), W(3), W(1), W(5), W(1),
W(4), W(5), W(2), W(5), W(4), W(5), W(2), W(5),
W(4), W(5), W(2), W(5), W(4), W(5), W(2), W(5),
W(3), W(1), W(5), W(1), W(3), W(1), W(5), W(1)
};
-static const int x264_dct8_weight2_zigzag[64] = {
- W(0), W(3), W(3), W(4), W(1), W(4), W(3), W(5),
- W(5), W(3), W(0), W(1), W(2), W(1), W(0), W(3),
- W(3), W(5), W(5), W(3), W(3), W(4), W(1), W(4),
- W(1), W(4), W(1), W(4), W(3), W(5), W(5), W(3),
- W(3), W(5), W(5), W(3), W(1), W(2), W(1), W(0),
- W(1), W(2), W(1), W(5), W(5), W(3), W(3), W(5),
- W(5), W(1), W(4), W(1), W(4), W(1), W(3), W(5),
- W(5), W(3), W(1), W(2), W(1), W(5), W(5), W(1)
-};
#undef W
+extern uint16_t x264_dct4_weight2_zigzag[2][16]; // [2] = {frame, field}
+extern uint16_t x264_dct8_weight2_zigzag[2][64];
+
typedef struct
{
- void (*sub4x4_dct) ( int16_t dct[4][4], uint8_t *pix1, int i_pix1, uint8_t *pix2, int i_pix2 );
- void (*add4x4_idct) ( uint8_t *p_dst, int i_dst, int16_t dct[4][4] );
+ // pix1 stride = FENC_STRIDE
+ // pix2 stride = FDEC_STRIDE
+ // p_dst stride = FDEC_STRIDE
+ void (*sub4x4_dct) ( dctcoef dct[16], pixel *pix1, pixel *pix2 );
+ void (*add4x4_idct) ( pixel *p_dst, dctcoef dct[16] );
+
+ void (*sub8x8_dct) ( dctcoef dct[4][16], pixel *pix1, pixel *pix2 );
+ void (*sub8x8_dct_dc)( dctcoef dct[4], pixel *pix1, pixel *pix2 );
+ void (*add8x8_idct) ( pixel *p_dst, dctcoef dct[4][16] );
+ void (*add8x8_idct_dc) ( pixel *p_dst, dctcoef dct[4] );
- void (*sub8x8_dct) ( int16_t dct[4][4][4], uint8_t *pix1, int i_pix1, uint8_t *pix2, int i_pix2 );
- void (*add8x8_idct) ( uint8_t *p_dst, int i_dst, int16_t dct[4][4][4] );
+ void (*sub8x16_dct_dc)( dctcoef dct[8], pixel *pix1, pixel *pix2 );
- void (*sub16x16_dct) ( int16_t dct[16][4][4], uint8_t *pix1, int i_pix1, uint8_t *pix2, int i_pix2 );
- void (*add16x16_idct) ( uint8_t *p_dst, int i_dst, int16_t dct[16][4][4] );
+ void (*sub16x16_dct) ( dctcoef dct[16][16], pixel *pix1, pixel *pix2 );
+ void (*add16x16_idct)( pixel *p_dst, dctcoef dct[16][16] );
+ void (*add16x16_idct_dc) ( pixel *p_dst, dctcoef dct[16] );
- void (*sub8x8_dct8) ( int16_t dct[8][8], uint8_t *pix1, int i_pix1, uint8_t *pix2, int i_pix2 );
- void (*add8x8_idct8) ( uint8_t *p_dst, int i_dst, int16_t dct[8][8] );
+ void (*sub8x8_dct8) ( dctcoef dct[64], pixel *pix1, pixel *pix2 );
+ void (*add8x8_idct8) ( pixel *p_dst, dctcoef dct[64] );
- void (*sub16x16_dct8) ( int16_t dct[4][8][8], uint8_t *pix1, int i_pix1, uint8_t *pix2, int i_pix2 );
- void (*add16x16_idct8) ( uint8_t *p_dst, int i_dst, int16_t dct[4][8][8] );
+ void (*sub16x16_dct8) ( dctcoef dct[4][64], pixel *pix1, pixel *pix2 );
+ void (*add16x16_idct8)( pixel *p_dst, dctcoef dct[4][64] );
- void (*dct4x4dc) ( int16_t d[4][4] );
- void (*idct4x4dc)( int16_t d[4][4] );
+ void (*dct4x4dc) ( dctcoef d[16] );
+ void (*idct4x4dc)( dctcoef d[16] );
- void (*dct2x2dc) ( int16_t d[2][2] );
- void (*idct2x2dc)( int16_t d[2][2] );
+ void (*dct2x4dc)( dctcoef dct[8], dctcoef dct4x4[8][16] );
} x264_dct_function_t;
+typedef struct
+{
+ void (*scan_8x8)( dctcoef level[64], dctcoef dct[64] );
+ void (*scan_4x4)( dctcoef level[16], dctcoef dct[16] );
+ int (*sub_8x8) ( dctcoef level[64], const pixel *p_src, pixel *p_dst );
+ int (*sub_4x4) ( dctcoef level[16], const pixel *p_src, pixel *p_dst );
+ int (*sub_4x4ac)( dctcoef level[16], const pixel *p_src, pixel *p_dst, dctcoef *dc );
+ void (*interleave_8x8_cavlc)( dctcoef *dst, dctcoef *src, uint8_t *nnz );
+
+} x264_zigzag_function_t;
+
void x264_dct_init( int cpu, x264_dct_function_t *dctf );
+void x264_dct_init_weights( void );
+void x264_zigzag_init( int cpu, x264_zigzag_function_t *pf_progressive, x264_zigzag_function_t *pf_interlaced );
#endif
projects / x264 / blobdiff