1 /*****************************************************************************
2 * predict.c: h264 encoder
3 *****************************************************************************
4 * Copyright (C) 2007-2008 Guillaume Poirier <gpoirier@mplayerhq.hu>
6 * This program is free software; you can redistribute it and/or modify
7 * it under the terms of the GNU General Public License as published by
8 * the Free Software Foundation; either version 2 of the License, or
9 * (at your option) any later version.
11 * This program is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 * GNU General Public License for more details.
16 * You should have received a copy of the GNU General Public License
17 * along with this program; if not, write to the Free Software
18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
19 *****************************************************************************/
25 #include "common/common.h"
28 #include "ppccommon.h"
30 static void predict_16x16_p_altivec( uint8_t *src )
37 for( i = 1; i <= 8; i++ )
39 H += i * ( src[7+i - FDEC_STRIDE ] - src[7-i - FDEC_STRIDE ] );
40 V += i * ( src[(7+i)*FDEC_STRIDE -1] - src[(7-i)*FDEC_STRIDE -1] );
43 a = 16 * ( src[15*FDEC_STRIDE -1] + src[15 - FDEC_STRIDE] );
44 b = ( 5 * H + 32 ) >> 6;
45 c = ( 5 * V + 32 ) >> 6;
46 i00 = a - b * 7 - c * 7 + 16;
48 vect_sshort_u i00_u, b_u, c_u;
53 vec_u16_t val5_v = vec_splat_u16(5);
54 vec_s16_t i00_v, b_v, c_v;
55 i00_v = vec_splat(i00_u.v, 0);
56 b_v = vec_splat(b_u.v, 0);
57 c_v = vec_splat(c_u.v, 0);
58 vec_s16_t induc_v = (vec_s16_t) CV(0, 1, 2, 3, 4, 5, 6, 7);
59 vec_s16_t b8_v = vec_sl(b_v, vec_splat_u16(3));
60 vec_s32_t mule_b_v = vec_mule(induc_v, b_v);
61 vec_s32_t mulo_b_v = vec_mulo(induc_v, b_v);
62 vec_s16_t mul_b_induc0_v = vec_pack(vec_mergeh(mule_b_v, mulo_b_v), vec_mergel(mule_b_v, mulo_b_v));
63 vec_s16_t add_i0_b_0v = vec_adds(i00_v, mul_b_induc0_v);
64 vec_s16_t add_i0_b_8v = vec_adds(b8_v, add_i0_b_0v);
68 for( y = 0; y < 16; y++ )
70 vec_s16_t shift_0_v = vec_sra(add_i0_b_0v, val5_v);
71 vec_s16_t shift_8_v = vec_sra(add_i0_b_8v, val5_v);
72 vec_u8_t com_sat_v = vec_packsu(shift_0_v, shift_8_v);
73 vec_st( com_sat_v, 0, &src[0]);
76 add_i0_b_0v = vec_adds(add_i0_b_0v, c_v);
77 add_i0_b_8v = vec_adds(add_i0_b_8v, c_v);
81 /****************************************************************************
83 ****************************************************************************/
84 void x264_predict_16x16_init_altivec( x264_predict_t pf[7] )
86 pf[I_PRED_16x16_P] = predict_16x16_p_altivec;