1 ;******************************************************************************
2 ;* MMX/SSE2-optimized functions for the RV30 and RV40 decoders
3 ;* Copyright (C) 2012 Christophe Gisquet <christophe.gisquet@gmail.com>
5 ;* This file is part of Libav.
7 ;* Libav 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.
12 ;* Libav 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.
17 ;* You should have received a copy of the GNU Lesser General Public
18 ;* License along with Libav; if not, write to the Free Software
19 ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20 ;******************************************************************************
23 %include "x86util.asm"
27 %macro IDCT_DC_NOROUND 1
32 %macro IDCT_DC_ROUND 1
39 cglobal rv34_idct_%1_mmx2, 1, 2, 0
52 %define IDCT_DC IDCT_DC_ROUND
54 %define IDCT_DC IDCT_DC_NOROUND
57 ; ff_rv34_idct_dc_add_mmx(uint8_t *dst, int stride, int dc);
58 cglobal rv34_idct_dc_add_mmx, 3, 3
91 ; ff_rv34_idct_dc_add_sse4(uint8_t *dst, int stride, int dc);
93 cglobal rv34_idct_dc_add_sse4, 3, 3, 6
115 pextrd [r0+r1], m2, 1
117 pextrd [r2+r1], m2, 3