view ppc/mathops.h @ 4980:800a543a2513 libavcodec

tweak mmx2 sad. 40% faster on core2, 18% faster on k8, 5% faster on p4.
author lorenm
date Fri, 11 May 2007 00:45:07 +0000
parents c8c591fe26f8
children 9ecbfc0c82bf
line wrap: on
line source

/*
 * simple math operations
 * Copyright (c) 2001, 2002 Fabrice Bellard.
 * Copyright (c) 2006 Michael Niedermayer <michaelni@gmx.at> et al
 *
 * 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
 */

#if defined(ARCH_POWERPC_405)
/* signed 16x16 -> 32 multiply add accumulate */
#   define MAC16(rt, ra, rb) \
        asm ("maclhw %0, %2, %3" : "=r" (rt) : "0" (rt), "r" (ra), "r" (rb));

/* signed 16x16 -> 32 multiply */
#   define MUL16(ra, rb) \
        ({ int __rt;
         asm ("mullhw %0, %1, %2" : "=r" (__rt) : "r" (ra), "r" (rb));
         __rt; })
#endif