Mercurial > libavcodec.hg
view bfin/mathops.h @ 12492:58a960d6e34c libavcodec
Rename h264_idct_sse2.asm to h264_idct.asm; move inline IDCT asm from
h264dsp_mmx.c to h264_idct.asm (as yasm code). Because the loops are now
coded in asm instead of C, this is (depending on the function) up to 50%
faster for cases where gcc didn't do a great job at looping.
Since h264_idct_add8() is now faster than the manual loop setup in h264.c,
in-asm idct calling can now be enabled for chroma as well (see r16207). For
MMX, this is 5% faster. For SSE2 (which isn't done for chroma if h264.c does
the looping), this makes it up to 50% faster. Speed gain overall is ~0.5-1.0%.
author | rbultje |
---|---|
date | Tue, 14 Sep 2010 13:36:26 +0000 |
parents | 25136467a218 |
children |
line wrap: on
line source
/* * simple math operations * * Copyright (C) 2007 Marc Hoffman <mmhoffm@gmail.com> * * 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 */ #ifndef AVCODEC_BFIN_MATHOPS_H #define AVCODEC_BFIN_MATHOPS_H #include "config.h" #if CONFIG_MPEGAUDIO_HP #define MULH(X,Y) ({ int xxo; \ __asm__ ( \ "a1 = %2.L * %1.L (FU);\n\t" \ "a1 = a1 >> 16;\n\t" \ "a1 += %2.H * %1.L (IS,M);\n\t" \ "a0 = %1.H * %2.H, a1+= %1.H * %2.L (IS,M);\n\t"\ "a1 = a1 >>> 16;\n\t" \ "%0 = (a0 += a1);\n\t" \ : "=d" (xxo) : "d" (X), "d" (Y) : "A0","A1"); xxo; }) #else #define MULH(X,Y) ({ int xxo; \ __asm__ ( \ "a1 = %2.H * %1.L (IS,M);\n\t" \ "a0 = %1.H * %2.H, a1+= %1.H * %2.L (IS,M);\n\t"\ "a1 = a1 >>> 16;\n\t" \ "%0 = (a0 += a1);\n\t" \ : "=d" (xxo) : "d" (X), "d" (Y) : "A0","A1"); xxo; }) #endif /* signed 16x16 -> 32 multiply */ #define MUL16(a, b) ({ int xxo; \ __asm__ ( \ "%0 = %1.l*%2.l (is);\n\t" \ : "=W" (xxo) : "d" (a), "d" (b) : "A1"); \ xxo; }) #endif /* AVCODEC_BFIN_MATHOPS_H */