Mercurial > libavcodec.hg
view dcadsp.c @ 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 | 8d3539d6ba3d |
children |
line wrap: on
line source
/* * Copyright (c) 2004 Gildas Bazin * Copyright (c) 2010 Mans Rullgard <mans@mansr.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 */ #include "config.h" #include "dcadsp.h" static void dca_lfe_fir_c(float *out, const float *in, const float *coefs, int decifactor, float scale, float bias) { float *out2 = out + decifactor; const float *cf0 = coefs; const float *cf1 = coefs + 256; int j, k; /* One decimated sample generates 2*decifactor interpolated ones */ for (k = 0; k < decifactor; k++) { float v0 = 0.0; float v1 = 0.0; for (j = 0; j < 256 / decifactor; j++) { float s = in[-j]; v0 += s * *cf0++; v1 += s * *--cf1; } *out++ = (v0 * scale) + bias; *out2++ = (v1 * scale) + bias; } } void ff_dcadsp_init(DCADSPContext *s) { s->lfe_fir = dca_lfe_fir_c; if (ARCH_ARM) ff_dcadsp_init_arm(s); }