Mercurial > libavcodec.hg
view mlpdsp.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 | 0b220468ba0d |
children |
line wrap: on
line source
/* * Copyright (c) 2007-2008 Ian Caulfield * 2009 Ramiro Polla * * 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 "libavcodec/mlp.h" #include "dsputil.h" static void ff_mlp_filter_channel(int32_t *state, const int32_t *coeff, int firorder, int iirorder, unsigned int filter_shift, int32_t mask, int blocksize, int32_t *sample_buffer) { int32_t *firbuf = state; int32_t *iirbuf = state + MAX_BLOCKSIZE + MAX_FIR_ORDER; const int32_t *fircoeff = coeff; const int32_t *iircoeff = coeff + MAX_FIR_ORDER; int i; for (i = 0; i < blocksize; i++) { int32_t residual = *sample_buffer; unsigned int order; int64_t accum = 0; int32_t result; for (order = 0; order < firorder; order++) accum += (int64_t) firbuf[order] * fircoeff[order]; for (order = 0; order < iirorder; order++) accum += (int64_t) iirbuf[order] * iircoeff[order]; accum = accum >> filter_shift; result = (accum + residual) & mask; *--firbuf = result; *--iirbuf = result - accum; *sample_buffer = result; sample_buffer += MAX_CHANNELS; } } void ff_mlp_init(DSPContext* c, AVCodecContext *avctx) { c->mlp_filter_channel = ff_mlp_filter_channel; if (ARCH_X86) ff_mlp_init_x86(c, avctx); }