1 ;*****************************************************************************
2 ;* x86-optimized functions for afir filter
3 ;* Copyright (c) 2017 Paul B Mahol
5 ;* This file is part of FFmpeg.
7 ;* FFmpeg 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 ;* FFmpeg 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 FFmpeg; if not, write to the Free Software
19 ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20 ;******************************************************************************
22 %include "libavutil/x86/x86util.asm"
26 ;------------------------------------------------------------------------------
27 ; void ff_fcmul_add(float *sum, const float *t, const float *c, int len)
28 ;------------------------------------------------------------------------------
31 cglobal fcmul_add, 4,4,6, sum, t, c, len
40 movsldup m0, [tq + lenq]
41 movsldup m3, [tq + lenq+mmsize]
42 movaps m1, [cq + lenq]
43 movaps m4, [cq + lenq+mmsize]
48 movshdup m2, [tq + lenq]
49 movshdup m5, [tq + lenq+mmsize]
54 addps m0, [sumq + lenq]
55 addps m3, [sumq + lenq+mmsize]
56 movaps [sumq + lenq], m0
57 movaps [sumq + lenq+mmsize], m3