1;*****************************************************************************
2;* x86-optimized Float DSP functions
3;*
4;* Copyright 2016 James Almer
5;*
6;* This file is part of FFmpeg.
7;*
8;* FFmpeg is free software; you can redistribute it and/or
9;* modify it under the terms of the GNU Lesser General Public
10;* License as published by the Free Software Foundation; either
11;* version 2.1 of the License, or (at your option) any later version.
12;*
13;* FFmpeg is distributed in the hope that it will be useful,
14;* but WITHOUT ANY WARRANTY; without even the implied warranty of
15;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
16;* Lesser General Public License for more details.
17;*
18;* You should have received a copy of the GNU Lesser General Public
19;* License along with FFmpeg; if not, write to the Free Software
20;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
21;******************************************************************************
22
23%include "x86util.asm"
24
25SECTION .text
26
27;-----------------------------------------------------------------------------
28; void ff_butterflies_fixed(float *src0, float *src1, int len);
29;-----------------------------------------------------------------------------
30INIT_XMM sse2
31cglobal butterflies_fixed, 3,3,3, src0, src1, len
32    shl       lend, 2
33    add      src0q, lenq
34    add      src1q, lenq
35    neg       lenq
36
37align 16
38.loop:
39    mova        m0, [src0q + lenq]
40    mova        m1, [src1q + lenq]
41    mova        m2, m0
42    paddd       m0, m1
43    psubd       m2, m1
44    mova        [src0q + lenq], m0
45    mova        [src1q + lenq], m2
46    add       lenq, mmsize
47    jl .loop
48    RET
49