13
0
livetrax/libs/ardour/sse_functions_xmm.cc
Paul Davis c4ac437490 * libardour uses ARDOUR::nframes_t and ARDOUR::nframes64_t explicitly in headers
* use explicit operator<< and operator>> that in turn use PBD::EnumWriter when serializing and deserializing to/from rc files
* adds scrolling in mixer window (from 2.X)
* BBT math stuff - untested, but basically operational
* move LocaleGuard into its own file(s) in libs/pbd
* Tempo now uses nframes64_t everywhere (except for sample rate values)
* as in 2.X, use mkstemp and hack to avoid temp file nonsense, and remove erroneous free() from disk stats output


git-svn-id: svn://localhost/ardour2/branches/3.0@5961 d708f5d6-7413-0410-9779-e7cbd77b26cf
2009-10-28 21:36:40 +00:00

117 lines
3.3 KiB
C++

/*
Copyright (C) 2007 Paul sDavis
Written by Sampo Savolainen
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program 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 General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <xmmintrin.h>
#include "ardour/types.h"
void
x86_sse_find_peaks(const ARDOUR::Sample* buf, ARDOUR::nframes_t nframes, float *min, float *max)
{
__m128 current_max, current_min, work;
// Load max and min values into all four slots of the XMM registers
current_min = _mm_set1_ps(*min);
current_max = _mm_set1_ps(*max);
// Work input until "buf" reaches 16 byte alignment
while ( ((unsigned long)buf) % 16 != 0 && nframes > 0) {
// Load the next float into the work buffer
work = _mm_set1_ps(*buf);
current_min = _mm_min_ps(current_min, work);
current_max = _mm_max_ps(current_max, work);
buf++;
nframes--;
}
// use 64 byte prefetch for quadruple quads
while (nframes >= 16) {
__builtin_prefetch(buf+64,0,0);
work = _mm_load_ps(buf);
current_min = _mm_min_ps(current_min, work);
current_max = _mm_max_ps(current_max, work);
buf+=4;
work = _mm_load_ps(buf);
current_min = _mm_min_ps(current_min, work);
current_max = _mm_max_ps(current_max, work);
buf+=4;
work = _mm_load_ps(buf);
current_min = _mm_min_ps(current_min, work);
current_max = _mm_max_ps(current_max, work);
buf+=4;
work = _mm_load_ps(buf);
current_min = _mm_min_ps(current_min, work);
current_max = _mm_max_ps(current_max, work);
buf+=4;
nframes-=16;
}
// work through aligned buffers
while (nframes >= 4) {
work = _mm_load_ps(buf);
current_min = _mm_min_ps(current_min, work);
current_max = _mm_max_ps(current_max, work);
buf+=4;
nframes-=4;
}
// work through the rest < 4 samples
while ( nframes > 0) {
// Load the next float into the work buffer
work = _mm_set1_ps(*buf);
current_min = _mm_min_ps(current_min, work);
current_max = _mm_max_ps(current_max, work);
buf++;
nframes--;
}
// Find min & max value in current_max through shuffle tricks
work = current_min;
work = _mm_shuffle_ps(work, work, _MM_SHUFFLE(2, 3, 0, 1));
work = _mm_min_ps (work, current_min);
current_min = work;
work = _mm_shuffle_ps(work, work, _MM_SHUFFLE(1, 0, 3, 2));
work = _mm_min_ps (work, current_min);
_mm_store_ss(min, work);
work = current_max;
work = _mm_shuffle_ps(work, work, _MM_SHUFFLE(2, 3, 0, 1));
work = _mm_max_ps (work, current_max);
current_max = work;
work = _mm_shuffle_ps(work, work, _MM_SHUFFLE(1, 0, 3, 2));
work = _mm_max_ps (work, current_max);
_mm_store_ss(max, work);
}