From 449aab3c465bbbf66d221fac3d7ea559f1720357 Mon Sep 17 00:00:00 2001 From: Paul Davis Date: Mon, 2 Jun 2008 21:41:35 +0000 Subject: rollback to 3428, before the mysterious removal of libs/* at 3431/3432 git-svn-id: svn://localhost/ardour2/branches/3.0@3435 d708f5d6-7413-0410-9779-e7cbd77b26cf --- libs/ardour/sse_functions_xmm.cc | 116 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 libs/ardour/sse_functions_xmm.cc (limited to 'libs/ardour/sse_functions_xmm.cc') diff --git a/libs/ardour/sse_functions_xmm.cc b/libs/ardour/sse_functions_xmm.cc new file mode 100644 index 0000000000..9b37c37912 --- /dev/null +++ b/libs/ardour/sse_functions_xmm.cc @@ -0,0 +1,116 @@ +/* + 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 +#include + +void +x86_sse_find_peaks(const ARDOUR::Sample* buf, 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); +} + + + -- cgit v1.2.3