furnace/extern/fftw/doc/html/FFTW-MPI-Performance-Tips.html

105 lines
4.6 KiB
HTML
Raw Normal View History

<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<!-- This manual is for FFTW
(version 3.3.10, 10 December 2020).
Copyright (C) 2003 Matteo Frigo.
Copyright (C) 2003 Massachusetts Institute of Technology.
Permission is granted to make and distribute verbatim copies of this
manual provided the copyright notice and this permission notice are
preserved on all copies.
Permission is granted to copy and distribute modified versions of this
manual under the conditions for verbatim copying, provided that the
entire resulting derived work is distributed under the terms of a
permission notice identical to this one.
Permission is granted to copy and distribute translations of this manual
into another language, under the above conditions for modified versions,
except that this permission notice may be stated in a translation
approved by the Free Software Foundation. -->
<!-- Created by GNU Texinfo 6.7, http://www.gnu.org/software/texinfo/ -->
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>FFTW MPI Performance Tips (FFTW 3.3.10)</title>
<meta name="description" content="FFTW MPI Performance Tips (FFTW 3.3.10)">
<meta name="keywords" content="FFTW MPI Performance Tips (FFTW 3.3.10)">
<meta name="resource-type" content="document">
<meta name="distribution" content="global">
<meta name="Generator" content="makeinfo">
<link href="index.html" rel="start" title="Top">
<link href="Concept-Index.html" rel="index" title="Concept Index">
<link href="index.html#SEC_Contents" rel="contents" title="Table of Contents">
<link href="Distributed_002dmemory-FFTW-with-MPI.html" rel="up" title="Distributed-memory FFTW with MPI">
<link href="Combining-MPI-and-Threads.html" rel="next" title="Combining MPI and Threads">
<link href="Avoiding-MPI-Deadlocks.html" rel="prev" title="Avoiding MPI Deadlocks">
<style type="text/css">
<!--
a.summary-letter {text-decoration: none}
blockquote.indentedblock {margin-right: 0em}
div.display {margin-left: 3.2em}
div.example {margin-left: 3.2em}
div.lisp {margin-left: 3.2em}
kbd {font-style: oblique}
pre.display {font-family: inherit}
pre.format {font-family: inherit}
pre.menu-comment {font-family: serif}
pre.menu-preformatted {font-family: serif}
span.nolinebreak {white-space: nowrap}
span.roman {font-family: initial; font-weight: normal}
span.sansserif {font-family: sans-serif; font-weight: normal}
ul.no-bullet {list-style: none}
-->
</style>
</head>
<body lang="en">
<span id="FFTW-MPI-Performance-Tips"></span><div class="header">
<p>
Next: <a href="Combining-MPI-and-Threads.html" accesskey="n" rel="next">Combining MPI and Threads</a>, Previous: <a href="Avoiding-MPI-Deadlocks.html" accesskey="p" rel="prev">Avoiding MPI Deadlocks</a>, Up: <a href="Distributed_002dmemory-FFTW-with-MPI.html" accesskey="u" rel="up">Distributed-memory FFTW with MPI</a> &nbsp; [<a href="index.html#SEC_Contents" title="Table of contents" rel="contents">Contents</a>][<a href="Concept-Index.html" title="Index" rel="index">Index</a>]</p>
</div>
<hr>
<span id="FFTW-MPI-Performance-Tips-1"></span><h3 class="section">6.10 FFTW MPI Performance Tips</h3>
<p>In this section, we collect a few tips on getting the best performance
out of FFTW&rsquo;s MPI transforms.
</p>
<p>First, because of the 1d block distribution, FFTW&rsquo;s parallelization is
currently limited by the size of the first dimension.
(Multidimensional block distributions may be supported by a future
version.) More generally, you should ideally arrange the dimensions so
that FFTW can divide them equally among the processes. See <a href="Load-balancing.html">Load balancing</a>.
<span id="index-block-distribution-2"></span>
<span id="index-load-balancing-1"></span>
</p>
<p>Second, if it is not too inconvenient, you should consider working
with transposed output for multidimensional plans, as this saves a
considerable amount of communications. See <a href="Transposed-distributions.html">Transposed distributions</a>.
<span id="index-transpose-3"></span>
</p>
<p>Third, the fastest choices are generally either an in-place transform
or an out-of-place transform with the <code>FFTW_DESTROY_INPUT</code> flag
(which allows the input array to be used as scratch space). In-place
is especially beneficial if the amount of data per process is large.
<span id="index-FFTW_005fDESTROY_005fINPUT-1"></span>
</p>
<p>Fourth, if you have multiple arrays to transform at once, rather than
calling FFTW&rsquo;s MPI transforms several times it usually seems to be
faster to interleave the data and use the advanced interface. (This
groups the communications together instead of requiring separate
messages for each transform.)
</p>
</body>
</html>