<!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>Distributed-memory FFTW with MPI (FFTW 3.3.10)</title>
<meta name="description" content="Distributed-memory FFTW with MPI (FFTW 3.3.10)">
<meta name="keywords" content="Distributed-memory FFTW with MPI (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="index.html" rel="up" title="Top">
<link href="FFTW-MPI-Installation.html" rel="next" title="FFTW MPI Installation">
<link href="Thread-safety.html" rel="prev" title="Thread safety">
<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="Distributed_002dmemory-FFTW-with-MPI"></span><div class="header">
<p>
Next: <a href="Calling-FFTW-from-Modern-Fortran.html" accesskey="n" rel="next">Calling FFTW from Modern Fortran</a>, Previous: <a href="Multi_002dthreaded-FFTW.html" accesskey="p" rel="prev">Multi-threaded FFTW</a>, Up: <a href="index.html" accesskey="u" rel="up">Top</a> [<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="Distributed_002dmemory-FFTW-with-MPI-1"></span><h2 class="chapter">6 Distributed-memory FFTW with MPI</h2>
<span id="index-MPI"></span>
<span id="index-parallel-transform-1"></span>
<p>In this chapter we document the parallel FFTW routines for parallel
systems supporting the MPI message-passing interface. Unlike the
shared-memory threads described in the previous chapter, MPI allows
you to use <em>distributed-memory</em> parallelism, where each CPU has
its own separate memory, and which can scale up to clusters of many
thousands of processors. This capability comes at a price, however:
each process only stores a <em>portion</em> of the data to be
transformed, which means that the data structures and
programming-interface are quite different from the serial or threads
versions of FFTW.
<span id="index-data-distribution"></span>
</p>
<p>Distributed-memory parallelism is especially useful when you are
transforming arrays so large that they do not fit into the memory of a
single processor. The storage per-process required by FFTW’s MPI
routines is proportional to the total array size divided by the number
of processes. Conversely, distributed-memory parallelism can easily
pose an unacceptably high communications overhead for small problems;
the threshold problem size for which parallelism becomes advantageous
will depend on the precise problem you are interested in, your
hardware, and your MPI implementation.
</p>
<p>A note on terminology: in MPI, you divide the data among a set of
“processes” which each run in their own memory address space.
Generally, each process runs on a different physical processor, but
this is not required. A set of processes in MPI is described by an
opaque data structure called a “communicator,” the most common of
which is the predefined communicator <code>MPI_COMM_WORLD</code> which
refers to <em>all</em> processes. For more information on these and
other concepts common to all MPI programs, we refer the reader to the
documentation at <a href="http://www.mcs.anl.gov/research/projects/mpi/">the MPI home
page</a>.
<span id="index-MPI-communicator"></span>
<span id="index-MPI_005fCOMM_005fWORLD"></span>
</p>
<p>We assume in this chapter that the reader is familiar with the usage
of the serial (uniprocessor) FFTW, and focus only on the concepts new
to the MPI interface.
</p>
<table class="menu" border="0" cellspacing="0">
<tr><td align="left" valign="top">• <a href="FFTW-MPI-Installation.html" accesskey="1">FFTW MPI Installation</a></td><td> </td><td align="left" valign="top">
</td></tr>
<tr><td align="left" valign="top">• <a href="Linking-and-Initializing-MPI-FFTW.html" accesskey="2">Linking and Initializing MPI FFTW</a></td><td> </td><td align="left" valign="top">
</td></tr>
<tr><td align="left" valign="top">• <a href="2d-MPI-example.html" accesskey="3">2d MPI example</a></td><td> </td><td align="left" valign="top">
</td></tr>
<tr><td align="left" valign="top">• <a href="MPI-Data-Distribution.html" accesskey="4">MPI Data Distribution</a></td><td> </td><td align="left" valign="top">
</td></tr>
<tr><td align="left" valign="top">• <a href="Multi_002ddimensional-MPI-DFTs-of-Real-Data.html" accesskey="5">Multi-dimensional MPI DFTs of Real Data</a></td><td> </td><td align="left" valign="top">
</td></tr>
<tr><td align="left" valign="top">• <a href="Other-Multi_002ddimensional-Real_002ddata-MPI-Transforms.html" accesskey="6">Other Multi-dimensional Real-data MPI Transforms</a></td><td> </td><td align="left" valign="top">
</td></tr>
<tr><td align="left" valign="top">• <a href="FFTW-MPI-Transposes.html" accesskey="7">FFTW MPI Transposes</a></td><td> </td><td align="left" valign="top">
</td></tr>
<tr><td align="left" valign="top">• <a href="FFTW-MPI-Wisdom.html" accesskey="8">FFTW MPI Wisdom</a></td><td> </td><td align="left" valign="top">
</td></tr>
<tr><td align="left" valign="top">• <a href="Avoiding-MPI-Deadlocks.html" accesskey="9">Avoiding MPI Deadlocks</a></td><td> </td><td align="left" valign="top">
</td></tr>
<tr><td align="left" valign="top">• <a href="FFTW-MPI-Performance-Tips.html">FFTW MPI Performance Tips</a></td><td> </td><td align="left" valign="top">
</td></tr>
<tr><td align="left" valign="top">• <a href="Combining-MPI-and-Threads.html">Combining MPI and Threads</a></td><td> </td><td align="left" valign="top">
</td></tr>
<tr><td align="left" valign="top">• <a href="FFTW-MPI-Reference.html">FFTW MPI Reference</a></td><td> </td><td align="left" valign="top">
</td></tr>
<tr><td align="left" valign="top">• <a href="FFTW-MPI-Fortran-Interface.html">FFTW MPI Fortran Interface</a></td><td> </td><td align="left" valign="top">
</td></tr>
</table>
<hr>
<div class="header">
<p>
Next: <a href="Calling-FFTW-from-Modern-Fortran.html" accesskey="n" rel="next">Calling FFTW from Modern Fortran</a>, Previous: <a href="Multi_002dthreaded-FFTW.html" accesskey="p" rel="prev">Multi-threaded FFTW</a>, Up: <a href="index.html" accesskey="u" rel="up">Top</a> [<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>
</body>
</html>