Mercurial > hg > sv-dependency-builds

annotate src/fftw-3.3.8/doc/html/Combining-MPI-and-Threads.html @ 83:ae30d91d2ffe

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Replace these with versions built using an older toolset (so as to avoid ABI compatibilities when linking on Ubuntu 14.04 for packaging purposes)
author Chris Cannam
date Fri, 07 Feb 2020 11:51:13 +0000
parents d0c2a83c1364
children
rev   line source
Chris@82 1 <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
Chris@82 2 <html>
Chris@82 3 <!-- This manual is for FFTW
Chris@82 4 (version 3.3.8, 24 May 2018).
Chris@82 5
Chris@82 6 Copyright (C) 2003 Matteo Frigo.
Chris@82 7
Chris@82 8 Copyright (C) 2003 Massachusetts Institute of Technology.
Chris@82 9
Chris@82 10 Permission is granted to make and distribute verbatim copies of this
Chris@82 11 manual provided the copyright notice and this permission notice are
Chris@82 12 preserved on all copies.
Chris@82 13
Chris@82 14 Permission is granted to copy and distribute modified versions of this
Chris@82 15 manual under the conditions for verbatim copying, provided that the
Chris@82 16 entire resulting derived work is distributed under the terms of a
Chris@82 17 permission notice identical to this one.
Chris@82 18
Chris@82 19 Permission is granted to copy and distribute translations of this manual
Chris@82 20 into another language, under the above conditions for modified versions,
Chris@82 21 except that this permission notice may be stated in a translation
Chris@82 22 approved by the Free Software Foundation. -->
Chris@82 23 <!-- Created by GNU Texinfo 6.3, http://www.gnu.org/software/texinfo/ -->
Chris@82 24 <head>
Chris@82 25 <title>FFTW 3.3.8: Combining MPI and Threads</title>
Chris@82 26
Chris@82 27 <meta name="description" content="FFTW 3.3.8: Combining MPI and Threads">
Chris@82 28 <meta name="keywords" content="FFTW 3.3.8: Combining MPI and Threads">
Chris@82 29 <meta name="resource-type" content="document">
Chris@82 30 <meta name="distribution" content="global">
Chris@82 31 <meta name="Generator" content="makeinfo">
Chris@82 32 <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
Chris@82 33 <link href="index.html#Top" rel="start" title="Top">
Chris@82 34 <link href="Concept-Index.html#Concept-Index" rel="index" title="Concept Index">
Chris@82 35 <link href="index.html#SEC_Contents" rel="contents" title="Table of Contents">
Chris@82 36 <link href="Distributed_002dmemory-FFTW-with-MPI.html#Distributed_002dmemory-FFTW-with-MPI" rel="up" title="Distributed-memory FFTW with MPI">
Chris@82 37 <link href="FFTW-MPI-Reference.html#FFTW-MPI-Reference" rel="next" title="FFTW MPI Reference">
Chris@82 38 <link href="FFTW-MPI-Performance-Tips.html#FFTW-MPI-Performance-Tips" rel="prev" title="FFTW MPI Performance Tips">
Chris@82 39 <style type="text/css">
Chris@82 40 <!--
Chris@82 41 a.summary-letter {text-decoration: none}
Chris@82 42 blockquote.indentedblock {margin-right: 0em}
Chris@82 43 blockquote.smallindentedblock {margin-right: 0em; font-size: smaller}
Chris@82 44 blockquote.smallquotation {font-size: smaller}
Chris@82 45 div.display {margin-left: 3.2em}
Chris@82 46 div.example {margin-left: 3.2em}
Chris@82 47 div.lisp {margin-left: 3.2em}
Chris@82 48 div.smalldisplay {margin-left: 3.2em}
Chris@82 49 div.smallexample {margin-left: 3.2em}
Chris@82 50 div.smalllisp {margin-left: 3.2em}
Chris@82 51 kbd {font-style: oblique}
Chris@82 52 pre.display {font-family: inherit}
Chris@82 53 pre.format {font-family: inherit}
Chris@82 54 pre.menu-comment {font-family: serif}
Chris@82 55 pre.menu-preformatted {font-family: serif}
Chris@82 56 pre.smalldisplay {font-family: inherit; font-size: smaller}
Chris@82 57 pre.smallexample {font-size: smaller}
Chris@82 58 pre.smallformat {font-family: inherit; font-size: smaller}
Chris@82 59 pre.smalllisp {font-size: smaller}
Chris@82 60 span.nolinebreak {white-space: nowrap}
Chris@82 61 span.roman {font-family: initial; font-weight: normal}
Chris@82 62 span.sansserif {font-family: sans-serif; font-weight: normal}
Chris@82 63 ul.no-bullet {list-style: none}
Chris@82 64 -->
Chris@82 65 </style>
Chris@82 66
Chris@82 67
Chris@82 68 </head>
Chris@82 69
Chris@82 70 <body lang="en">
Chris@82 71 <a name="Combining-MPI-and-Threads"></a>
Chris@82 72 <div class="header">
Chris@82 73 <p>
Chris@82 74 Next: <a href="FFTW-MPI-Reference.html#FFTW-MPI-Reference" accesskey="n" rel="next">FFTW MPI Reference</a>, Previous: <a href="FFTW-MPI-Performance-Tips.html#FFTW-MPI-Performance-Tips" accesskey="p" rel="prev">FFTW MPI Performance Tips</a>, Up: <a href="Distributed_002dmemory-FFTW-with-MPI.html#Distributed_002dmemory-FFTW-with-MPI" 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#Concept-Index" title="Index" rel="index">Index</a>]</p>
Chris@82 75 </div>
Chris@82 76 <hr>
Chris@82 77 <a name="Combining-MPI-and-Threads-1"></a>
Chris@82 78 <h3 class="section">6.11 Combining MPI and Threads</h3>
Chris@82 79 <a name="index-threads-2"></a>
Chris@82 80
Chris@82 81 <p>In certain cases, it may be advantageous to combine MPI
Chris@82 82 (distributed-memory) and threads (shared-memory) parallelization.
Chris@82 83 FFTW supports this, with certain caveats. For example, if you have a
Chris@82 84 cluster of 4-processor shared-memory nodes, you may want to use
Chris@82 85 threads within the nodes and MPI between the nodes, instead of MPI for
Chris@82 86 all parallelization.
Chris@82 87 </p>
Chris@82 88 <p>In particular, it is possible to seamlessly combine the MPI FFTW
Chris@82 89 routines with the multi-threaded FFTW routines (see <a href="Multi_002dthreaded-FFTW.html#Multi_002dthreaded-FFTW">Multi-threaded FFTW</a>). However, some care must be taken in the initialization code,
Chris@82 90 which should look something like this:
Chris@82 91 </p>
Chris@82 92 <div class="example">
Chris@82 93 <pre class="example">int threads_ok;
Chris@82 94
Chris@82 95 int main(int argc, char **argv)
Chris@82 96 {
Chris@82 97 int provided;
Chris@82 98 MPI_Init_thread(&amp;argc, &amp;argv, MPI_THREAD_FUNNELED, &amp;provided);
Chris@82 99 threads_ok = provided &gt;= MPI_THREAD_FUNNELED;
Chris@82 100
Chris@82 101 if (threads_ok) threads_ok = fftw_init_threads();
Chris@82 102 fftw_mpi_init();
Chris@82 103
Chris@82 104 ...
Chris@82 105 if (threads_ok) fftw_plan_with_nthreads(...);
Chris@82 106 ...
Chris@82 107
Chris@82 108 MPI_Finalize();
Chris@82 109 }
Chris@82 110 </pre></div>
Chris@82 111 <a name="index-fftw_005fmpi_005finit-3"></a>
Chris@82 112 <a name="index-fftw_005finit_005fthreads-2"></a>
Chris@82 113 <a name="index-fftw_005fplan_005fwith_005fnthreads-1"></a>
Chris@82 114
Chris@82 115 <p>First, note that instead of calling <code>MPI_Init</code>, you should call
Chris@82 116 <code>MPI_Init_threads</code>, which is the initialization routine defined
Chris@82 117 by the MPI-2 standard to indicate to MPI that your program will be
Chris@82 118 multithreaded. We pass <code>MPI_THREAD_FUNNELED</code>, which indicates
Chris@82 119 that we will only call MPI routines from the main thread. (FFTW will
Chris@82 120 launch additional threads internally, but the extra threads will not
Chris@82 121 call MPI code.) (You may also pass <code>MPI_THREAD_SERIALIZED</code> or
Chris@82 122 <code>MPI_THREAD_MULTIPLE</code>, which requests additional multithreading
Chris@82 123 support from the MPI implementation, but this is not required by
Chris@82 124 FFTW.) The <code>provided</code> parameter returns what level of threads
Chris@82 125 support is actually supported by your MPI implementation; this
Chris@82 126 <em>must</em> be at least <code>MPI_THREAD_FUNNELED</code> if you want to call
Chris@82 127 the FFTW threads routines, so we define a global variable
Chris@82 128 <code>threads_ok</code> to record this. You should only call
Chris@82 129 <code>fftw_init_threads</code> or <code>fftw_plan_with_nthreads</code> if
Chris@82 130 <code>threads_ok</code> is true. For more information on thread safety in
Chris@82 131 MPI, see the
Chris@82 132 <a href="http://www.mpi-forum.org/docs/mpi-20-html/node162.htm">MPI and
Chris@82 133 Threads</a> section of the MPI-2 standard.
Chris@82 134 <a name="index-thread-safety-2"></a>
Chris@82 135 </p>
Chris@82 136
Chris@82 137 <p>Second, we must call <code>fftw_init_threads</code> <em>before</em>
Chris@82 138 <code>fftw_mpi_init</code>. This is critical for technical reasons having
Chris@82 139 to do with how FFTW initializes its list of algorithms.
Chris@82 140 </p>
Chris@82 141 <p>Then, if you call <code>fftw_plan_with_nthreads(N)</code>, <em>every</em> MPI
Chris@82 142 process will launch (up to) <code>N</code> threads to parallelize its transforms.
Chris@82 143 </p>
Chris@82 144 <p>For example, in the hypothetical cluster of 4-processor nodes, you
Chris@82 145 might wish to launch only a single MPI process per node, and then call
Chris@82 146 <code>fftw_plan_with_nthreads(4)</code> on each process to use all
Chris@82 147 processors in the nodes.
Chris@82 148 </p>
Chris@82 149 <p>This may or may not be faster than simply using as many MPI processes
Chris@82 150 as you have processors, however. On the one hand, using threads
Chris@82 151 within a node eliminates the need for explicit message passing within
Chris@82 152 the node. On the other hand, FFTW&rsquo;s transpose routines are not
Chris@82 153 multi-threaded, and this means that the communications that do take
Chris@82 154 place will not benefit from parallelization within the node.
Chris@82 155 Moreover, many MPI implementations already have optimizations to
Chris@82 156 exploit shared memory when it is available, so adding the
Chris@82 157 multithreaded FFTW on top of this may be superfluous.
Chris@82 158 <a name="index-transpose-4"></a>
Chris@82 159 </p>
Chris@82 160 <hr>
Chris@82 161 <div class="header">
Chris@82 162 <p>
Chris@82 163 Next: <a href="FFTW-MPI-Reference.html#FFTW-MPI-Reference" accesskey="n" rel="next">FFTW MPI Reference</a>, Previous: <a href="FFTW-MPI-Performance-Tips.html#FFTW-MPI-Performance-Tips" accesskey="p" rel="prev">FFTW MPI Performance Tips</a>, Up: <a href="Distributed_002dmemory-FFTW-with-MPI.html#Distributed_002dmemory-FFTW-with-MPI" 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#Concept-Index" title="Index" rel="index">Index</a>]</p>
Chris@82 164 </div>
Chris@82 165
Chris@82 166
Chris@82 167
Chris@82 168 </body>
Chris@82 169 </html>