annotate src/fftw-3.3.8/doc/html/An-improved-replacement-for-MPI_005fAlltoall.html @ 169:223a55898ab9 tip default

Add null config files
author Chris Cannam <cannam@all-day-breakfast.com>
date Mon, 02 Mar 2020 14:03:47 +0000
parents bd3cc4d1df30
children
rev   line source
cannam@167 1 <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
cannam@167 2 <html>
cannam@167 3 <!-- This manual is for FFTW
cannam@167 4 (version 3.3.8, 24 May 2018).
cannam@167 5
cannam@167 6 Copyright (C) 2003 Matteo Frigo.
cannam@167 7
cannam@167 8 Copyright (C) 2003 Massachusetts Institute of Technology.
cannam@167 9
cannam@167 10 Permission is granted to make and distribute verbatim copies of this
cannam@167 11 manual provided the copyright notice and this permission notice are
cannam@167 12 preserved on all copies.
cannam@167 13
cannam@167 14 Permission is granted to copy and distribute modified versions of this
cannam@167 15 manual under the conditions for verbatim copying, provided that the
cannam@167 16 entire resulting derived work is distributed under the terms of a
cannam@167 17 permission notice identical to this one.
cannam@167 18
cannam@167 19 Permission is granted to copy and distribute translations of this manual
cannam@167 20 into another language, under the above conditions for modified versions,
cannam@167 21 except that this permission notice may be stated in a translation
cannam@167 22 approved by the Free Software Foundation. -->
cannam@167 23 <!-- Created by GNU Texinfo 6.3, http://www.gnu.org/software/texinfo/ -->
cannam@167 24 <head>
cannam@167 25 <title>FFTW 3.3.8: An improved replacement for MPI_Alltoall</title>
cannam@167 26
cannam@167 27 <meta name="description" content="FFTW 3.3.8: An improved replacement for MPI_Alltoall">
cannam@167 28 <meta name="keywords" content="FFTW 3.3.8: An improved replacement for MPI_Alltoall">
cannam@167 29 <meta name="resource-type" content="document">
cannam@167 30 <meta name="distribution" content="global">
cannam@167 31 <meta name="Generator" content="makeinfo">
cannam@167 32 <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
cannam@167 33 <link href="index.html#Top" rel="start" title="Top">
cannam@167 34 <link href="Concept-Index.html#Concept-Index" rel="index" title="Concept Index">
cannam@167 35 <link href="index.html#SEC_Contents" rel="contents" title="Table of Contents">
cannam@167 36 <link href="FFTW-MPI-Transposes.html#FFTW-MPI-Transposes" rel="up" title="FFTW MPI Transposes">
cannam@167 37 <link href="FFTW-MPI-Wisdom.html#FFTW-MPI-Wisdom" rel="next" title="FFTW MPI Wisdom">
cannam@167 38 <link href="Advanced-distributed_002dtranspose-interface.html#Advanced-distributed_002dtranspose-interface" rel="prev" title="Advanced distributed-transpose interface">
cannam@167 39 <style type="text/css">
cannam@167 40 <!--
cannam@167 41 a.summary-letter {text-decoration: none}
cannam@167 42 blockquote.indentedblock {margin-right: 0em}
cannam@167 43 blockquote.smallindentedblock {margin-right: 0em; font-size: smaller}
cannam@167 44 blockquote.smallquotation {font-size: smaller}
cannam@167 45 div.display {margin-left: 3.2em}
cannam@167 46 div.example {margin-left: 3.2em}
cannam@167 47 div.lisp {margin-left: 3.2em}
cannam@167 48 div.smalldisplay {margin-left: 3.2em}
cannam@167 49 div.smallexample {margin-left: 3.2em}
cannam@167 50 div.smalllisp {margin-left: 3.2em}
cannam@167 51 kbd {font-style: oblique}
cannam@167 52 pre.display {font-family: inherit}
cannam@167 53 pre.format {font-family: inherit}
cannam@167 54 pre.menu-comment {font-family: serif}
cannam@167 55 pre.menu-preformatted {font-family: serif}
cannam@167 56 pre.smalldisplay {font-family: inherit; font-size: smaller}
cannam@167 57 pre.smallexample {font-size: smaller}
cannam@167 58 pre.smallformat {font-family: inherit; font-size: smaller}
cannam@167 59 pre.smalllisp {font-size: smaller}
cannam@167 60 span.nolinebreak {white-space: nowrap}
cannam@167 61 span.roman {font-family: initial; font-weight: normal}
cannam@167 62 span.sansserif {font-family: sans-serif; font-weight: normal}
cannam@167 63 ul.no-bullet {list-style: none}
cannam@167 64 -->
cannam@167 65 </style>
cannam@167 66
cannam@167 67
cannam@167 68 </head>
cannam@167 69
cannam@167 70 <body lang="en">
cannam@167 71 <a name="An-improved-replacement-for-MPI_005fAlltoall"></a>
cannam@167 72 <div class="header">
cannam@167 73 <p>
cannam@167 74 Previous: <a href="Advanced-distributed_002dtranspose-interface.html#Advanced-distributed_002dtranspose-interface" accesskey="p" rel="prev">Advanced distributed-transpose interface</a>, Up: <a href="FFTW-MPI-Transposes.html#FFTW-MPI-Transposes" accesskey="u" rel="up">FFTW MPI Transposes</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>
cannam@167 75 </div>
cannam@167 76 <hr>
cannam@167 77 <a name="An-improved-replacement-for-MPI_005fAlltoall-1"></a>
cannam@167 78 <h4 class="subsection">6.7.3 An improved replacement for MPI_Alltoall</h4>
cannam@167 79
cannam@167 80 <p>We close this section by noting that FFTW&rsquo;s MPI transpose routines can
cannam@167 81 be thought of as a generalization for the <code>MPI_Alltoall</code> function
cannam@167 82 (albeit only for floating-point types), and in some circumstances can
cannam@167 83 function as an improved replacement.
cannam@167 84 <a name="index-MPI_005fAlltoall"></a>
cannam@167 85 </p>
cannam@167 86
cannam@167 87 <p><code>MPI_Alltoall</code> is defined by the MPI standard as:
cannam@167 88 </p>
cannam@167 89 <div class="example">
cannam@167 90 <pre class="example">int MPI_Alltoall(void *sendbuf, int sendcount, MPI_Datatype sendtype,
cannam@167 91 void *recvbuf, int recvcnt, MPI_Datatype recvtype,
cannam@167 92 MPI_Comm comm);
cannam@167 93 </pre></div>
cannam@167 94
cannam@167 95 <p>In particular, for <code>double*</code> arrays <code>in</code> and <code>out</code>,
cannam@167 96 consider the call:
cannam@167 97 </p>
cannam@167 98 <div class="example">
cannam@167 99 <pre class="example">MPI_Alltoall(in, howmany, MPI_DOUBLE, out, howmany MPI_DOUBLE, comm);
cannam@167 100 </pre></div>
cannam@167 101
cannam@167 102 <p>This is completely equivalent to:
cannam@167 103 </p>
cannam@167 104 <div class="example">
cannam@167 105 <pre class="example">MPI_Comm_size(comm, &amp;P);
cannam@167 106 plan = fftw_mpi_plan_many_transpose(P, P, howmany, 1, 1, in, out, comm, FFTW_ESTIMATE);
cannam@167 107 fftw_execute(plan);
cannam@167 108 fftw_destroy_plan(plan);
cannam@167 109 </pre></div>
cannam@167 110
cannam@167 111 <p>That is, computing a P&nbsp;&times;&nbsp;P
cannam@167 112 transpose on <code>P</code> processes,
cannam@167 113 with a block size of 1, is just a standard all-to-all communication.
cannam@167 114 </p>
cannam@167 115 <p>However, using the FFTW routine instead of <code>MPI_Alltoall</code> may
cannam@167 116 have certain advantages. First of all, FFTW&rsquo;s routine can operate
cannam@167 117 in-place (<code>in == out</code>) whereas <code>MPI_Alltoall</code> can only
cannam@167 118 operate out-of-place.
cannam@167 119 <a name="index-in_002dplace-8"></a>
cannam@167 120 </p>
cannam@167 121
cannam@167 122 <p>Second, even for out-of-place plans, FFTW&rsquo;s routine may be faster,
cannam@167 123 especially if you need to perform the all-to-all communication many
cannam@167 124 times and can afford to use <code>FFTW_MEASURE</code> or
cannam@167 125 <code>FFTW_PATIENT</code>. It should certainly be no slower, not including
cannam@167 126 the time to create the plan, since one of the possible algorithms that
cannam@167 127 FFTW uses for an out-of-place transpose <em>is</em> simply to call
cannam@167 128 <code>MPI_Alltoall</code>. However, FFTW also considers several other
cannam@167 129 possible algorithms that, depending on your MPI implementation and
cannam@167 130 your hardware, may be faster.
cannam@167 131 <a name="index-FFTW_005fMEASURE-3"></a>
cannam@167 132 <a name="index-FFTW_005fPATIENT-4"></a>
cannam@167 133 </p>
cannam@167 134
cannam@167 135
cannam@167 136
cannam@167 137 </body>
cannam@167 138 </html>