Mercurial > hg > sv-dependency-builds

comparison src/fftw-3.3.5/doc/html/An-improved-replacement-for-MPI_005fAlltoall.html @ 127:7867fa7e1b6b

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Current fftw source
author Chris Cannam <cannam@all-day-breakfast.com>
date Tue, 18 Oct 2016 13:40:26 +0100
parents
children
comparison
equal deleted inserted replaced
126:4a7071416412 127:7867fa7e1b6b
1 <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
2 <html>
3 <!-- This manual is for FFTW
4 (version 3.3.5, 30 July 2016).
5
6 Copyright (C) 2003 Matteo Frigo.
7
8 Copyright (C) 2003 Massachusetts Institute of Technology.
9
10 Permission is granted to make and distribute verbatim copies of this
11 manual provided the copyright notice and this permission notice are
12 preserved on all copies.
13
14 Permission is granted to copy and distribute modified versions of this
15 manual under the conditions for verbatim copying, provided that the
16 entire resulting derived work is distributed under the terms of a
17 permission notice identical to this one.
18
19 Permission is granted to copy and distribute translations of this manual
20 into another language, under the above conditions for modified versions,
21 except that this permission notice may be stated in a translation
22 approved by the Free Software Foundation. -->
23 <!-- Created by GNU Texinfo 5.2, http://www.gnu.org/software/texinfo/ -->
24 <head>
25 <title>FFTW 3.3.5: An improved replacement for MPI_Alltoall</title>
26
27 <meta name="description" content="FFTW 3.3.5: An improved replacement for MPI_Alltoall">
28 <meta name="keywords" content="FFTW 3.3.5: An improved replacement for MPI_Alltoall">
29 <meta name="resource-type" content="document">
30 <meta name="distribution" content="global">
31 <meta name="Generator" content="makeinfo">
32 <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
33 <link href="index.html#Top" rel="start" title="Top">
34 <link href="Concept-Index.html#Concept-Index" rel="index" title="Concept Index">
35 <link href="index.html#SEC_Contents" rel="contents" title="Table of Contents">
36 <link href="FFTW-MPI-Transposes.html#FFTW-MPI-Transposes" rel="up" title="FFTW MPI Transposes">
37 <link href="FFTW-MPI-Wisdom.html#FFTW-MPI-Wisdom" rel="next" title="FFTW MPI Wisdom">
38 <link href="Advanced-distributed_002dtranspose-interface.html#Advanced-distributed_002dtranspose-interface" rel="prev" title="Advanced distributed-transpose interface">
39 <style type="text/css">
40 <!--
41 a.summary-letter {text-decoration: none}
42 blockquote.smallquotation {font-size: smaller}
43 div.display {margin-left: 3.2em}
44 div.example {margin-left: 3.2em}
45 div.indentedblock {margin-left: 3.2em}
46 div.lisp {margin-left: 3.2em}
47 div.smalldisplay {margin-left: 3.2em}
48 div.smallexample {margin-left: 3.2em}
49 div.smallindentedblock {margin-left: 3.2em; font-size: smaller}
50 div.smalllisp {margin-left: 3.2em}
51 kbd {font-style:oblique}
52 pre.display {font-family: inherit}
53 pre.format {font-family: inherit}
54 pre.menu-comment {font-family: serif}
55 pre.menu-preformatted {font-family: serif}
56 pre.smalldisplay {font-family: inherit; font-size: smaller}
57 pre.smallexample {font-size: smaller}
58 pre.smallformat {font-family: inherit; font-size: smaller}
59 pre.smalllisp {font-size: smaller}
60 span.nocodebreak {white-space:nowrap}
61 span.nolinebreak {white-space:nowrap}
62 span.roman {font-family:serif; font-weight:normal}
63 span.sansserif {font-family:sans-serif; font-weight:normal}
64 ul.no-bullet {list-style: none}
65 -->
66 </style>
67
68
69 </head>
70
71 <body lang="en" bgcolor="#FFFFFF" text="#000000" link="#0000FF" vlink="#800080" alink="#FF0000">
72 <a name="An-improved-replacement-for-MPI_005fAlltoall"></a>
73 <div class="header">
74 <p>
75 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>
76 </div>
77 <hr>
78 <a name="An-improved-replacement-for-MPI_005fAlltoall-1"></a>
79 <h4 class="subsection">6.7.3 An improved replacement for MPI_Alltoall</h4>
80
81 <p>We close this section by noting that FFTW&rsquo;s MPI transpose routines can
82 be thought of as a generalization for the <code>MPI_Alltoall</code> function
83 (albeit only for floating-point types), and in some circumstances can
84 function as an improved replacement.
85 <a name="index-MPI_005fAlltoall"></a>
86 </p>
87
88 <p><code>MPI_Alltoall</code> is defined by the MPI standard as:
89 </p>
90 <div class="example">
91 <pre class="example">int MPI_Alltoall(void *sendbuf, int sendcount, MPI_Datatype sendtype,
92 void *recvbuf, int recvcnt, MPI_Datatype recvtype,
93 MPI_Comm comm);
94 </pre></div>
95
96 <p>In particular, for <code>double*</code> arrays <code>in</code> and <code>out</code>,
97 consider the call:
98 </p>
99 <div class="example">
100 <pre class="example">MPI_Alltoall(in, howmany, MPI_DOUBLE, out, howmany MPI_DOUBLE, comm);
101 </pre></div>
102
103 <p>This is completely equivalent to:
104 </p>
105 <div class="example">
106 <pre class="example">MPI_Comm_size(comm, &amp;P);
107 plan = fftw_mpi_plan_many_transpose(P, P, howmany, 1, 1, in, out, comm, FFTW_ESTIMATE);
108 fftw_execute(plan);
109 fftw_destroy_plan(plan);
110 </pre></div>
111
112 <p>That is, computing a P&nbsp;&times;&nbsp;P transpose on <code>P</code> processes,
113 with a block size of 1, is just a standard all-to-all communication.
114 </p>
115 <p>However, using the FFTW routine instead of <code>MPI_Alltoall</code> may
116 have certain advantages. First of all, FFTW&rsquo;s routine can operate
117 in-place (<code>in == out</code>) whereas <code>MPI_Alltoall</code> can only
118 operate out-of-place.
119 <a name="index-in_002dplace-8"></a>
120 </p>
121
122 <p>Second, even for out-of-place plans, FFTW&rsquo;s routine may be faster,
123 especially if you need to perform the all-to-all communication many
124 times and can afford to use <code>FFTW_MEASURE</code> or
125 <code>FFTW_PATIENT</code>. It should certainly be no slower, not including
126 the time to create the plan, since one of the possible algorithms that
127 FFTW uses for an out-of-place transpose <em>is</em> simply to call
128 <code>MPI_Alltoall</code>. However, FFTW also considers several other
129 possible algorithms that, depending on your MPI implementation and
130 your hardware, may be faster.
131 <a name="index-FFTW_005fMEASURE-3"></a>
132 <a name="index-FFTW_005fPATIENT-4"></a>
133 </p>
134
135
136
137 </body>
138 </html>