Mercurial > hg > sv-dependency-builds
comparison src/fftw-3.3.8/doc/html/Basic-and-advanced-distribution-interfaces.html @ 167:bd3cc4d1df30
Add FFTW 3.3.8 source, and a Linux build
author | Chris Cannam <cannam@all-day-breakfast.com> |
---|---|
date | Tue, 19 Nov 2019 14:52:55 +0000 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
166:cbd6d7e562c7 | 167:bd3cc4d1df30 |
---|---|
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 3.3.8, 24 May 2018). | |
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 6.3, http://www.gnu.org/software/texinfo/ --> | |
24 <head> | |
25 <title>FFTW 3.3.8: Basic and advanced distribution interfaces</title> | |
26 | |
27 <meta name="description" content="FFTW 3.3.8: Basic and advanced distribution interfaces"> | |
28 <meta name="keywords" content="FFTW 3.3.8: Basic and advanced distribution interfaces"> | |
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="MPI-Data-Distribution.html#MPI-Data-Distribution" rel="up" title="MPI Data Distribution"> | |
37 <link href="Load-balancing.html#Load-balancing" rel="next" title="Load balancing"> | |
38 <link href="MPI-Data-Distribution.html#MPI-Data-Distribution" rel="prev" title="MPI Data Distribution"> | |
39 <style type="text/css"> | |
40 <!-- | |
41 a.summary-letter {text-decoration: none} | |
42 blockquote.indentedblock {margin-right: 0em} | |
43 blockquote.smallindentedblock {margin-right: 0em; font-size: smaller} | |
44 blockquote.smallquotation {font-size: smaller} | |
45 div.display {margin-left: 3.2em} | |
46 div.example {margin-left: 3.2em} | |
47 div.lisp {margin-left: 3.2em} | |
48 div.smalldisplay {margin-left: 3.2em} | |
49 div.smallexample {margin-left: 3.2em} | |
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.nolinebreak {white-space: nowrap} | |
61 span.roman {font-family: initial; font-weight: normal} | |
62 span.sansserif {font-family: sans-serif; font-weight: normal} | |
63 ul.no-bullet {list-style: none} | |
64 --> | |
65 </style> | |
66 | |
67 | |
68 </head> | |
69 | |
70 <body lang="en"> | |
71 <a name="Basic-and-advanced-distribution-interfaces"></a> | |
72 <div class="header"> | |
73 <p> | |
74 Next: <a href="Load-balancing.html#Load-balancing" accesskey="n" rel="next">Load balancing</a>, Previous: <a href="MPI-Data-Distribution.html#MPI-Data-Distribution" accesskey="p" rel="prev">MPI Data Distribution</a>, Up: <a href="MPI-Data-Distribution.html#MPI-Data-Distribution" accesskey="u" rel="up">MPI Data Distribution</a> [<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> | |
75 </div> | |
76 <hr> | |
77 <a name="Basic-and-advanced-distribution-interfaces-1"></a> | |
78 <h4 class="subsection">6.4.1 Basic and advanced distribution interfaces</h4> | |
79 | |
80 <p>As with the planner interface, the ‘<samp>fftw_mpi_local_size</samp>’ | |
81 distribution interface is broken into basic and advanced | |
82 (‘<samp>_many</samp>’) interfaces, where the latter allows you to specify the | |
83 block size manually and also to request block sizes when computing | |
84 multiple transforms simultaneously. These functions are documented | |
85 more exhaustively by the FFTW MPI Reference, but we summarize the | |
86 basic ideas here using a couple of two-dimensional examples. | |
87 </p> | |
88 <p>For the 100 × 200 | |
89 complex-DFT example, above, we would find | |
90 the distribution by calling the following function in the basic | |
91 interface: | |
92 </p> | |
93 <div class="example"> | |
94 <pre class="example">ptrdiff_t fftw_mpi_local_size_2d(ptrdiff_t n0, ptrdiff_t n1, MPI_Comm comm, | |
95 ptrdiff_t *local_n0, ptrdiff_t *local_0_start); | |
96 </pre></div> | |
97 <a name="index-fftw_005fmpi_005flocal_005fsize_005f2d-1"></a> | |
98 | |
99 <p>Given the total size of the data to be transformed (here, <code>n0 = | |
100 100</code> and <code>n1 = 200</code>) and an MPI communicator (<code>comm</code>), this | |
101 function provides three numbers. | |
102 </p> | |
103 <p>First, it describes the shape of the local data: the current process | |
104 should store a <code>local_n0</code> by <code>n1</code> slice of the overall | |
105 dataset, in row-major order (<code>n1</code> dimension contiguous), starting | |
106 at index <code>local_0_start</code>. That is, if the total dataset is | |
107 viewed as a <code>n0</code> by <code>n1</code> matrix, the current process should | |
108 store the rows <code>local_0_start</code> to | |
109 <code>local_0_start+local_n0-1</code>. Obviously, if you are running with | |
110 only a single MPI process, that process will store the entire array: | |
111 <code>local_0_start</code> will be zero and <code>local_n0</code> will be | |
112 <code>n0</code>. See <a href="Row_002dmajor-Format.html#Row_002dmajor-Format">Row-major Format</a>. | |
113 <a name="index-row_002dmajor-4"></a> | |
114 </p> | |
115 | |
116 <p>Second, the return value is the total number of data elements (e.g., | |
117 complex numbers for a complex DFT) that should be allocated for the | |
118 input and output arrays on the current process (ideally with | |
119 <code>fftw_malloc</code> or an ‘<samp>fftw_alloc</samp>’ function, to ensure optimal | |
120 alignment). It might seem that this should always be equal to | |
121 <code>local_n0 * n1</code>, but this is <em>not</em> the case. FFTW’s | |
122 distributed FFT algorithms require data redistributions at | |
123 intermediate stages of the transform, and in some circumstances this | |
124 may require slightly larger local storage. This is discussed in more | |
125 detail below, under <a href="Load-balancing.html#Load-balancing">Load balancing</a>. | |
126 <a name="index-fftw_005fmalloc-5"></a> | |
127 <a name="index-fftw_005falloc_005fcomplex-3"></a> | |
128 </p> | |
129 | |
130 <a name="index-advanced-interface-4"></a> | |
131 <p>The advanced-interface ‘<samp>local_size</samp>’ function for multidimensional | |
132 transforms returns the same three things (<code>local_n0</code>, | |
133 <code>local_0_start</code>, and the total number of elements to allocate), | |
134 but takes more inputs: | |
135 </p> | |
136 <div class="example"> | |
137 <pre class="example">ptrdiff_t fftw_mpi_local_size_many(int rnk, const ptrdiff_t *n, | |
138 ptrdiff_t howmany, | |
139 ptrdiff_t block0, | |
140 MPI_Comm comm, | |
141 ptrdiff_t *local_n0, | |
142 ptrdiff_t *local_0_start); | |
143 </pre></div> | |
144 <a name="index-fftw_005fmpi_005flocal_005fsize_005fmany"></a> | |
145 | |
146 <p>The two-dimensional case above corresponds to <code>rnk = 2</code> and an | |
147 array <code>n</code> of length 2 with <code>n[0] = n0</code> and <code>n[1] = n1</code>. | |
148 This routine is for any <code>rnk > 1</code>; one-dimensional transforms | |
149 have their own interface because they work slightly differently, as | |
150 discussed below. | |
151 </p> | |
152 <p>First, the advanced interface allows you to perform multiple | |
153 transforms at once, of interleaved data, as specified by the | |
154 <code>howmany</code> parameter. (<code>hoamany</code> is 1 for a single | |
155 transform.) | |
156 </p> | |
157 <p>Second, here you can specify your desired block size in the <code>n0</code> | |
158 dimension, <code>block0</code>. To use FFTW’s default block size, pass | |
159 <code>FFTW_MPI_DEFAULT_BLOCK</code> (0) for <code>block0</code>. Otherwise, on | |
160 <code>P</code> processes, FFTW will return <code>local_n0</code> equal to | |
161 <code>block0</code> on the first <code>P / block0</code> processes (rounded down), | |
162 return <code>local_n0</code> equal to <code>n0 - block0 * (P / block0)</code> on | |
163 the next process, and <code>local_n0</code> equal to zero on any remaining | |
164 processes. In general, we recommend using the default block size | |
165 (which corresponds to <code>n0 / P</code>, rounded up). | |
166 <a name="index-FFTW_005fMPI_005fDEFAULT_005fBLOCK"></a> | |
167 <a name="index-block-distribution-1"></a> | |
168 </p> | |
169 | |
170 <p>For example, suppose you have <code>P = 4</code> processes and <code>n0 = | |
171 21</code>. The default will be a block size of <code>6</code>, which will give | |
172 <code>local_n0 = 6</code> on the first three processes and <code>local_n0 = | |
173 3</code> on the last process. Instead, however, you could specify | |
174 <code>block0 = 5</code> if you wanted, which would give <code>local_n0 = 5</code> | |
175 on processes 0 to 2, <code>local_n0 = 6</code> on process 3. (This choice, | |
176 while it may look superficially more “balanced,” has the same | |
177 critical path as FFTW’s default but requires more communications.) | |
178 </p> | |
179 <hr> | |
180 <div class="header"> | |
181 <p> | |
182 Next: <a href="Load-balancing.html#Load-balancing" accesskey="n" rel="next">Load balancing</a>, Previous: <a href="MPI-Data-Distribution.html#MPI-Data-Distribution" accesskey="p" rel="prev">MPI Data Distribution</a>, Up: <a href="MPI-Data-Distribution.html#MPI-Data-Distribution" accesskey="u" rel="up">MPI Data Distribution</a> [<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> | |
183 </div> | |
184 | |
185 | |
186 | |
187 </body> | |
188 </html> |