Chris@10
|
1 <html lang="en">
|
Chris@10
|
2 <head>
|
Chris@10
|
3 <title>Usage of Multi-threaded FFTW - FFTW 3.3.3</title>
|
Chris@10
|
4 <meta http-equiv="Content-Type" content="text/html">
|
Chris@10
|
5 <meta name="description" content="FFTW 3.3.3">
|
Chris@10
|
6 <meta name="generator" content="makeinfo 4.13">
|
Chris@10
|
7 <link title="Top" rel="start" href="index.html#Top">
|
Chris@10
|
8 <link rel="up" href="Multi_002dthreaded-FFTW.html#Multi_002dthreaded-FFTW" title="Multi-threaded FFTW">
|
Chris@10
|
9 <link rel="prev" href="Installation-and-Supported-Hardware_002fSoftware.html#Installation-and-Supported-Hardware_002fSoftware" title="Installation and Supported Hardware/Software">
|
Chris@10
|
10 <link rel="next" href="How-Many-Threads-to-Use_003f.html#How-Many-Threads-to-Use_003f" title="How Many Threads to Use?">
|
Chris@10
|
11 <link href="http://www.gnu.org/software/texinfo/" rel="generator-home" title="Texinfo Homepage">
|
Chris@10
|
12 <!--
|
Chris@10
|
13 This manual is for FFTW
|
Chris@10
|
14 (version 3.3.3, 25 November 2012).
|
Chris@10
|
15
|
Chris@10
|
16 Copyright (C) 2003 Matteo Frigo.
|
Chris@10
|
17
|
Chris@10
|
18 Copyright (C) 2003 Massachusetts Institute of Technology.
|
Chris@10
|
19
|
Chris@10
|
20 Permission is granted to make and distribute verbatim copies of
|
Chris@10
|
21 this manual provided the copyright notice and this permission
|
Chris@10
|
22 notice are preserved on all copies.
|
Chris@10
|
23
|
Chris@10
|
24 Permission is granted to copy and distribute modified versions of
|
Chris@10
|
25 this manual under the conditions for verbatim copying, provided
|
Chris@10
|
26 that the entire resulting derived work is distributed under the
|
Chris@10
|
27 terms of a permission notice identical to this one.
|
Chris@10
|
28
|
Chris@10
|
29 Permission is granted to copy and distribute translations of this
|
Chris@10
|
30 manual into another language, under the above conditions for
|
Chris@10
|
31 modified versions, except that this permission notice may be
|
Chris@10
|
32 stated in a translation approved by the Free Software Foundation.
|
Chris@10
|
33 -->
|
Chris@10
|
34 <meta http-equiv="Content-Style-Type" content="text/css">
|
Chris@10
|
35 <style type="text/css"><!--
|
Chris@10
|
36 pre.display { font-family:inherit }
|
Chris@10
|
37 pre.format { font-family:inherit }
|
Chris@10
|
38 pre.smalldisplay { font-family:inherit; font-size:smaller }
|
Chris@10
|
39 pre.smallformat { font-family:inherit; font-size:smaller }
|
Chris@10
|
40 pre.smallexample { font-size:smaller }
|
Chris@10
|
41 pre.smalllisp { font-size:smaller }
|
Chris@10
|
42 span.sc { font-variant:small-caps }
|
Chris@10
|
43 span.roman { font-family:serif; font-weight:normal; }
|
Chris@10
|
44 span.sansserif { font-family:sans-serif; font-weight:normal; }
|
Chris@10
|
45 --></style>
|
Chris@10
|
46 </head>
|
Chris@10
|
47 <body>
|
Chris@10
|
48 <div class="node">
|
Chris@10
|
49 <a name="Usage-of-Multi-threaded-FFTW"></a>
|
Chris@10
|
50 <a name="Usage-of-Multi_002dthreaded-FFTW"></a>
|
Chris@10
|
51 <p>
|
Chris@10
|
52 Next: <a rel="next" accesskey="n" href="How-Many-Threads-to-Use_003f.html#How-Many-Threads-to-Use_003f">How Many Threads to Use?</a>,
|
Chris@10
|
53 Previous: <a rel="previous" accesskey="p" href="Installation-and-Supported-Hardware_002fSoftware.html#Installation-and-Supported-Hardware_002fSoftware">Installation and Supported Hardware/Software</a>,
|
Chris@10
|
54 Up: <a rel="up" accesskey="u" href="Multi_002dthreaded-FFTW.html#Multi_002dthreaded-FFTW">Multi-threaded FFTW</a>
|
Chris@10
|
55 <hr>
|
Chris@10
|
56 </div>
|
Chris@10
|
57
|
Chris@10
|
58 <h3 class="section">5.2 Usage of Multi-threaded FFTW</h3>
|
Chris@10
|
59
|
Chris@10
|
60 <p>Here, it is assumed that the reader is already familiar with the usage
|
Chris@10
|
61 of the uniprocessor FFTW routines, described elsewhere in this manual.
|
Chris@10
|
62 We only describe what one has to change in order to use the
|
Chris@10
|
63 multi-threaded routines.
|
Chris@10
|
64
|
Chris@10
|
65 <p><a name="index-OpenMP-332"></a>First, programs using the parallel complex transforms should be linked
|
Chris@10
|
66 with <code>-lfftw3_threads -lfftw3 -lm</code> on Unix, or <code>-lfftw3_omp
|
Chris@10
|
67 -lfftw3 -lm</code> if you compiled with OpenMP. You will also need to link
|
Chris@10
|
68 with whatever library is responsible for threads on your system
|
Chris@10
|
69 (e.g. <code>-lpthread</code> on GNU/Linux) or include whatever compiler flag
|
Chris@10
|
70 enables OpenMP (e.g. <code>-fopenmp</code> with gcc).
|
Chris@10
|
71 <a name="index-linking-on-Unix-333"></a>
|
Chris@10
|
72
|
Chris@10
|
73 <p>Second, before calling <em>any</em> FFTW routines, you should call the
|
Chris@10
|
74 function:
|
Chris@10
|
75
|
Chris@10
|
76 <pre class="example"> int fftw_init_threads(void);
|
Chris@10
|
77 </pre>
|
Chris@10
|
78 <p><a name="index-fftw_005finit_005fthreads-334"></a>
|
Chris@10
|
79 This function, which need only be called once, performs any one-time
|
Chris@10
|
80 initialization required to use threads on your system. It returns zero
|
Chris@10
|
81 if there was some error (which should not happen under normal
|
Chris@10
|
82 circumstances) and a non-zero value otherwise.
|
Chris@10
|
83
|
Chris@10
|
84 <p>Third, before creating a plan that you want to parallelize, you should
|
Chris@10
|
85 call:
|
Chris@10
|
86
|
Chris@10
|
87 <pre class="example"> void fftw_plan_with_nthreads(int nthreads);
|
Chris@10
|
88 </pre>
|
Chris@10
|
89 <p><a name="index-fftw_005fplan_005fwith_005fnthreads-335"></a>
|
Chris@10
|
90 The <code>nthreads</code> argument indicates the number of threads you want
|
Chris@10
|
91 FFTW to use (or actually, the maximum number). All plans subsequently
|
Chris@10
|
92 created with any planner routine will use that many threads. You can
|
Chris@10
|
93 call <code>fftw_plan_with_nthreads</code>, create some plans, call
|
Chris@10
|
94 <code>fftw_plan_with_nthreads</code> again with a different argument, and
|
Chris@10
|
95 create some more plans for a new number of threads. Plans already created
|
Chris@10
|
96 before a call to <code>fftw_plan_with_nthreads</code> are unaffected. If you
|
Chris@10
|
97 pass an <code>nthreads</code> argument of <code>1</code> (the default), threads are
|
Chris@10
|
98 disabled for subsequent plans.
|
Chris@10
|
99
|
Chris@10
|
100 <p><a name="index-OpenMP-336"></a>With OpenMP, to configure FFTW to use all of the currently running
|
Chris@10
|
101 OpenMP threads (set by <code>omp_set_num_threads(nthreads)</code> or by the
|
Chris@10
|
102 <code>OMP_NUM_THREADS</code> environment variable), you can do:
|
Chris@10
|
103 <code>fftw_plan_with_nthreads(omp_get_max_threads())</code>. (The ‘<samp><span class="samp">omp_</span></samp>’
|
Chris@10
|
104 OpenMP functions are declared via <code>#include <omp.h></code>.)
|
Chris@10
|
105
|
Chris@10
|
106 <p><a name="index-thread-safety-337"></a>Given a plan, you then execute it as usual with
|
Chris@10
|
107 <code>fftw_execute(plan)</code>, and the execution will use the number of
|
Chris@10
|
108 threads specified when the plan was created. When done, you destroy
|
Chris@10
|
109 it as usual with <code>fftw_destroy_plan</code>. As described in
|
Chris@10
|
110 <a href="Thread-safety.html#Thread-safety">Thread safety</a>, plan <em>execution</em> is thread-safe, but plan
|
Chris@10
|
111 creation and destruction are <em>not</em>: you should create/destroy
|
Chris@10
|
112 plans only from a single thread, but can safely execute multiple plans
|
Chris@10
|
113 in parallel.
|
Chris@10
|
114
|
Chris@10
|
115 <p>There is one additional routine: if you want to get rid of all memory
|
Chris@10
|
116 and other resources allocated internally by FFTW, you can call:
|
Chris@10
|
117
|
Chris@10
|
118 <pre class="example"> void fftw_cleanup_threads(void);
|
Chris@10
|
119 </pre>
|
Chris@10
|
120 <p><a name="index-fftw_005fcleanup_005fthreads-338"></a>
|
Chris@10
|
121 which is much like the <code>fftw_cleanup()</code> function except that it
|
Chris@10
|
122 also gets rid of threads-related data. You must <em>not</em> execute any
|
Chris@10
|
123 previously created plans after calling this function.
|
Chris@10
|
124
|
Chris@10
|
125 <p>We should also mention one other restriction: if you save wisdom from a
|
Chris@10
|
126 program using the multi-threaded FFTW, that wisdom <em>cannot be used</em>
|
Chris@10
|
127 by a program using only the single-threaded FFTW (i.e. not calling
|
Chris@10
|
128 <code>fftw_init_threads</code>). See <a href="Words-of-Wisdom_002dSaving-Plans.html#Words-of-Wisdom_002dSaving-Plans">Words of Wisdom-Saving Plans</a>.
|
Chris@10
|
129
|
Chris@10
|
130 <!-- -->
|
Chris@10
|
131 </body></html>
|
Chris@10
|
132
|