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: Introduction</title>
|
cannam@167
|
26
|
cannam@167
|
27 <meta name="description" content="FFTW 3.3.8: Introduction">
|
cannam@167
|
28 <meta name="keywords" content="FFTW 3.3.8: Introduction">
|
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="index.html#Top" rel="up" title="Top">
|
cannam@167
|
37 <link href="Tutorial.html#Tutorial" rel="next" title="Tutorial">
|
cannam@167
|
38 <link href="index.html#Top" rel="prev" title="Top">
|
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="Introduction"></a>
|
cannam@167
|
72 <div class="header">
|
cannam@167
|
73 <p>
|
cannam@167
|
74 Next: <a href="Tutorial.html#Tutorial" accesskey="n" rel="next">Tutorial</a>, Previous: <a href="index.html#Top" accesskey="p" rel="prev">Top</a>, Up: <a href="index.html#Top" accesskey="u" rel="up">Top</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>
|
cannam@167
|
75 </div>
|
cannam@167
|
76 <hr>
|
cannam@167
|
77 <a name="Introduction-1"></a>
|
cannam@167
|
78 <h2 class="chapter">1 Introduction</h2>
|
cannam@167
|
79 <p>This manual documents version 3.3.8 of FFTW, the
|
cannam@167
|
80 <em>Fastest Fourier Transform in the West</em>. FFTW is a comprehensive
|
cannam@167
|
81 collection of fast C routines for computing the discrete Fourier
|
cannam@167
|
82 transform (DFT) and various special cases thereof.
|
cannam@167
|
83 <a name="index-discrete-Fourier-transform"></a>
|
cannam@167
|
84 <a name="index-DFT"></a>
|
cannam@167
|
85 </p><ul>
|
cannam@167
|
86 <li> FFTW computes the DFT of complex data, real data, even-
|
cannam@167
|
87 or odd-symmetric real data (these symmetric transforms are usually
|
cannam@167
|
88 known as the discrete cosine or sine transform, respectively), and the
|
cannam@167
|
89 discrete Hartley transform (DHT) of real data.
|
cannam@167
|
90
|
cannam@167
|
91 </li><li> The input data can have arbitrary length.
|
cannam@167
|
92 FFTW employs <i>O</i>(<i>n</i> log <i>n</i>)
|
cannam@167
|
93 algorithms for all lengths, including
|
cannam@167
|
94 prime numbers.
|
cannam@167
|
95
|
cannam@167
|
96 </li><li> FFTW supports arbitrary multi-dimensional data.
|
cannam@167
|
97
|
cannam@167
|
98 </li><li> FFTW supports the SSE, SSE2, AVX, AVX2, AVX512, KCVI, Altivec, VSX, and
|
cannam@167
|
99 NEON vector instruction sets.
|
cannam@167
|
100
|
cannam@167
|
101 </li><li> FFTW includes parallel (multi-threaded) transforms
|
cannam@167
|
102 for shared-memory systems.
|
cannam@167
|
103 </li><li> Starting with version 3.3, FFTW includes distributed-memory parallel
|
cannam@167
|
104 transforms using MPI.
|
cannam@167
|
105 </li></ul>
|
cannam@167
|
106
|
cannam@167
|
107 <p>We assume herein that you are familiar with the properties and uses of
|
cannam@167
|
108 the DFT that are relevant to your application. Otherwise, see
|
cannam@167
|
109 e.g. <cite>The Fast Fourier Transform and Its Applications</cite> by E. O. Brigham
|
cannam@167
|
110 (Prentice-Hall, Englewood Cliffs, NJ, 1988).
|
cannam@167
|
111 <a href="http://www.fftw.org">Our web page</a> also has links to FFT-related
|
cannam@167
|
112 information online.
|
cannam@167
|
113 <a name="index-FFTW"></a>
|
cannam@167
|
114 </p>
|
cannam@167
|
115
|
cannam@167
|
116 <p>In order to use FFTW effectively, you need to learn one basic concept
|
cannam@167
|
117 of FFTW’s internal structure: FFTW does not use a fixed algorithm for
|
cannam@167
|
118 computing the transform, but instead it adapts the DFT algorithm to
|
cannam@167
|
119 details of the underlying hardware in order to maximize performance.
|
cannam@167
|
120 Hence, the computation of the transform is split into two phases.
|
cannam@167
|
121 First, FFTW’s <em>planner</em> “learns” the fastest way to compute the
|
cannam@167
|
122 transform on your machine. The planner
|
cannam@167
|
123 <a name="index-planner"></a>
|
cannam@167
|
124 produces a data structure called a <em>plan</em> that contains this
|
cannam@167
|
125 <a name="index-plan"></a>
|
cannam@167
|
126 information. Subsequently, the plan is <em>executed</em>
|
cannam@167
|
127 <a name="index-execute"></a>
|
cannam@167
|
128 to transform the array of input data as dictated by the plan. The
|
cannam@167
|
129 plan can be reused as many times as needed. In typical
|
cannam@167
|
130 high-performance applications, many transforms of the same size are
|
cannam@167
|
131 computed and, consequently, a relatively expensive initialization of
|
cannam@167
|
132 this sort is acceptable. On the other hand, if you need a single
|
cannam@167
|
133 transform of a given size, the one-time cost of the planner becomes
|
cannam@167
|
134 significant. For this case, FFTW provides fast planners based on
|
cannam@167
|
135 heuristics or on previously computed plans.
|
cannam@167
|
136 </p>
|
cannam@167
|
137 <p>FFTW supports transforms of data with arbitrary length, rank,
|
cannam@167
|
138 multiplicity, and a general memory layout. In simple cases, however,
|
cannam@167
|
139 this generality may be unnecessary and confusing. Consequently, we
|
cannam@167
|
140 organized the interface to FFTW into three levels of increasing
|
cannam@167
|
141 generality.
|
cannam@167
|
142 </p><ul>
|
cannam@167
|
143 <li> The <em>basic interface</em> computes a single
|
cannam@167
|
144 transform of contiguous data.
|
cannam@167
|
145 </li><li> The <em>advanced interface</em> computes transforms
|
cannam@167
|
146 of multiple or strided arrays.
|
cannam@167
|
147 </li><li> The <em>guru interface</em> supports the most general data
|
cannam@167
|
148 layouts, multiplicities, and strides.
|
cannam@167
|
149 </li></ul>
|
cannam@167
|
150 <p>We expect that most users will be best served by the basic interface,
|
cannam@167
|
151 whereas the guru interface requires careful attention to the
|
cannam@167
|
152 documentation to avoid problems.
|
cannam@167
|
153 <a name="index-basic-interface"></a>
|
cannam@167
|
154 <a name="index-advanced-interface"></a>
|
cannam@167
|
155 <a name="index-guru-interface"></a>
|
cannam@167
|
156 </p>
|
cannam@167
|
157
|
cannam@167
|
158 <p>Besides the automatic performance adaptation performed by the planner,
|
cannam@167
|
159 it is also possible for advanced users to customize FFTW manually. For
|
cannam@167
|
160 example, if code space is a concern, we provide a tool that links only
|
cannam@167
|
161 the subset of FFTW needed by your application. Conversely, you may need
|
cannam@167
|
162 to extend FFTW because the standard distribution is not sufficient for
|
cannam@167
|
163 your needs. For example, the standard FFTW distribution works most
|
cannam@167
|
164 efficiently for arrays whose size can be factored into small primes
|
cannam@167
|
165 (<em>2</em>, <em>3</em>, <em>5</em>, and <em>7</em>), and otherwise it uses a
|
cannam@167
|
166 slower general-purpose routine. If you need efficient transforms of
|
cannam@167
|
167 other sizes, you can use FFTW’s code generator, which produces fast C
|
cannam@167
|
168 programs (“codelets”) for any particular array size you may care
|
cannam@167
|
169 about.
|
cannam@167
|
170 <a name="index-code-generator"></a>
|
cannam@167
|
171 <a name="index-codelet"></a>
|
cannam@167
|
172 For example, if you need transforms of size
|
cannam@167
|
173 513 = 19*3<sup>3</sup>,
|
cannam@167
|
174 you can customize FFTW to support the factor <em>19</em> efficiently.
|
cannam@167
|
175 </p>
|
cannam@167
|
176 <p>For more information regarding FFTW, see the paper, “The Design and
|
cannam@167
|
177 Implementation of FFTW3,” by M. Frigo and S. G. Johnson, which was an
|
cannam@167
|
178 invited paper in <cite>Proc. IEEE</cite> <b>93</b> (2), p. 216 (2005). The
|
cannam@167
|
179 code generator is described in the paper “A fast Fourier transform
|
cannam@167
|
180 compiler”,
|
cannam@167
|
181 <a name="index-compiler"></a>
|
cannam@167
|
182 by M. Frigo, in the <cite>Proceedings of the 1999 ACM SIGPLAN Conference
|
cannam@167
|
183 on Programming Language Design and Implementation (PLDI), Atlanta,
|
cannam@167
|
184 Georgia, May 1999</cite>. These papers, along with the latest version of
|
cannam@167
|
185 FFTW, the FAQ, benchmarks, and other links, are available at
|
cannam@167
|
186 <a href="http://www.fftw.org">the FFTW home page</a>.
|
cannam@167
|
187 </p>
|
cannam@167
|
188 <p>The current version of FFTW incorporates many good ideas from the past
|
cannam@167
|
189 thirty years of FFT literature. In one way or another, FFTW uses the
|
cannam@167
|
190 Cooley-Tukey algorithm, the prime factor algorithm, Rader’s algorithm
|
cannam@167
|
191 for prime sizes, and a split-radix algorithm (with a
|
cannam@167
|
192 “conjugate-pair” variation pointed out to us by Dan Bernstein).
|
cannam@167
|
193 FFTW’s code generator also produces new algorithms that we do not
|
cannam@167
|
194 completely understand.
|
cannam@167
|
195 <a name="index-algorithm"></a>
|
cannam@167
|
196 The reader is referred to the cited papers for the appropriate
|
cannam@167
|
197 references.
|
cannam@167
|
198 </p>
|
cannam@167
|
199 <p>The rest of this manual is organized as follows. We first discuss the
|
cannam@167
|
200 sequential (single-processor) implementation. We start by describing
|
cannam@167
|
201 the basic interface/features of FFTW in <a href="Tutorial.html#Tutorial">Tutorial</a>.
|
cannam@167
|
202 Next, <a href="Other-Important-Topics.html#Other-Important-Topics">Other Important Topics</a> discusses data alignment
|
cannam@167
|
203 (see <a href="SIMD-alignment-and-fftw_005fmalloc.html#SIMD-alignment-and-fftw_005fmalloc">SIMD alignment and fftw_malloc</a>),
|
cannam@167
|
204 the storage scheme of multi-dimensional arrays
|
cannam@167
|
205 (see <a href="Multi_002ddimensional-Array-Format.html#Multi_002ddimensional-Array-Format">Multi-dimensional Array Format</a>), and FFTW’s mechanism for
|
cannam@167
|
206 storing plans on disk (see <a href="Words-of-Wisdom_002dSaving-Plans.html#Words-of-Wisdom_002dSaving-Plans">Words of Wisdom-Saving Plans</a>). Next,
|
cannam@167
|
207 <a href="FFTW-Reference.html#FFTW-Reference">FFTW Reference</a> provides comprehensive documentation of all
|
cannam@167
|
208 FFTW’s features. Parallel transforms are discussed in their own
|
cannam@167
|
209 chapters: <a href="Multi_002dthreaded-FFTW.html#Multi_002dthreaded-FFTW">Multi-threaded FFTW</a> and <a href="Distributed_002dmemory-FFTW-with-MPI.html#Distributed_002dmemory-FFTW-with-MPI">Distributed-memory FFTW with MPI</a>. Fortran programmers can also use FFTW, as described in
|
cannam@167
|
210 <a href="Calling-FFTW-from-Legacy-Fortran.html#Calling-FFTW-from-Legacy-Fortran">Calling FFTW from Legacy Fortran</a> and <a href="Calling-FFTW-from-Modern-Fortran.html#Calling-FFTW-from-Modern-Fortran">Calling FFTW from Modern Fortran</a>. <a href="Installation-and-Customization.html#Installation-and-Customization">Installation and Customization</a> explains how to
|
cannam@167
|
211 install FFTW in your computer system and how to adapt FFTW to your
|
cannam@167
|
212 needs. License and copyright information is given in <a href="License-and-Copyright.html#License-and-Copyright">License and Copyright</a>. Finally, we thank all the people who helped us in
|
cannam@167
|
213 <a href="Acknowledgments.html#Acknowledgments">Acknowledgments</a>.
|
cannam@167
|
214 </p>
|
cannam@167
|
215 <hr>
|
cannam@167
|
216 <div class="header">
|
cannam@167
|
217 <p>
|
cannam@167
|
218 Next: <a href="Tutorial.html#Tutorial" accesskey="n" rel="next">Tutorial</a>, Previous: <a href="index.html#Top" accesskey="p" rel="prev">Top</a>, Up: <a href="index.html#Top" accesskey="u" rel="up">Top</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>
|
cannam@167
|
219 </div>
|
cannam@167
|
220
|
cannam@167
|
221
|
cannam@167
|
222
|
cannam@167
|
223 </body>
|
cannam@167
|
224 </html>
|