cannam@127
|
1 <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
|
cannam@127
|
2 <html>
|
cannam@127
|
3 <!-- This manual is for FFTW
|
cannam@127
|
4 (version 3.3.5, 30 July 2016).
|
cannam@127
|
5
|
cannam@127
|
6 Copyright (C) 2003 Matteo Frigo.
|
cannam@127
|
7
|
cannam@127
|
8 Copyright (C) 2003 Massachusetts Institute of Technology.
|
cannam@127
|
9
|
cannam@127
|
10 Permission is granted to make and distribute verbatim copies of this
|
cannam@127
|
11 manual provided the copyright notice and this permission notice are
|
cannam@127
|
12 preserved on all copies.
|
cannam@127
|
13
|
cannam@127
|
14 Permission is granted to copy and distribute modified versions of this
|
cannam@127
|
15 manual under the conditions for verbatim copying, provided that the
|
cannam@127
|
16 entire resulting derived work is distributed under the terms of a
|
cannam@127
|
17 permission notice identical to this one.
|
cannam@127
|
18
|
cannam@127
|
19 Permission is granted to copy and distribute translations of this manual
|
cannam@127
|
20 into another language, under the above conditions for modified versions,
|
cannam@127
|
21 except that this permission notice may be stated in a translation
|
cannam@127
|
22 approved by the Free Software Foundation. -->
|
cannam@127
|
23 <!-- Created by GNU Texinfo 5.2, http://www.gnu.org/software/texinfo/ -->
|
cannam@127
|
24 <head>
|
cannam@127
|
25 <title>FFTW 3.3.5: Installation on Unix</title>
|
cannam@127
|
26
|
cannam@127
|
27 <meta name="description" content="FFTW 3.3.5: Installation on Unix">
|
cannam@127
|
28 <meta name="keywords" content="FFTW 3.3.5: Installation on Unix">
|
cannam@127
|
29 <meta name="resource-type" content="document">
|
cannam@127
|
30 <meta name="distribution" content="global">
|
cannam@127
|
31 <meta name="Generator" content="makeinfo">
|
cannam@127
|
32 <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
|
cannam@127
|
33 <link href="index.html#Top" rel="start" title="Top">
|
cannam@127
|
34 <link href="Concept-Index.html#Concept-Index" rel="index" title="Concept Index">
|
cannam@127
|
35 <link href="index.html#SEC_Contents" rel="contents" title="Table of Contents">
|
cannam@127
|
36 <link href="Installation-and-Customization.html#Installation-and-Customization" rel="up" title="Installation and Customization">
|
cannam@127
|
37 <link href="Installation-on-non_002dUnix-systems.html#Installation-on-non_002dUnix-systems" rel="next" title="Installation on non-Unix systems">
|
cannam@127
|
38 <link href="Installation-and-Customization.html#Installation-and-Customization" rel="prev" title="Installation and Customization">
|
cannam@127
|
39 <style type="text/css">
|
cannam@127
|
40 <!--
|
cannam@127
|
41 a.summary-letter {text-decoration: none}
|
cannam@127
|
42 blockquote.smallquotation {font-size: smaller}
|
cannam@127
|
43 div.display {margin-left: 3.2em}
|
cannam@127
|
44 div.example {margin-left: 3.2em}
|
cannam@127
|
45 div.indentedblock {margin-left: 3.2em}
|
cannam@127
|
46 div.lisp {margin-left: 3.2em}
|
cannam@127
|
47 div.smalldisplay {margin-left: 3.2em}
|
cannam@127
|
48 div.smallexample {margin-left: 3.2em}
|
cannam@127
|
49 div.smallindentedblock {margin-left: 3.2em; font-size: smaller}
|
cannam@127
|
50 div.smalllisp {margin-left: 3.2em}
|
cannam@127
|
51 kbd {font-style:oblique}
|
cannam@127
|
52 pre.display {font-family: inherit}
|
cannam@127
|
53 pre.format {font-family: inherit}
|
cannam@127
|
54 pre.menu-comment {font-family: serif}
|
cannam@127
|
55 pre.menu-preformatted {font-family: serif}
|
cannam@127
|
56 pre.smalldisplay {font-family: inherit; font-size: smaller}
|
cannam@127
|
57 pre.smallexample {font-size: smaller}
|
cannam@127
|
58 pre.smallformat {font-family: inherit; font-size: smaller}
|
cannam@127
|
59 pre.smalllisp {font-size: smaller}
|
cannam@127
|
60 span.nocodebreak {white-space:nowrap}
|
cannam@127
|
61 span.nolinebreak {white-space:nowrap}
|
cannam@127
|
62 span.roman {font-family:serif; font-weight:normal}
|
cannam@127
|
63 span.sansserif {font-family:sans-serif; font-weight:normal}
|
cannam@127
|
64 ul.no-bullet {list-style: none}
|
cannam@127
|
65 -->
|
cannam@127
|
66 </style>
|
cannam@127
|
67
|
cannam@127
|
68
|
cannam@127
|
69 </head>
|
cannam@127
|
70
|
cannam@127
|
71 <body lang="en" bgcolor="#FFFFFF" text="#000000" link="#0000FF" vlink="#800080" alink="#FF0000">
|
cannam@127
|
72 <a name="Installation-on-Unix"></a>
|
cannam@127
|
73 <div class="header">
|
cannam@127
|
74 <p>
|
cannam@127
|
75 Next: <a href="Installation-on-non_002dUnix-systems.html#Installation-on-non_002dUnix-systems" accesskey="n" rel="next">Installation on non-Unix systems</a>, Previous: <a href="Installation-and-Customization.html#Installation-and-Customization" accesskey="p" rel="prev">Installation and Customization</a>, Up: <a href="Installation-and-Customization.html#Installation-and-Customization" accesskey="u" rel="up">Installation and Customization</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@127
|
76 </div>
|
cannam@127
|
77 <hr>
|
cannam@127
|
78 <a name="Installation-on-Unix-1"></a>
|
cannam@127
|
79 <h3 class="section">10.1 Installation on Unix</h3>
|
cannam@127
|
80
|
cannam@127
|
81 <p>FFTW comes with a <code>configure</code> program in the GNU style.
|
cannam@127
|
82 Installation can be as simple as:
|
cannam@127
|
83 <a name="index-configure-2"></a>
|
cannam@127
|
84 </p>
|
cannam@127
|
85 <div class="example">
|
cannam@127
|
86 <pre class="example">./configure
|
cannam@127
|
87 make
|
cannam@127
|
88 make install
|
cannam@127
|
89 </pre></div>
|
cannam@127
|
90
|
cannam@127
|
91 <p>This will build the uniprocessor complex and real transform libraries
|
cannam@127
|
92 along with the test programs. (We recommend that you use GNU
|
cannam@127
|
93 <code>make</code> if it is available; on some systems it is called
|
cannam@127
|
94 <code>gmake</code>.) The “<code>make install</code>” command installs the fftw
|
cannam@127
|
95 and rfftw libraries in standard places, and typically requires root
|
cannam@127
|
96 privileges (unless you specify a different install directory with the
|
cannam@127
|
97 <code>--prefix</code> flag to <code>configure</code>). You can also type
|
cannam@127
|
98 “<code>make check</code>” to put the FFTW test programs through their paces.
|
cannam@127
|
99 If you have problems during configuration or compilation, you may want
|
cannam@127
|
100 to run “<code>make distclean</code>” before trying again; this ensures that
|
cannam@127
|
101 you don’t have any stale files left over from previous compilation
|
cannam@127
|
102 attempts.
|
cannam@127
|
103 </p>
|
cannam@127
|
104 <p>The <code>configure</code> script chooses the <code>gcc</code> compiler by default,
|
cannam@127
|
105 if it is available; you can select some other compiler with:
|
cannam@127
|
106 </p><div class="example">
|
cannam@127
|
107 <pre class="example">./configure CC="<span class="roman"><i><the name of your C compiler></i></span>"
|
cannam@127
|
108 </pre></div>
|
cannam@127
|
109
|
cannam@127
|
110 <p>The <code>configure</code> script knows good <code>CFLAGS</code> (C compiler flags)
|
cannam@127
|
111 <a name="index-compiler-flags"></a>
|
cannam@127
|
112 for a few systems. If your system is not known, the <code>configure</code>
|
cannam@127
|
113 script will print out a warning. In this case, you should re-configure
|
cannam@127
|
114 FFTW with the command
|
cannam@127
|
115 </p><div class="example">
|
cannam@127
|
116 <pre class="example">./configure CFLAGS="<span class="roman"><i><write your CFLAGS here></i></span>"
|
cannam@127
|
117 </pre></div>
|
cannam@127
|
118 <p>and then compile as usual. If you do find an optimal set of
|
cannam@127
|
119 <code>CFLAGS</code> for your system, please let us know what they are (along
|
cannam@127
|
120 with the output of <code>config.guess</code>) so that we can include them in
|
cannam@127
|
121 future releases.
|
cannam@127
|
122 </p>
|
cannam@127
|
123 <p><code>configure</code> supports all the standard flags defined by the GNU
|
cannam@127
|
124 Coding Standards; see the <code>INSTALL</code> file in FFTW or
|
cannam@127
|
125 <a href="http://www.gnu.org/prep/standards/html_node/index.html">the GNU web page</a>.
|
cannam@127
|
126 Note especially <code>--help</code> to list all flags and
|
cannam@127
|
127 <code>--enable-shared</code> to create shared, rather than static, libraries.
|
cannam@127
|
128 <code>configure</code> also accepts a few FFTW-specific flags, particularly:
|
cannam@127
|
129 </p>
|
cannam@127
|
130 <ul>
|
cannam@127
|
131 <li> <a name="index-precision-9"></a>
|
cannam@127
|
132 <code>--enable-float</code>: Produces a single-precision version of FFTW
|
cannam@127
|
133 (<code>float</code>) instead of the default double-precision (<code>double</code>).
|
cannam@127
|
134 See <a href="Precision.html#Precision">Precision</a>.
|
cannam@127
|
135
|
cannam@127
|
136 </li><li> <a name="index-precision-10"></a>
|
cannam@127
|
137 <code>--enable-long-double</code>: Produces a long-double precision version of
|
cannam@127
|
138 FFTW (<code>long double</code>) instead of the default double-precision
|
cannam@127
|
139 (<code>double</code>). The <code>configure</code> script will halt with an error
|
cannam@127
|
140 message if <code>long double</code> is the same size as <code>double</code> on your
|
cannam@127
|
141 machine/compiler. See <a href="Precision.html#Precision">Precision</a>.
|
cannam@127
|
142
|
cannam@127
|
143 </li><li> <a name="index-precision-11"></a>
|
cannam@127
|
144 <code>--enable-quad-precision</code>: Produces a quadruple-precision version
|
cannam@127
|
145 of FFTW using the nonstandard <code>__float128</code> type provided by
|
cannam@127
|
146 <code>gcc</code> 4.6 or later on x86, x86-64, and Itanium architectures,
|
cannam@127
|
147 instead of the default double-precision (<code>double</code>). The
|
cannam@127
|
148 <code>configure</code> script will halt with an error message if the
|
cannam@127
|
149 compiler is not <code>gcc</code> version 4.6 or later or if <code>gcc</code>’s
|
cannam@127
|
150 <code>libquadmath</code> library is not installed. See <a href="Precision.html#Precision">Precision</a>.
|
cannam@127
|
151
|
cannam@127
|
152 </li><li> <a name="index-threads-3"></a>
|
cannam@127
|
153 <code>--enable-threads</code>: Enables compilation and installation of the
|
cannam@127
|
154 FFTW threads library (see <a href="Multi_002dthreaded-FFTW.html#Multi_002dthreaded-FFTW">Multi-threaded FFTW</a>), which provides a
|
cannam@127
|
155 simple interface to parallel transforms for SMP systems. By default,
|
cannam@127
|
156 the threads routines are not compiled.
|
cannam@127
|
157
|
cannam@127
|
158 </li><li> <code>--enable-openmp</code>: Like <code>--enable-threads</code>, but using OpenMP
|
cannam@127
|
159 compiler directives in order to induce parallelism rather than
|
cannam@127
|
160 spawning its own threads directly, and installing an ‘<samp>fftw3_omp</samp>’ library
|
cannam@127
|
161 rather than an ‘<samp>fftw3_threads</samp>’ library (see <a href="Multi_002dthreaded-FFTW.html#Multi_002dthreaded-FFTW">Multi-threaded FFTW</a>). You can use both <code>--enable-openmp</code> and <code>--enable-threads</code>
|
cannam@127
|
162 since they compile/install libraries with different names. By default,
|
cannam@127
|
163 the OpenMP routines are not compiled.
|
cannam@127
|
164
|
cannam@127
|
165 </li><li> <code>--with-combined-threads</code>: By default, if <code>--enable-threads</code>
|
cannam@127
|
166 is used, the threads support is compiled into a separate library that
|
cannam@127
|
167 must be linked in addition to the main FFTW library. This is so that
|
cannam@127
|
168 users of the serial library do not need to link the system threads
|
cannam@127
|
169 libraries. If <code>--with-combined-threads</code> is specified, however,
|
cannam@127
|
170 then no separate threads library is created, and threads are included
|
cannam@127
|
171 in the main FFTW library. This is mainly useful under Windows, where
|
cannam@127
|
172 no system threads library is required and inter-library dependencies
|
cannam@127
|
173 are problematic.
|
cannam@127
|
174
|
cannam@127
|
175 </li><li> <a name="index-MPI-1"></a>
|
cannam@127
|
176 <code>--enable-mpi</code>: Enables compilation and installation of the FFTW
|
cannam@127
|
177 MPI library (see <a href="Distributed_002dmemory-FFTW-with-MPI.html#Distributed_002dmemory-FFTW-with-MPI">Distributed-memory FFTW with MPI</a>), which provides
|
cannam@127
|
178 parallel transforms for distributed-memory systems with MPI. (By
|
cannam@127
|
179 default, the MPI routines are not compiled.) See <a href="FFTW-MPI-Installation.html#FFTW-MPI-Installation">FFTW MPI Installation</a>.
|
cannam@127
|
180
|
cannam@127
|
181 </li><li> <a name="index-Fortran_002dcallable-wrappers"></a>
|
cannam@127
|
182 <code>--disable-fortran</code>: Disables inclusion of legacy-Fortran
|
cannam@127
|
183 wrapper routines (see <a href="Calling-FFTW-from-Legacy-Fortran.html#Calling-FFTW-from-Legacy-Fortran">Calling FFTW from Legacy Fortran</a>) in the standard
|
cannam@127
|
184 FFTW libraries. These wrapper routines increase the library size by
|
cannam@127
|
185 only a negligible amount, so they are included by default as long as
|
cannam@127
|
186 the <code>configure</code> script finds a Fortran compiler on your system.
|
cannam@127
|
187 (To specify a particular Fortran compiler <i>foo</i>, pass
|
cannam@127
|
188 <code>F77=</code><i>foo</i> to <code>configure</code>.)
|
cannam@127
|
189
|
cannam@127
|
190 </li><li> <code>--with-g77-wrappers</code>: By default, when Fortran wrappers are
|
cannam@127
|
191 included, the wrappers employ the linking conventions of the Fortran
|
cannam@127
|
192 compiler detected by the <code>configure</code> script. If this compiler is
|
cannam@127
|
193 GNU <code>g77</code>, however, then <em>two</em> versions of the wrappers are
|
cannam@127
|
194 included: one with <code>g77</code>’s idiosyncratic convention of appending
|
cannam@127
|
195 two underscores to identifiers, and one with the more common
|
cannam@127
|
196 convention of appending only a single underscore. This way, the same
|
cannam@127
|
197 FFTW library will work with both <code>g77</code> and other Fortran
|
cannam@127
|
198 compilers, such as GNU <code>gfortran</code>. However, the converse is not
|
cannam@127
|
199 true: if you configure with a different compiler, then the
|
cannam@127
|
200 <code>g77</code>-compatible wrappers are not included. By specifying
|
cannam@127
|
201 <code>--with-g77-wrappers</code>, the <code>g77</code>-compatible wrappers are
|
cannam@127
|
202 included in addition to wrappers for whatever Fortran compiler
|
cannam@127
|
203 <code>configure</code> finds.
|
cannam@127
|
204 <a name="index-g77"></a>
|
cannam@127
|
205
|
cannam@127
|
206 </li><li> <code>--with-slow-timer</code>: Disables the use of hardware cycle counters,
|
cannam@127
|
207 and falls back on <code>gettimeofday</code> or <code>clock</code>. This greatly
|
cannam@127
|
208 worsens performance, and should generally not be used (unless you don’t
|
cannam@127
|
209 have a cycle counter but still really want an optimized plan regardless
|
cannam@127
|
210 of the time). See <a href="Cycle-Counters.html#Cycle-Counters">Cycle Counters</a>.
|
cannam@127
|
211
|
cannam@127
|
212 </li><li> <code>--enable-sse</code> (single precision),
|
cannam@127
|
213 <code>--enable-sse2</code> (single, double),
|
cannam@127
|
214 <code>--enable-avx</code> (single, double),
|
cannam@127
|
215 <code>--enable-avx2</code> (single, double),
|
cannam@127
|
216 <code>--enable-avx512</code> (single, double),
|
cannam@127
|
217 <code>--enable-avx-128-fma</code>,
|
cannam@127
|
218 <code>--enable-kcvi</code> (single),
|
cannam@127
|
219 <code>--enable-altivec</code> (single),
|
cannam@127
|
220 <code>--enable-vsx</code> (single, double),
|
cannam@127
|
221 <code>--enable-neon</code> (single, double on aarch64),
|
cannam@127
|
222 <code>--enable-generic-simd128</code>,
|
cannam@127
|
223 and
|
cannam@127
|
224 <code>--enable-generic-simd256</code>:
|
cannam@127
|
225
|
cannam@127
|
226 <p>Enable various SIMD instruction sets. You need compiler that supports
|
cannam@127
|
227 the given SIMD extensions, but FFTW will try to detect at runtime
|
cannam@127
|
228 whether the CPU supports these extensions. That is, you can compile
|
cannam@127
|
229 with<code>--enable-avx</code> and the code will still run on a CPU without AVX
|
cannam@127
|
230 support.
|
cannam@127
|
231 </p>
|
cannam@127
|
232 <ul class="no-bullet">
|
cannam@127
|
233 <li>- These options require a compiler supporting SIMD extensions, and
|
cannam@127
|
234 compiler support is always a bit flaky: see the FFTW FAQ for a list of
|
cannam@127
|
235 compiler versions that have problems compiling FFTW.
|
cannam@127
|
236 </li><li>- Because of the large variety of ARM processors and ABIs, FFTW
|
cannam@127
|
237 does not attempt to guess the correct <code>gcc</code> flags for generating
|
cannam@127
|
238 NEON code. In general, you will have to provide them on the command line.
|
cannam@127
|
239 This command line is known to have worked at least once:
|
cannam@127
|
240 <div class="example">
|
cannam@127
|
241 <pre class="example">./configure --with-slow-timer --host=arm-linux-gnueabi \
|
cannam@127
|
242 --enable-single --enable-neon \
|
cannam@127
|
243 "CC=arm-linux-gnueabi-gcc -march=armv7-a -mfloat-abi=softfp"
|
cannam@127
|
244 </pre></div>
|
cannam@127
|
245 </li></ul>
|
cannam@127
|
246
|
cannam@127
|
247 </li></ul>
|
cannam@127
|
248
|
cannam@127
|
249 <a name="index-compiler-2"></a>
|
cannam@127
|
250 <p>To force <code>configure</code> to use a particular C compiler <i>foo</i>
|
cannam@127
|
251 (instead of the default, usually <code>gcc</code>), pass <code>CC=</code><i>foo</i> to the
|
cannam@127
|
252 <code>configure</code> script; you may also need to set the flags via the variable
|
cannam@127
|
253 <code>CFLAGS</code> as described above.
|
cannam@127
|
254 <a name="index-compiler-flags-1"></a>
|
cannam@127
|
255 </p>
|
cannam@127
|
256 <hr>
|
cannam@127
|
257 <div class="header">
|
cannam@127
|
258 <p>
|
cannam@127
|
259 Next: <a href="Installation-on-non_002dUnix-systems.html#Installation-on-non_002dUnix-systems" accesskey="n" rel="next">Installation on non-Unix systems</a>, Previous: <a href="Installation-and-Customization.html#Installation-and-Customization" accesskey="p" rel="prev">Installation and Customization</a>, Up: <a href="Installation-and-Customization.html#Installation-and-Customization" accesskey="u" rel="up">Installation and Customization</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@127
|
260 </div>
|
cannam@127
|
261
|
cannam@127
|
262
|
cannam@127
|
263
|
cannam@127
|
264 </body>
|
cannam@127
|
265 </html>
|