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: Installation on Unix</title>
|
cannam@167
|
26
|
cannam@167
|
27 <meta name="description" content="FFTW 3.3.8: Installation on Unix">
|
cannam@167
|
28 <meta name="keywords" content="FFTW 3.3.8: Installation on Unix">
|
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="Installation-and-Customization.html#Installation-and-Customization" rel="up" title="Installation and Customization">
|
cannam@167
|
37 <link href="Installation-on-non_002dUnix-systems.html#Installation-on-non_002dUnix-systems" rel="next" title="Installation on non-Unix systems">
|
cannam@167
|
38 <link href="Installation-and-Customization.html#Installation-and-Customization" rel="prev" title="Installation and Customization">
|
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="Installation-on-Unix"></a>
|
cannam@167
|
72 <div class="header">
|
cannam@167
|
73 <p>
|
cannam@167
|
74 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@167
|
75 </div>
|
cannam@167
|
76 <hr>
|
cannam@167
|
77 <a name="Installation-on-Unix-1"></a>
|
cannam@167
|
78 <h3 class="section">10.1 Installation on Unix</h3>
|
cannam@167
|
79
|
cannam@167
|
80 <p>FFTW comes with a <code>configure</code> program in the GNU style.
|
cannam@167
|
81 Installation can be as simple as:
|
cannam@167
|
82 <a name="index-configure-2"></a>
|
cannam@167
|
83 </p>
|
cannam@167
|
84 <div class="example">
|
cannam@167
|
85 <pre class="example">./configure
|
cannam@167
|
86 make
|
cannam@167
|
87 make install
|
cannam@167
|
88 </pre></div>
|
cannam@167
|
89
|
cannam@167
|
90 <p>This will build the uniprocessor complex and real transform libraries
|
cannam@167
|
91 along with the test programs. (We recommend that you use GNU
|
cannam@167
|
92 <code>make</code> if it is available; on some systems it is called
|
cannam@167
|
93 <code>gmake</code>.) The “<code>make install</code>” command installs the fftw
|
cannam@167
|
94 and rfftw libraries in standard places, and typically requires root
|
cannam@167
|
95 privileges (unless you specify a different install directory with the
|
cannam@167
|
96 <code>--prefix</code> flag to <code>configure</code>). You can also type
|
cannam@167
|
97 “<code>make check</code>” to put the FFTW test programs through their paces.
|
cannam@167
|
98 If you have problems during configuration or compilation, you may want
|
cannam@167
|
99 to run “<code>make distclean</code>” before trying again; this ensures that
|
cannam@167
|
100 you don’t have any stale files left over from previous compilation
|
cannam@167
|
101 attempts.
|
cannam@167
|
102 </p>
|
cannam@167
|
103 <p>The <code>configure</code> script chooses the <code>gcc</code> compiler by default,
|
cannam@167
|
104 if it is available; you can select some other compiler with:
|
cannam@167
|
105 </p><div class="example">
|
cannam@167
|
106 <pre class="example">./configure CC="<span class="roman"><i><the name of your C compiler></i></span>"
|
cannam@167
|
107 </pre></div>
|
cannam@167
|
108
|
cannam@167
|
109 <p>The <code>configure</code> script knows good <code>CFLAGS</code> (C compiler flags)
|
cannam@167
|
110 <a name="index-compiler-flags"></a>
|
cannam@167
|
111 for a few systems. If your system is not known, the <code>configure</code>
|
cannam@167
|
112 script will print out a warning. In this case, you should re-configure
|
cannam@167
|
113 FFTW with the command
|
cannam@167
|
114 </p><div class="example">
|
cannam@167
|
115 <pre class="example">./configure CFLAGS="<span class="roman"><i><write your CFLAGS here></i></span>"
|
cannam@167
|
116 </pre></div>
|
cannam@167
|
117 <p>and then compile as usual. If you do find an optimal set of
|
cannam@167
|
118 <code>CFLAGS</code> for your system, please let us know what they are (along
|
cannam@167
|
119 with the output of <code>config.guess</code>) so that we can include them in
|
cannam@167
|
120 future releases.
|
cannam@167
|
121 </p>
|
cannam@167
|
122 <p><code>configure</code> supports all the standard flags defined by the GNU
|
cannam@167
|
123 Coding Standards; see the <code>INSTALL</code> file in FFTW or
|
cannam@167
|
124 <a href="http://www.gnu.org/prep/standards/html_node/index.html">the GNU web page</a>.
|
cannam@167
|
125 Note especially <code>--help</code> to list all flags and
|
cannam@167
|
126 <code>--enable-shared</code> to create shared, rather than static, libraries.
|
cannam@167
|
127 <code>configure</code> also accepts a few FFTW-specific flags, particularly:
|
cannam@167
|
128 </p>
|
cannam@167
|
129 <ul>
|
cannam@167
|
130 <li> <a name="index-precision-9"></a>
|
cannam@167
|
131 <code>--enable-float</code>: Produces a single-precision version of FFTW
|
cannam@167
|
132 (<code>float</code>) instead of the default double-precision (<code>double</code>).
|
cannam@167
|
133 See <a href="Precision.html#Precision">Precision</a>.
|
cannam@167
|
134
|
cannam@167
|
135 </li><li> <a name="index-precision-10"></a>
|
cannam@167
|
136 <code>--enable-long-double</code>: Produces a long-double precision version of
|
cannam@167
|
137 FFTW (<code>long double</code>) instead of the default double-precision
|
cannam@167
|
138 (<code>double</code>). The <code>configure</code> script will halt with an error
|
cannam@167
|
139 message if <code>long double</code> is the same size as <code>double</code> on your
|
cannam@167
|
140 machine/compiler. See <a href="Precision.html#Precision">Precision</a>.
|
cannam@167
|
141
|
cannam@167
|
142 </li><li> <a name="index-precision-11"></a>
|
cannam@167
|
143 <code>--enable-quad-precision</code>: Produces a quadruple-precision version
|
cannam@167
|
144 of FFTW using the nonstandard <code>__float128</code> type provided by
|
cannam@167
|
145 <code>gcc</code> 4.6 or later on x86, x86-64, and Itanium architectures,
|
cannam@167
|
146 instead of the default double-precision (<code>double</code>). The
|
cannam@167
|
147 <code>configure</code> script will halt with an error message if the
|
cannam@167
|
148 compiler is not <code>gcc</code> version 4.6 or later or if <code>gcc</code>’s
|
cannam@167
|
149 <code>libquadmath</code> library is not installed. See <a href="Precision.html#Precision">Precision</a>.
|
cannam@167
|
150
|
cannam@167
|
151 </li><li> <a name="index-threads-3"></a>
|
cannam@167
|
152 <code>--enable-threads</code>: Enables compilation and installation of the
|
cannam@167
|
153 FFTW threads library (see <a href="Multi_002dthreaded-FFTW.html#Multi_002dthreaded-FFTW">Multi-threaded FFTW</a>), which provides a
|
cannam@167
|
154 simple interface to parallel transforms for SMP systems. By default,
|
cannam@167
|
155 the threads routines are not compiled.
|
cannam@167
|
156
|
cannam@167
|
157 </li><li> <code>--enable-openmp</code>: Like <code>--enable-threads</code>, but using OpenMP
|
cannam@167
|
158 compiler directives in order to induce parallelism rather than
|
cannam@167
|
159 spawning its own threads directly, and installing an ‘<samp>fftw3_omp</samp>’ library
|
cannam@167
|
160 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@167
|
161 since they compile/install libraries with different names. By default,
|
cannam@167
|
162 the OpenMP routines are not compiled.
|
cannam@167
|
163
|
cannam@167
|
164 </li><li> <code>--with-combined-threads</code>: By default, if <code>--enable-threads</code>
|
cannam@167
|
165 is used, the threads support is compiled into a separate library that
|
cannam@167
|
166 must be linked in addition to the main FFTW library. This is so that
|
cannam@167
|
167 users of the serial library do not need to link the system threads
|
cannam@167
|
168 libraries. If <code>--with-combined-threads</code> is specified, however,
|
cannam@167
|
169 then no separate threads library is created, and threads are included
|
cannam@167
|
170 in the main FFTW library. This is mainly useful under Windows, where
|
cannam@167
|
171 no system threads library is required and inter-library dependencies
|
cannam@167
|
172 are problematic.
|
cannam@167
|
173
|
cannam@167
|
174 </li><li> <a name="index-MPI-1"></a>
|
cannam@167
|
175 <code>--enable-mpi</code>: Enables compilation and installation of the FFTW
|
cannam@167
|
176 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@167
|
177 parallel transforms for distributed-memory systems with MPI. (By
|
cannam@167
|
178 default, the MPI routines are not compiled.) See <a href="FFTW-MPI-Installation.html#FFTW-MPI-Installation">FFTW MPI Installation</a>.
|
cannam@167
|
179
|
cannam@167
|
180 </li><li> <a name="index-Fortran_002dcallable-wrappers"></a>
|
cannam@167
|
181 <code>--disable-fortran</code>: Disables inclusion of legacy-Fortran
|
cannam@167
|
182 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@167
|
183 FFTW libraries. These wrapper routines increase the library size by
|
cannam@167
|
184 only a negligible amount, so they are included by default as long as
|
cannam@167
|
185 the <code>configure</code> script finds a Fortran compiler on your system.
|
cannam@167
|
186 (To specify a particular Fortran compiler <i>foo</i>, pass
|
cannam@167
|
187 <code>F77=</code><i>foo</i> to <code>configure</code>.)
|
cannam@167
|
188
|
cannam@167
|
189 </li><li> <code>--with-g77-wrappers</code>: By default, when Fortran wrappers are
|
cannam@167
|
190 included, the wrappers employ the linking conventions of the Fortran
|
cannam@167
|
191 compiler detected by the <code>configure</code> script. If this compiler is
|
cannam@167
|
192 GNU <code>g77</code>, however, then <em>two</em> versions of the wrappers are
|
cannam@167
|
193 included: one with <code>g77</code>’s idiosyncratic convention of appending
|
cannam@167
|
194 two underscores to identifiers, and one with the more common
|
cannam@167
|
195 convention of appending only a single underscore. This way, the same
|
cannam@167
|
196 FFTW library will work with both <code>g77</code> and other Fortran
|
cannam@167
|
197 compilers, such as GNU <code>gfortran</code>. However, the converse is not
|
cannam@167
|
198 true: if you configure with a different compiler, then the
|
cannam@167
|
199 <code>g77</code>-compatible wrappers are not included. By specifying
|
cannam@167
|
200 <code>--with-g77-wrappers</code>, the <code>g77</code>-compatible wrappers are
|
cannam@167
|
201 included in addition to wrappers for whatever Fortran compiler
|
cannam@167
|
202 <code>configure</code> finds.
|
cannam@167
|
203 <a name="index-g77"></a>
|
cannam@167
|
204
|
cannam@167
|
205 </li><li> <code>--with-slow-timer</code>: Disables the use of hardware cycle counters,
|
cannam@167
|
206 and falls back on <code>gettimeofday</code> or <code>clock</code>. This greatly
|
cannam@167
|
207 worsens performance, and should generally not be used (unless you don’t
|
cannam@167
|
208 have a cycle counter but still really want an optimized plan regardless
|
cannam@167
|
209 of the time). See <a href="Cycle-Counters.html#Cycle-Counters">Cycle Counters</a>.
|
cannam@167
|
210
|
cannam@167
|
211 </li><li> <code>--enable-sse</code> (single precision),
|
cannam@167
|
212 <code>--enable-sse2</code> (single, double),
|
cannam@167
|
213 <code>--enable-avx</code> (single, double),
|
cannam@167
|
214 <code>--enable-avx2</code> (single, double),
|
cannam@167
|
215 <code>--enable-avx512</code> (single, double),
|
cannam@167
|
216 <code>--enable-avx-128-fma</code>,
|
cannam@167
|
217 <code>--enable-kcvi</code> (single),
|
cannam@167
|
218 <code>--enable-altivec</code> (single),
|
cannam@167
|
219 <code>--enable-vsx</code> (single, double),
|
cannam@167
|
220 <code>--enable-neon</code> (single, double on aarch64),
|
cannam@167
|
221 <code>--enable-generic-simd128</code>,
|
cannam@167
|
222 and
|
cannam@167
|
223 <code>--enable-generic-simd256</code>:
|
cannam@167
|
224
|
cannam@167
|
225 <p>Enable various SIMD instruction sets. You need compiler that supports
|
cannam@167
|
226 the given SIMD extensions, but FFTW will try to detect at runtime
|
cannam@167
|
227 whether the CPU supports these extensions. That is, you can compile
|
cannam@167
|
228 with<code>--enable-avx</code> and the code will still run on a CPU without AVX
|
cannam@167
|
229 support.
|
cannam@167
|
230 </p>
|
cannam@167
|
231 <ul class="no-bullet">
|
cannam@167
|
232 <li>- These options require a compiler supporting SIMD extensions, and
|
cannam@167
|
233 compiler support is always a bit flaky: see the FFTW FAQ for a list of
|
cannam@167
|
234 compiler versions that have problems compiling FFTW.
|
cannam@167
|
235 </li><li>- Because of the large variety of ARM processors and ABIs, FFTW
|
cannam@167
|
236 does not attempt to guess the correct <code>gcc</code> flags for generating
|
cannam@167
|
237 NEON code. In general, you will have to provide them on the command line.
|
cannam@167
|
238 This command line is known to have worked at least once:
|
cannam@167
|
239 <div class="example">
|
cannam@167
|
240 <pre class="example">./configure --with-slow-timer --host=arm-linux-gnueabi \
|
cannam@167
|
241 --enable-single --enable-neon \
|
cannam@167
|
242 "CC=arm-linux-gnueabi-gcc -march=armv7-a -mfloat-abi=softfp"
|
cannam@167
|
243 </pre></div>
|
cannam@167
|
244 </li></ul>
|
cannam@167
|
245
|
cannam@167
|
246 </li></ul>
|
cannam@167
|
247
|
cannam@167
|
248 <a name="index-compiler-2"></a>
|
cannam@167
|
249 <p>To force <code>configure</code> to use a particular C compiler <i>foo</i>
|
cannam@167
|
250 (instead of the default, usually <code>gcc</code>), pass <code>CC=</code><i>foo</i> to the
|
cannam@167
|
251 <code>configure</code> script; you may also need to set the flags via the variable
|
cannam@167
|
252 <code>CFLAGS</code> as described above.
|
cannam@167
|
253 <a name="index-compiler-flags-1"></a>
|
cannam@167
|
254 </p>
|
cannam@167
|
255 <hr>
|
cannam@167
|
256 <div class="header">
|
cannam@167
|
257 <p>
|
cannam@167
|
258 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@167
|
259 </div>
|
cannam@167
|
260
|
cannam@167
|
261
|
cannam@167
|
262
|
cannam@167
|
263 </body>
|
cannam@167
|
264 </html>
|