annotate src/fftw-3.3.5/doc/html/Multi_002ddimensional-MPI-DFTs-of-Real-Data.html @ 42:2cd0e3b3e1fd

Current fftw source
author Chris Cannam
date Tue, 18 Oct 2016 13:40:26 +0100
parents
children
rev   line source
Chris@42 1 <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
Chris@42 2 <html>
Chris@42 3 <!-- This manual is for FFTW
Chris@42 4 (version 3.3.5, 30 July 2016).
Chris@42 5
Chris@42 6 Copyright (C) 2003 Matteo Frigo.
Chris@42 7
Chris@42 8 Copyright (C) 2003 Massachusetts Institute of Technology.
Chris@42 9
Chris@42 10 Permission is granted to make and distribute verbatim copies of this
Chris@42 11 manual provided the copyright notice and this permission notice are
Chris@42 12 preserved on all copies.
Chris@42 13
Chris@42 14 Permission is granted to copy and distribute modified versions of this
Chris@42 15 manual under the conditions for verbatim copying, provided that the
Chris@42 16 entire resulting derived work is distributed under the terms of a
Chris@42 17 permission notice identical to this one.
Chris@42 18
Chris@42 19 Permission is granted to copy and distribute translations of this manual
Chris@42 20 into another language, under the above conditions for modified versions,
Chris@42 21 except that this permission notice may be stated in a translation
Chris@42 22 approved by the Free Software Foundation. -->
Chris@42 23 <!-- Created by GNU Texinfo 5.2, http://www.gnu.org/software/texinfo/ -->
Chris@42 24 <head>
Chris@42 25 <title>FFTW 3.3.5: Multi-dimensional MPI DFTs of Real Data</title>
Chris@42 26
Chris@42 27 <meta name="description" content="FFTW 3.3.5: Multi-dimensional MPI DFTs of Real Data">
Chris@42 28 <meta name="keywords" content="FFTW 3.3.5: Multi-dimensional MPI DFTs of Real Data">
Chris@42 29 <meta name="resource-type" content="document">
Chris@42 30 <meta name="distribution" content="global">
Chris@42 31 <meta name="Generator" content="makeinfo">
Chris@42 32 <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
Chris@42 33 <link href="index.html#Top" rel="start" title="Top">
Chris@42 34 <link href="Concept-Index.html#Concept-Index" rel="index" title="Concept Index">
Chris@42 35 <link href="index.html#SEC_Contents" rel="contents" title="Table of Contents">
Chris@42 36 <link href="Distributed_002dmemory-FFTW-with-MPI.html#Distributed_002dmemory-FFTW-with-MPI" rel="up" title="Distributed-memory FFTW with MPI">
Chris@42 37 <link href="Other-Multi_002ddimensional-Real_002ddata-MPI-Transforms.html#Other-Multi_002ddimensional-Real_002ddata-MPI-Transforms" rel="next" title="Other Multi-dimensional Real-data MPI Transforms">
Chris@42 38 <link href="One_002ddimensional-distributions.html#One_002ddimensional-distributions" rel="prev" title="One-dimensional distributions">
Chris@42 39 <style type="text/css">
Chris@42 40 <!--
Chris@42 41 a.summary-letter {text-decoration: none}
Chris@42 42 blockquote.smallquotation {font-size: smaller}
Chris@42 43 div.display {margin-left: 3.2em}
Chris@42 44 div.example {margin-left: 3.2em}
Chris@42 45 div.indentedblock {margin-left: 3.2em}
Chris@42 46 div.lisp {margin-left: 3.2em}
Chris@42 47 div.smalldisplay {margin-left: 3.2em}
Chris@42 48 div.smallexample {margin-left: 3.2em}
Chris@42 49 div.smallindentedblock {margin-left: 3.2em; font-size: smaller}
Chris@42 50 div.smalllisp {margin-left: 3.2em}
Chris@42 51 kbd {font-style:oblique}
Chris@42 52 pre.display {font-family: inherit}
Chris@42 53 pre.format {font-family: inherit}
Chris@42 54 pre.menu-comment {font-family: serif}
Chris@42 55 pre.menu-preformatted {font-family: serif}
Chris@42 56 pre.smalldisplay {font-family: inherit; font-size: smaller}
Chris@42 57 pre.smallexample {font-size: smaller}
Chris@42 58 pre.smallformat {font-family: inherit; font-size: smaller}
Chris@42 59 pre.smalllisp {font-size: smaller}
Chris@42 60 span.nocodebreak {white-space:nowrap}
Chris@42 61 span.nolinebreak {white-space:nowrap}
Chris@42 62 span.roman {font-family:serif; font-weight:normal}
Chris@42 63 span.sansserif {font-family:sans-serif; font-weight:normal}
Chris@42 64 ul.no-bullet {list-style: none}
Chris@42 65 -->
Chris@42 66 </style>
Chris@42 67
Chris@42 68
Chris@42 69 </head>
Chris@42 70
Chris@42 71 <body lang="en" bgcolor="#FFFFFF" text="#000000" link="#0000FF" vlink="#800080" alink="#FF0000">
Chris@42 72 <a name="Multi_002ddimensional-MPI-DFTs-of-Real-Data"></a>
Chris@42 73 <div class="header">
Chris@42 74 <p>
Chris@42 75 Next: <a href="Other-Multi_002ddimensional-Real_002ddata-MPI-Transforms.html#Other-Multi_002ddimensional-Real_002ddata-MPI-Transforms" accesskey="n" rel="next">Other Multi-dimensional Real-data MPI Transforms</a>, Previous: <a href="MPI-Data-Distribution.html#MPI-Data-Distribution" accesskey="p" rel="prev">MPI Data Distribution</a>, Up: <a href="Distributed_002dmemory-FFTW-with-MPI.html#Distributed_002dmemory-FFTW-with-MPI" accesskey="u" rel="up">Distributed-memory FFTW with MPI</a> &nbsp; [<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>
Chris@42 76 </div>
Chris@42 77 <hr>
Chris@42 78 <a name="Multi_002ddimensional-MPI-DFTs-of-Real-Data-1"></a>
Chris@42 79 <h3 class="section">6.5 Multi-dimensional MPI DFTs of Real Data</h3>
Chris@42 80
Chris@42 81 <p>FFTW&rsquo;s MPI interface also supports multi-dimensional DFTs of real
Chris@42 82 data, similar to the serial r2c and c2r interfaces. (Parallel
Chris@42 83 one-dimensional real-data DFTs are not currently supported; you must
Chris@42 84 use a complex transform and set the imaginary parts of the inputs to
Chris@42 85 zero.)
Chris@42 86 </p>
Chris@42 87 <p>The key points to understand for r2c and c2r MPI transforms (compared
Chris@42 88 to the MPI complex DFTs or the serial r2c/c2r transforms), are:
Chris@42 89 </p>
Chris@42 90 <ul>
Chris@42 91 <li> Just as for serial transforms, r2c/c2r DFTs transform n<sub>0</sub>&nbsp;&times;&nbsp;n<sub>1</sub>&nbsp;&times;&nbsp;n<sub>2</sub>&nbsp;&times;&nbsp;&hellip;&nbsp;&times;&nbsp;n<sub>d-1</sub> real
Chris@42 92 data to/from n<sub>0</sub>&nbsp;&times;&nbsp;n<sub>1</sub>&nbsp;&times;&nbsp;n<sub>2</sub>&nbsp;&times;&nbsp;&hellip;&nbsp;&times;&nbsp;(n<sub>d-1</sub>/2 + 1) complex data: the last dimension of the
Chris@42 93 complex data is cut in half (rounded down), plus one. As for the
Chris@42 94 serial transforms, the sizes you pass to the &lsquo;<samp>plan_dft_r2c</samp>&rsquo; and
Chris@42 95 &lsquo;<samp>plan_dft_c2r</samp>&rsquo; are the n<sub>0</sub>&nbsp;&times;&nbsp;n<sub>1</sub>&nbsp;&times;&nbsp;n<sub>2</sub>&nbsp;&times;&nbsp;&hellip;&nbsp;&times;&nbsp;n<sub>d-1</sub> dimensions of the real data.
Chris@42 96
Chris@42 97 </li><li> <a name="index-padding-4"></a>
Chris@42 98 Although the real data is <em>conceptually</em> n<sub>0</sub>&nbsp;&times;&nbsp;n<sub>1</sub>&nbsp;&times;&nbsp;n<sub>2</sub>&nbsp;&times;&nbsp;&hellip;&nbsp;&times;&nbsp;n<sub>d-1</sub>, it is
Chris@42 99 <em>physically</em> stored as an n<sub>0</sub>&nbsp;&times;&nbsp;n<sub>1</sub>&nbsp;&times;&nbsp;n<sub>2</sub>&nbsp;&times;&nbsp;&hellip;&nbsp;&times;&nbsp;[2&nbsp;(n<sub>d-1</sub>/2 + 1)] array, where the last
Chris@42 100 dimension has been <em>padded</em> to make it the same size as the
Chris@42 101 complex output. This is much like the in-place serial r2c/c2r
Chris@42 102 interface (see <a href="Multi_002dDimensional-DFTs-of-Real-Data.html#Multi_002dDimensional-DFTs-of-Real-Data">Multi-Dimensional DFTs of Real Data</a>), except that
Chris@42 103 in MPI the padding is required even for out-of-place data. The extra
Chris@42 104 padding numbers are ignored by FFTW (they are <em>not</em> like
Chris@42 105 zero-padding the transform to a larger size); they are only used to
Chris@42 106 determine the data layout.
Chris@42 107
Chris@42 108 </li><li> <a name="index-data-distribution-3"></a>
Chris@42 109 The data distribution in MPI for <em>both</em> the real and complex data
Chris@42 110 is determined by the shape of the <em>complex</em> data. That is, you
Chris@42 111 call the appropriate &lsquo;<samp>local size</samp>&rsquo; function for the n<sub>0</sub>&nbsp;&times;&nbsp;n<sub>1</sub>&nbsp;&times;&nbsp;n<sub>2</sub>&nbsp;&times;&nbsp;&hellip;&nbsp;&times;&nbsp;(n<sub>d-1</sub>/2 + 1)
Chris@42 112 complex data, and then use the <em>same</em> distribution for the real
Chris@42 113 data except that the last complex dimension is replaced by a (padded)
Chris@42 114 real dimension of twice the length.
Chris@42 115
Chris@42 116 </li></ul>
Chris@42 117
Chris@42 118 <p>For example suppose we are performing an out-of-place r2c transform of
Chris@42 119 L&nbsp;&times;&nbsp;M&nbsp;&times;&nbsp;N real data [padded to L&nbsp;&times;&nbsp;M&nbsp;&times;&nbsp;2(N/2+1)],
Chris@42 120 resulting in L&nbsp;&times;&nbsp;M&nbsp;&times;&nbsp;N/2+1 complex data. Similar to the
Chris@42 121 example in <a href="2d-MPI-example.html#g_t2d-MPI-example">2d MPI example</a>, we might do something like:
Chris@42 122 </p>
Chris@42 123 <div class="example">
Chris@42 124 <pre class="example">#include &lt;fftw3-mpi.h&gt;
Chris@42 125
Chris@42 126 int main(int argc, char **argv)
Chris@42 127 {
Chris@42 128 const ptrdiff_t L = ..., M = ..., N = ...;
Chris@42 129 fftw_plan plan;
Chris@42 130 double *rin;
Chris@42 131 fftw_complex *cout;
Chris@42 132 ptrdiff_t alloc_local, local_n0, local_0_start, i, j, k;
Chris@42 133
Chris@42 134 MPI_Init(&amp;argc, &amp;argv);
Chris@42 135 fftw_mpi_init();
Chris@42 136
Chris@42 137 /* <span class="roman">get local data size and allocate</span> */
Chris@42 138 alloc_local = fftw_mpi_local_size_3d(L, M, N/2+1, MPI_COMM_WORLD,
Chris@42 139 &amp;local_n0, &amp;local_0_start);
Chris@42 140 rin = fftw_alloc_real(2 * alloc_local);
Chris@42 141 cout = fftw_alloc_complex(alloc_local);
Chris@42 142
Chris@42 143 /* <span class="roman">create plan for out-of-place r2c DFT</span> */
Chris@42 144 plan = fftw_mpi_plan_dft_r2c_3d(L, M, N, rin, cout, MPI_COMM_WORLD,
Chris@42 145 FFTW_MEASURE);
Chris@42 146
Chris@42 147 /* <span class="roman">initialize rin to some function</span> my_func(x,y,z) */
Chris@42 148 for (i = 0; i &lt; local_n0; ++i)
Chris@42 149 for (j = 0; j &lt; M; ++j)
Chris@42 150 for (k = 0; k &lt; N; ++k)
Chris@42 151 rin[(i*M + j) * (2*(N/2+1)) + k] = my_func(local_0_start+i, j, k);
Chris@42 152
Chris@42 153 /* <span class="roman">compute transforms as many times as desired</span> */
Chris@42 154 fftw_execute(plan);
Chris@42 155
Chris@42 156 fftw_destroy_plan(plan);
Chris@42 157
Chris@42 158 MPI_Finalize();
Chris@42 159 }
Chris@42 160 </pre></div>
Chris@42 161
Chris@42 162 <a name="index-fftw_005falloc_005freal-2"></a>
Chris@42 163 <a name="index-row_002dmajor-5"></a>
Chris@42 164 <p>Note that we allocated <code>rin</code> using <code>fftw_alloc_real</code> with an
Chris@42 165 argument of <code>2 * alloc_local</code>: since <code>alloc_local</code> is the
Chris@42 166 number of <em>complex</em> values to allocate, the number of <em>real</em>
Chris@42 167 values is twice as many. The <code>rin</code> array is then
Chris@42 168 local_n0&nbsp;&times;&nbsp;M&nbsp;&times;&nbsp;2(N/2+1) in row-major order, so its
Chris@42 169 <code>(i,j,k)</code> element is at the index <code>(i*M + j) * (2*(N/2+1)) +
Chris@42 170 k</code> (see <a href="Multi_002ddimensional-Array-Format.html#Multi_002ddimensional-Array-Format">Multi-dimensional Array Format</a>).
Chris@42 171 </p>
Chris@42 172 <a name="index-transpose-1"></a>
Chris@42 173 <a name="index-FFTW_005fTRANSPOSED_005fOUT"></a>
Chris@42 174 <a name="index-FFTW_005fTRANSPOSED_005fIN"></a>
Chris@42 175 <p>As for the complex transforms, improved performance can be obtained by
Chris@42 176 specifying that the output is the transpose of the input or vice versa
Chris@42 177 (see <a href="Transposed-distributions.html#Transposed-distributions">Transposed distributions</a>). In our L&nbsp;&times;&nbsp;M&nbsp;&times;&nbsp;N r2c
Chris@42 178 example, including <code>FFTW_TRANSPOSED_OUT</code> in the flags means that
Chris@42 179 the input would be a padded L&nbsp;&times;&nbsp;M&nbsp;&times;&nbsp;2(N/2+1) real array
Chris@42 180 distributed over the <code>L</code> dimension, while the output would be a
Chris@42 181 M&nbsp;&times;&nbsp;L&nbsp;&times;&nbsp;N/2+1 complex array distributed over the <code>M</code>
Chris@42 182 dimension. To perform the inverse c2r transform with the same data
Chris@42 183 distributions, you would use the <code>FFTW_TRANSPOSED_IN</code> flag.
Chris@42 184 </p>
Chris@42 185 <hr>
Chris@42 186 <div class="header">
Chris@42 187 <p>
Chris@42 188 Next: <a href="Other-Multi_002ddimensional-Real_002ddata-MPI-Transforms.html#Other-Multi_002ddimensional-Real_002ddata-MPI-Transforms" accesskey="n" rel="next">Other Multi-dimensional Real-data MPI Transforms</a>, Previous: <a href="MPI-Data-Distribution.html#MPI-Data-Distribution" accesskey="p" rel="prev">MPI Data Distribution</a>, Up: <a href="Distributed_002dmemory-FFTW-with-MPI.html#Distributed_002dmemory-FFTW-with-MPI" accesskey="u" rel="up">Distributed-memory FFTW with MPI</a> &nbsp; [<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>
Chris@42 189 </div>
Chris@42 190
Chris@42 191
Chris@42 192
Chris@42 193 </body>
Chris@42 194 </html>