Mercurial > hg > sv-dependency-builds

annotate src/fftw-3.3.8/doc/html/MPI-Plan-Creation.html @ 169:223a55898ab9 tip default

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Add null config files
author Chris Cannam <cannam@all-day-breakfast.com>
date Mon, 02 Mar 2020 14:03:47 +0000
parents bd3cc4d1df30
children
rev   line source
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: MPI Plan Creation</title>
cannam@167 26
cannam@167 27 <meta name="description" content="FFTW 3.3.8: MPI Plan Creation">
cannam@167 28 <meta name="keywords" content="FFTW 3.3.8: MPI Plan Creation">
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="FFTW-MPI-Reference.html#FFTW-MPI-Reference" rel="up" title="FFTW MPI Reference">
cannam@167 37 <link href="MPI-Wisdom-Communication.html#MPI-Wisdom-Communication" rel="next" title="MPI Wisdom Communication">
cannam@167 38 <link href="MPI-Data-Distribution-Functions.html#MPI-Data-Distribution-Functions" rel="prev" title="MPI Data Distribution Functions">
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="MPI-Plan-Creation"></a>
cannam@167 72 <div class="header">
cannam@167 73 <p>
cannam@167 74 Next: <a href="MPI-Wisdom-Communication.html#MPI-Wisdom-Communication" accesskey="n" rel="next">MPI Wisdom Communication</a>, Previous: <a href="MPI-Data-Distribution-Functions.html#MPI-Data-Distribution-Functions" accesskey="p" rel="prev">MPI Data Distribution Functions</a>, Up: <a href="FFTW-MPI-Reference.html#FFTW-MPI-Reference" accesskey="u" rel="up">FFTW MPI Reference</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>
cannam@167 75 </div>
cannam@167 76 <hr>
cannam@167 77 <a name="MPI-Plan-Creation-1"></a>
cannam@167 78 <h4 class="subsection">6.12.5 MPI Plan Creation</h4>
cannam@167 79
cannam@167 80 <a name="Complex_002ddata-MPI-DFTs"></a>
cannam@167 81 <h4 class="subsubheading">Complex-data MPI DFTs</h4>
cannam@167 82
cannam@167 83 <p>Plans for complex-data DFTs (see <a href="2d-MPI-example.html#g_t2d-MPI-example">2d MPI example</a>) are created by:
cannam@167 84 </p>
cannam@167 85 <a name="index-fftw_005fmpi_005fplan_005fdft_005f1d"></a>
cannam@167 86 <a name="index-fftw_005fmpi_005fplan_005fdft_005f2d-1"></a>
cannam@167 87 <a name="index-fftw_005fmpi_005fplan_005fdft_005f3d"></a>
cannam@167 88 <a name="index-fftw_005fmpi_005fplan_005fdft"></a>
cannam@167 89 <a name="index-fftw_005fmpi_005fplan_005fmany_005fdft"></a>
cannam@167 90 <div class="example">
cannam@167 91 <pre class="example">fftw_plan fftw_mpi_plan_dft_1d(ptrdiff_t n0, fftw_complex *in, fftw_complex *out,
cannam@167 92 MPI_Comm comm, int sign, unsigned flags);
cannam@167 93 fftw_plan fftw_mpi_plan_dft_2d(ptrdiff_t n0, ptrdiff_t n1,
cannam@167 94 fftw_complex *in, fftw_complex *out,
cannam@167 95 MPI_Comm comm, int sign, unsigned flags);
cannam@167 96 fftw_plan fftw_mpi_plan_dft_3d(ptrdiff_t n0, ptrdiff_t n1, ptrdiff_t n2,
cannam@167 97 fftw_complex *in, fftw_complex *out,
cannam@167 98 MPI_Comm comm, int sign, unsigned flags);
cannam@167 99 fftw_plan fftw_mpi_plan_dft(int rnk, const ptrdiff_t *n,
cannam@167 100 fftw_complex *in, fftw_complex *out,
cannam@167 101 MPI_Comm comm, int sign, unsigned flags);
cannam@167 102 fftw_plan fftw_mpi_plan_many_dft(int rnk, const ptrdiff_t *n,
cannam@167 103 ptrdiff_t howmany, ptrdiff_t block, ptrdiff_t tblock,
cannam@167 104 fftw_complex *in, fftw_complex *out,
cannam@167 105 MPI_Comm comm, int sign, unsigned flags);
cannam@167 106 </pre></div>
cannam@167 107
cannam@167 108 <a name="index-MPI-communicator-2"></a>
cannam@167 109 <a name="index-collective-function-4"></a>
cannam@167 110 <p>These are similar to their serial counterparts (see <a href="Complex-DFTs.html#Complex-DFTs">Complex DFTs</a>)
cannam@167 111 in specifying the dimensions, sign, and flags of the transform. The
cannam@167 112 <code>comm</code> argument gives an MPI communicator that specifies the set
cannam@167 113 of processes to participate in the transform; plan creation is a
cannam@167 114 collective function that must be called for all processes in the
cannam@167 115 communicator. The <code>in</code> and <code>out</code> pointers refer only to a
cannam@167 116 portion of the overall transform data (see <a href="MPI-Data-Distribution.html#MPI-Data-Distribution">MPI Data Distribution</a>)
cannam@167 117 as specified by the &lsquo;<samp>local_size</samp>&rsquo; functions in the previous
cannam@167 118 section. Unless <code>flags</code> contains <code>FFTW_ESTIMATE</code>, these
cannam@167 119 arrays are overwritten during plan creation as for the serial
cannam@167 120 interface. For multi-dimensional transforms, any dimensions <code>&gt;
cannam@167 121 1</code> are supported; for one-dimensional transforms, only composite
cannam@167 122 (non-prime) <code>n0</code> are currently supported (unlike the serial
cannam@167 123 FFTW). Requesting an unsupported transform size will yield a
cannam@167 124 <code>NULL</code> plan. (As in the serial interface, highly composite sizes
cannam@167 125 generally yield the best performance.)
cannam@167 126 </p>
cannam@167 127 <a name="index-advanced-interface-6"></a>
cannam@167 128 <a name="index-FFTW_005fMPI_005fDEFAULT_005fBLOCK-2"></a>
cannam@167 129 <a name="index-stride-3"></a>
cannam@167 130 <p>The advanced-interface <code>fftw_mpi_plan_many_dft</code> additionally
cannam@167 131 allows you to specify the block sizes for the first dimension
cannam@167 132 (<code>block</code>) of 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>
cannam@167 133 input data and the first dimension
cannam@167 134 (<code>tblock</code>) of the n<sub>1</sub>&nbsp;&times;&nbsp;n<sub>0</sub>&nbsp;&times;&nbsp;n<sub>2</sub>&nbsp;&times;&hellip;&times;&nbsp;n<sub>d-1</sub>
cannam@167 135 transposed data (at intermediate
cannam@167 136 steps of the transform, and for the output if
cannam@167 137 <code>FFTW_TRANSPOSED_OUT</code> is specified in <code>flags</code>). These must
cannam@167 138 be the same block sizes as were passed to the corresponding
cannam@167 139 &lsquo;<samp>local_size</samp>&rsquo; function; you can pass <code>FFTW_MPI_DEFAULT_BLOCK</code>
cannam@167 140 to use FFTW&rsquo;s default block size as in the basic interface. Also, the
cannam@167 141 <code>howmany</code> parameter specifies that the transform is of contiguous
cannam@167 142 <code>howmany</code>-tuples rather than individual complex numbers; this
cannam@167 143 corresponds to the same parameter in the serial advanced interface
cannam@167 144 (see <a href="Advanced-Complex-DFTs.html#Advanced-Complex-DFTs">Advanced Complex DFTs</a>) with <code>stride = howmany</code> and
cannam@167 145 <code>dist = 1</code>.
cannam@167 146 </p>
cannam@167 147 <a name="MPI-flags"></a>
cannam@167 148 <h4 class="subsubheading">MPI flags</h4>
cannam@167 149
cannam@167 150 <p>The <code>flags</code> can be any of those for the serial FFTW
cannam@167 151 (see <a href="Planner-Flags.html#Planner-Flags">Planner Flags</a>), and in addition may include one or more of
cannam@167 152 the following MPI-specific flags, which improve performance at the
cannam@167 153 cost of changing the output or input data formats.
cannam@167 154 </p>
cannam@167 155 <ul>
cannam@167 156 <li> <a name="index-FFTW_005fMPI_005fSCRAMBLED_005fOUT-2"></a>
cannam@167 157 <a name="index-FFTW_005fMPI_005fSCRAMBLED_005fIN-2"></a>
cannam@167 158 <code>FFTW_MPI_SCRAMBLED_OUT</code>, <code>FFTW_MPI_SCRAMBLED_IN</code>: valid for
cannam@167 159 1d transforms only, these flags indicate that the output/input of the
cannam@167 160 transform are in an undocumented &ldquo;scrambled&rdquo; order. A forward
cannam@167 161 <code>FFTW_MPI_SCRAMBLED_OUT</code> transform can be inverted by a backward
cannam@167 162 <code>FFTW_MPI_SCRAMBLED_IN</code> (times the usual 1/<i>N</i> normalization).
cannam@167 163 See <a href="One_002ddimensional-distributions.html#One_002ddimensional-distributions">One-dimensional distributions</a>.
cannam@167 164
cannam@167 165 </li><li> <a name="index-FFTW_005fMPI_005fTRANSPOSED_005fOUT-2"></a>
cannam@167 166 <a name="index-FFTW_005fMPI_005fTRANSPOSED_005fIN-2"></a>
cannam@167 167 <code>FFTW_MPI_TRANSPOSED_OUT</code>, <code>FFTW_MPI_TRANSPOSED_IN</code>: valid
cannam@167 168 for multidimensional (<code>rnk &gt; 1</code>) transforms only, these flags
cannam@167 169 specify that the output or input of 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;n<sub>d-1</sub>
cannam@167 170 transform is
cannam@167 171 transposed to n<sub>1</sub>&nbsp;&times;&nbsp;n<sub>0</sub>&nbsp;&times;&nbsp;n<sub>2</sub>&nbsp;&times;&hellip;&times;&nbsp;n<sub>d-1</sub>
cannam@167 172 . See <a href="Transposed-distributions.html#Transposed-distributions">Transposed distributions</a>.
cannam@167 173
cannam@167 174 </li></ul>
cannam@167 175
cannam@167 176 <a name="Real_002ddata-MPI-DFTs"></a>
cannam@167 177 <h4 class="subsubheading">Real-data MPI DFTs</h4>
cannam@167 178
cannam@167 179 <a name="index-r2c-4"></a>
cannam@167 180 <p>Plans for real-input/output (r2c/c2r) DFTs (see <a href="Multi_002ddimensional-MPI-DFTs-of-Real-Data.html#Multi_002ddimensional-MPI-DFTs-of-Real-Data">Multi-dimensional MPI DFTs of Real Data</a>) are created by:
cannam@167 181 </p>
cannam@167 182 <a name="index-fftw_005fmpi_005fplan_005fdft_005fr2c_005f2d"></a>
cannam@167 183 <a name="index-fftw_005fmpi_005fplan_005fdft_005fr2c_005f2d-1"></a>
cannam@167 184 <a name="index-fftw_005fmpi_005fplan_005fdft_005fr2c_005f3d"></a>
cannam@167 185 <a name="index-fftw_005fmpi_005fplan_005fdft_005fr2c"></a>
cannam@167 186 <a name="index-fftw_005fmpi_005fplan_005fdft_005fc2r_005f2d"></a>
cannam@167 187 <a name="index-fftw_005fmpi_005fplan_005fdft_005fc2r_005f2d-1"></a>
cannam@167 188 <a name="index-fftw_005fmpi_005fplan_005fdft_005fc2r_005f3d"></a>
cannam@167 189 <a name="index-fftw_005fmpi_005fplan_005fdft_005fc2r"></a>
cannam@167 190 <div class="example">
cannam@167 191 <pre class="example">fftw_plan fftw_mpi_plan_dft_r2c_2d(ptrdiff_t n0, ptrdiff_t n1,
cannam@167 192 double *in, fftw_complex *out,
cannam@167 193 MPI_Comm comm, unsigned flags);
cannam@167 194 fftw_plan fftw_mpi_plan_dft_r2c_2d(ptrdiff_t n0, ptrdiff_t n1,
cannam@167 195 double *in, fftw_complex *out,
cannam@167 196 MPI_Comm comm, unsigned flags);
cannam@167 197 fftw_plan fftw_mpi_plan_dft_r2c_3d(ptrdiff_t n0, ptrdiff_t n1, ptrdiff_t n2,
cannam@167 198 double *in, fftw_complex *out,
cannam@167 199 MPI_Comm comm, unsigned flags);
cannam@167 200 fftw_plan fftw_mpi_plan_dft_r2c(int rnk, const ptrdiff_t *n,
cannam@167 201 double *in, fftw_complex *out,
cannam@167 202 MPI_Comm comm, unsigned flags);
cannam@167 203 fftw_plan fftw_mpi_plan_dft_c2r_2d(ptrdiff_t n0, ptrdiff_t n1,
cannam@167 204 fftw_complex *in, double *out,
cannam@167 205 MPI_Comm comm, unsigned flags);
cannam@167 206 fftw_plan fftw_mpi_plan_dft_c2r_2d(ptrdiff_t n0, ptrdiff_t n1,
cannam@167 207 fftw_complex *in, double *out,
cannam@167 208 MPI_Comm comm, unsigned flags);
cannam@167 209 fftw_plan fftw_mpi_plan_dft_c2r_3d(ptrdiff_t n0, ptrdiff_t n1, ptrdiff_t n2,
cannam@167 210 fftw_complex *in, double *out,
cannam@167 211 MPI_Comm comm, unsigned flags);
cannam@167 212 fftw_plan fftw_mpi_plan_dft_c2r(int rnk, const ptrdiff_t *n,
cannam@167 213 fftw_complex *in, double *out,
cannam@167 214 MPI_Comm comm, unsigned flags);
cannam@167 215 </pre></div>
cannam@167 216
cannam@167 217 <p>Similar to the serial interface (see <a href="Real_002ddata-DFTs.html#Real_002ddata-DFTs">Real-data DFTs</a>), these
cannam@167 218 transform logically 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>
cannam@167 219 real 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)
cannam@167 220 complex
cannam@167 221 data, representing the non-redundant half of the conjugate-symmetry
cannam@167 222 output of a real-input DFT (see <a href="Multi_002ddimensional-Transforms.html#Multi_002ddimensional-Transforms">Multi-dimensional Transforms</a>).
cannam@167 223 However, the real array must be stored within a padded 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)]
cannam@167 224
cannam@167 225 array (much like the in-place serial r2c transforms, but here for
cannam@167 226 out-of-place transforms as well). Currently, only multi-dimensional
cannam@167 227 (<code>rnk &gt; 1</code>) r2c/c2r transforms are supported (requesting a plan
cannam@167 228 for <code>rnk = 1</code> will yield <code>NULL</code>). As explained above
cannam@167 229 (see <a href="Multi_002ddimensional-MPI-DFTs-of-Real-Data.html#Multi_002ddimensional-MPI-DFTs-of-Real-Data">Multi-dimensional MPI DFTs of Real Data</a>), the data
cannam@167 230 distribution of both the real and complex arrays is given by the
cannam@167 231 &lsquo;<samp>local_size</samp>&rsquo; function called for the dimensions of the
cannam@167 232 <em>complex</em> array. Similar to the other planning functions, the
cannam@167 233 input and output arrays are overwritten when the plan is created
cannam@167 234 except in <code>FFTW_ESTIMATE</code> mode.
cannam@167 235 </p>
cannam@167 236 <p>As for the complex DFTs above, there is an advance interface that
cannam@167 237 allows you to manually specify block sizes and to transform contiguous
cannam@167 238 <code>howmany</code>-tuples of real/complex numbers:
cannam@167 239 </p>
cannam@167 240 <a name="index-fftw_005fmpi_005fplan_005fmany_005fdft_005fr2c"></a>
cannam@167 241 <a name="index-fftw_005fmpi_005fplan_005fmany_005fdft_005fc2r"></a>
cannam@167 242 <div class="example">
cannam@167 243 <pre class="example">fftw_plan fftw_mpi_plan_many_dft_r2c
cannam@167 244 (int rnk, const ptrdiff_t *n, ptrdiff_t howmany,
cannam@167 245 ptrdiff_t iblock, ptrdiff_t oblock,
cannam@167 246 double *in, fftw_complex *out,
cannam@167 247 MPI_Comm comm, unsigned flags);
cannam@167 248 fftw_plan fftw_mpi_plan_many_dft_c2r
cannam@167 249 (int rnk, const ptrdiff_t *n, ptrdiff_t howmany,
cannam@167 250 ptrdiff_t iblock, ptrdiff_t oblock,
cannam@167 251 fftw_complex *in, double *out,
cannam@167 252 MPI_Comm comm, unsigned flags);
cannam@167 253 </pre></div>
cannam@167 254
cannam@167 255 <a name="MPI-r2r-transforms"></a>
cannam@167 256 <h4 class="subsubheading">MPI r2r transforms</h4>
cannam@167 257
cannam@167 258 <a name="index-r2r-4"></a>
cannam@167 259 <p>There are corresponding plan-creation routines for r2r
cannam@167 260 transforms (see <a href="More-DFTs-of-Real-Data.html#More-DFTs-of-Real-Data">More DFTs of Real Data</a>), currently supporting
cannam@167 261 multidimensional (<code>rnk &gt; 1</code>) transforms only (<code>rnk = 1</code> will
cannam@167 262 yield a <code>NULL</code> plan):
cannam@167 263 </p>
cannam@167 264 <div class="example">
cannam@167 265 <pre class="example">fftw_plan fftw_mpi_plan_r2r_2d(ptrdiff_t n0, ptrdiff_t n1,
cannam@167 266 double *in, double *out,
cannam@167 267 MPI_Comm comm,
cannam@167 268 fftw_r2r_kind kind0, fftw_r2r_kind kind1,
cannam@167 269 unsigned flags);
cannam@167 270 fftw_plan fftw_mpi_plan_r2r_3d(ptrdiff_t n0, ptrdiff_t n1, ptrdiff_t n2,
cannam@167 271 double *in, double *out,
cannam@167 272 MPI_Comm comm,
cannam@167 273 fftw_r2r_kind kind0, fftw_r2r_kind kind1, fftw_r2r_kind kind2,
cannam@167 274 unsigned flags);
cannam@167 275 fftw_plan fftw_mpi_plan_r2r(int rnk, const ptrdiff_t *n,
cannam@167 276 double *in, double *out,
cannam@167 277 MPI_Comm comm, const fftw_r2r_kind *kind,
cannam@167 278 unsigned flags);
cannam@167 279 fftw_plan fftw_mpi_plan_many_r2r(int rnk, const ptrdiff_t *n,
cannam@167 280 ptrdiff_t iblock, ptrdiff_t oblock,
cannam@167 281 double *in, double *out,
cannam@167 282 MPI_Comm comm, const fftw_r2r_kind *kind,
cannam@167 283 unsigned flags);
cannam@167 284 </pre></div>
cannam@167 285
cannam@167 286 <p>The parameters are much the same as for the complex DFTs above, except
cannam@167 287 that the arrays are of real numbers (and hence the outputs of the
cannam@167 288 &lsquo;<samp>local_size</samp>&rsquo; data-distribution functions should be interpreted as
cannam@167 289 counts of real rather than complex numbers). Also, the <code>kind</code>
cannam@167 290 parameters specify the r2r kinds along each dimension as for the
cannam@167 291 serial interface (see <a href="Real_002dto_002dReal-Transform-Kinds.html#Real_002dto_002dReal-Transform-Kinds">Real-to-Real Transform Kinds</a>). See <a href="Other-Multi_002ddimensional-Real_002ddata-MPI-Transforms.html#Other-Multi_002ddimensional-Real_002ddata-MPI-Transforms">Other Multi-dimensional Real-data MPI Transforms</a>.
cannam@167 292 </p>
cannam@167 293 <a name="MPI-transposition"></a>
cannam@167 294 <h4 class="subsubheading">MPI transposition</h4>
cannam@167 295 <a name="index-transpose-5"></a>
cannam@167 296
cannam@167 297 <p>FFTW also provides routines to plan a transpose of a distributed
cannam@167 298 <code>n0</code> by <code>n1</code> array of real numbers, or an array of
cannam@167 299 <code>howmany</code>-tuples of real numbers with specified block sizes
cannam@167 300 (see <a href="FFTW-MPI-Transposes.html#FFTW-MPI-Transposes">FFTW MPI Transposes</a>):
cannam@167 301 </p>
cannam@167 302 <a name="index-fftw_005fmpi_005fplan_005ftranspose-1"></a>
cannam@167 303 <a name="index-fftw_005fmpi_005fplan_005fmany_005ftranspose-1"></a>
cannam@167 304 <div class="example">
cannam@167 305 <pre class="example">fftw_plan fftw_mpi_plan_transpose(ptrdiff_t n0, ptrdiff_t n1,
cannam@167 306 double *in, double *out,
cannam@167 307 MPI_Comm comm, unsigned flags);
cannam@167 308 fftw_plan fftw_mpi_plan_many_transpose
cannam@167 309 (ptrdiff_t n0, ptrdiff_t n1, ptrdiff_t howmany,
cannam@167 310 ptrdiff_t block0, ptrdiff_t block1,
cannam@167 311 double *in, double *out, MPI_Comm comm, unsigned flags);
cannam@167 312 </pre></div>
cannam@167 313
cannam@167 314 <a name="index-new_002darray-execution-2"></a>
cannam@167 315 <a name="index-fftw_005fmpi_005fexecute_005fr2r-1"></a>
cannam@167 316 <p>These plans are used with the <code>fftw_mpi_execute_r2r</code> new-array
cannam@167 317 execute function (see <a href="Using-MPI-Plans.html#Using-MPI-Plans">Using MPI Plans</a>), since they count as (rank
cannam@167 318 zero) r2r plans from FFTW&rsquo;s perspective.
cannam@167 319 </p>
cannam@167 320 <hr>
cannam@167 321 <div class="header">
cannam@167 322 <p>
cannam@167 323 Next: <a href="MPI-Wisdom-Communication.html#MPI-Wisdom-Communication" accesskey="n" rel="next">MPI Wisdom Communication</a>, Previous: <a href="MPI-Data-Distribution-Functions.html#MPI-Data-Distribution-Functions" accesskey="p" rel="prev">MPI Data Distribution Functions</a>, Up: <a href="FFTW-MPI-Reference.html#FFTW-MPI-Reference" accesskey="u" rel="up">FFTW MPI Reference</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>
cannam@167 324 </div>
cannam@167 325
cannam@167 326
cannam@167 327
cannam@167 328 </body>
cannam@167 329 </html>