You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
psblas3/docs/html/node59.html

453 lines
13 KiB
HTML

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">
<!--Converted with LaTeX2HTML 2008 (1.71)
original version by: Nikos Drakos, CBLU, University of Leeds
* revised and updated by: Marcus Hennecke, Ross Moore, Herb Swan
* with significant contributions from:
Jens Lippmann, Marek Rouchal, Martin Wilck and others -->
<HTML>
<HEAD>
<TITLE>psb_cdall -- Allocates a communication descriptor</TITLE>
<META NAME="description" CONTENT="psb_cdall -- Allocates a communication descriptor">
<META NAME="keywords" CONTENT="userhtml">
<META NAME="resource-type" CONTENT="document">
<META NAME="distribution" CONTENT="global">
<META NAME="Generator" CONTENT="LaTeX2HTML v2008">
<META HTTP-EQUIV="Content-Style-Type" CONTENT="text/css">
<LINK REL="STYLESHEET" HREF="userhtml.css">
<LINK REL="next" HREF="node60.html">
<LINK REL="previous" HREF="node58.html">
<LINK REL="up" HREF="node58.html">
<LINK REL="next" HREF="node60.html">
</HEAD>
<BODY >
<!--Navigation Panel-->
<A NAME="tex2html962"
HREF="node60.html">
<IMG WIDTH="37" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="next" SRC="next.png"></A>
<A NAME="tex2html958"
HREF="node58.html">
<IMG WIDTH="26" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="up" SRC="up.png"></A>
<A NAME="tex2html952"
HREF="node58.html">
<IMG WIDTH="63" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="previous" SRC="prev.png"></A>
<A NAME="tex2html960"
HREF="node1.html">
<IMG WIDTH="65" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="contents" SRC="contents.png"></A>
<BR>
<B> Next:</B> <A NAME="tex2html963"
HREF="node60.html">psb_cdins Communication</A>
<B> Up:</B> <A NAME="tex2html959"
HREF="node58.html">Data management routines</A>
<B> Previous:</B> <A NAME="tex2html953"
HREF="node58.html">Data management routines</A>
&nbsp; <B> <A NAME="tex2html961"
HREF="node1.html">Contents</A></B>
<BR>
<BR>
<!--End of Navigation Panel-->
<H2><A NAME="SECTION00071000000000000000">
psb_cdall -- Allocates a communication descriptor</A>
</H2>
<P>
<PRE>
call psb_cdall(icontxt, desc_a, info,mg=mg,parts=parts)
call psb_cdall(icontxt, desc_a, info,vg=vg,[mg=mg,flag=flag])
call psb_cdall(icontxt, desc_a, info,vl=vl,[nl=nl,globalcheck=.true.,lidx=lidx])
call psb_cdall(icontxt, desc_a, info,nl=nl)
call psb_cdall(icontxt, desc_a, info,mg=mg,repl=.true.)
</PRE>
<P>
This subroutine initializes the communication descriptor associated
with an index space. One of the optional arguments
<code>parts</code>, <code>vg</code>, <code>vl</code>, <code>nl</code> or <code>repl</code>
must be specified, thereby choosing
the specific initialization strategy.
<DL>
<DT><STRONG><B>On Entry </B></STRONG></DT>
<DD>
</DD>
<DT><STRONG>Type:</STRONG></DT>
<DD>Synchronous.
</DD>
<DT><STRONG>icontxt</STRONG></DT>
<DD>the communication context.
<BR>
Scope:<B>global</B>.
<BR>
Type:<B>required</B>.
<BR>
Intent: <B>in</B>.
<BR>
Specified as: an integer value.
</DD>
<DT><STRONG>vg</STRONG></DT>
<DD>Data allocation: each index <!-- MATH
$i\in \{1\dots mg\}$
-->
<IMG
WIDTH="99" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
SRC="img79.png"
ALT="$i\in \{1\dots mg\}$"> is allocated
to process <IMG
WIDTH="38" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
SRC="img80.png"
ALT="$vg(i)$">.
<BR>
Scope:<B>global</B>.
<BR>
Type:<B>optional</B>.
<BR>
Intent: <B>in</B>.
<BR>
Specified as: an integer array.
</DD>
<DT><STRONG>flag</STRONG></DT>
<DD>Specifies whether entries in <IMG
WIDTH="21" HEIGHT="30" ALIGN="MIDDLE" BORDER="0"
SRC="img81.png"
ALT="$vg$"> are zero- or one-based.
<BR>
Scope:<B>global</B>.
<BR>
Type:<B>optional</B>.
<BR>
Intent: <B>in</B>.
<BR>
Specified as: an integer value <IMG
WIDTH="27" HEIGHT="30" ALIGN="MIDDLE" BORDER="0"
SRC="img82.png"
ALT="$0,1$">, default <IMG
WIDTH="12" HEIGHT="14" ALIGN="BOTTOM" BORDER="0"
SRC="img83.png"
ALT="$0$">.
<P>
</DD>
<DT><STRONG>mg</STRONG></DT>
<DD>the (global) number of rows of the problem.
<BR>
Scope:<B>global</B>.
<BR>
Type:<B>optional</B>.
<BR>
Intent: <B>in</B>.
<BR>
Specified as: an integer value. It is required if <code>parts</code> or
<code>repl</code> is specified, it is optional if <code>vg</code> is specified.
</DD>
<DT><STRONG>parts</STRONG></DT>
<DD>the subroutine that defines the partitioning scheme.
<BR>
Scope:<B>global</B>.
<BR>
Type:<B>required</B>.
<BR>
Specified as: a subroutine.
</DD>
<DT><STRONG>vl</STRONG></DT>
<DD>Data allocation: the set of global indices
<IMG
WIDTH="65" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
SRC="img84.png"
ALT="$vl(1:nl)$"> belonging to the calling process.
<BR>
Scope:<B>local</B>.
<BR>
Type:<B>optional</B>.
<BR>
Intent: <B>in</B>.
<BR>
Specified as: an integer array.
</DD>
<DT><STRONG>nl</STRONG></DT>
<DD>Data allocation: in a generalized block-row distribution the
number of indices belonging to the current process.
<BR>
Scope:<B>local</B>.
<BR>
Type:<B>optional</B>.
<BR>
Intent: <B>in</B>.
<BR>
Specified as: an integer value. May be specified together with
<code>vl</code>.
</DD>
<DT><STRONG>repl</STRONG></DT>
<DD>Data allocation: build a replicated index space
(i.e. all processes own all indices).
<BR>
Scope:<B>global</B>.
<BR>
Type:<B>optional</B>.
<BR>
Intent: <B>in</B>.
<BR>
Specified as: the logical value <code>.true.</code>
</DD>
<DT><STRONG>globalcheck</STRONG></DT>
<DD>Data allocation: do global checks on the local
index lists <code>vl</code>
<BR>
Scope:<B>global</B>.
<BR>
Type:<B>optional</B>.
<BR>
Intent: <B>in</B>.
<BR>
Specified as: a logical value, default: <code>.true.</code>
</DD>
<DT><STRONG>lidx</STRONG></DT>
<DD>Data allocation: the set of local indices
<IMG
WIDTH="81" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
SRC="img85.png"
ALT="$lidx(1:nl)$"> to be assigned to the global indices <IMG
WIDTH="17" HEIGHT="15" ALIGN="BOTTOM" BORDER="0"
SRC="img86.png"
ALT="$vl$">.
<BR>
Scope:<B>local</B>.
<BR>
Type:<B>optional</B>.
<BR>
Intent: <B>in</B>.
<BR>
Specified as: an integer array.
</DD>
</DL>
<P>
<DL>
<DT><STRONG><B>On Return</B></STRONG></DT>
<DD>
</DD>
<DT><STRONG>desc_a</STRONG></DT>
<DD>the communication descriptor.
<BR>
Scope:<B>local</B>.
<BR>
Type:<B>required</B>.
<BR>
Intent: <B>out</B>.
<BR>
Specified as: a structured data of type descdata<TT>psb_desc_type</TT>.
</DD>
<DT><STRONG>info</STRONG></DT>
<DD>Error code.
<BR>
Scope: <B>local</B>
<BR>
Type: <B>required</B>
<BR>
Intent: <B>out</B>.
<BR>
An integer value; 0 means no error has been detected.
</DD>
</DL>
<P>
<FONT SIZE="+1"><B>Notes</B></FONT>
<OL>
<LI>One of the optional arguments <code>parts</code>, <code>vg</code>,
<code>vl</code>, <code>nl</code> or <code>repl</code> must be specified, thereby choosing the
initialization strategy as follows:
<DL>
<DT><STRONG>parts</STRONG></DT>
<DD>In this case we have a subroutine specifying the mapping
between global indices and process/local index pairs. If this
optional argument is specified, then it is mandatory to
specify the argument <code>mg</code> as well.
The subroutine must conform to the following interface:
<PRE>
interface
subroutine psb_parts(glob_index,mg,np,pv,nv)
integer, intent (in) :: glob_index,np,mg
integer, intent (out) :: nv, pv(*)
end subroutine psb_parts
end interface
</PRE>
The input arguments are:
<DL>
<DT><STRONG>glob_index</STRONG></DT>
<DD>The global index to be mapped;
</DD>
<DT><STRONG>np</STRONG></DT>
<DD>The number of processes in the mapping;
</DD>
<DT><STRONG>mg</STRONG></DT>
<DD>The total number of global rows in the mapping;
</DD>
</DL>
The output arguments are:
<DL>
<DT><STRONG>nv</STRONG></DT>
<DD>The number of entries in <code>pv</code>;
</DD>
<DT><STRONG>pv</STRONG></DT>
<DD>A vector containing the indices of the processes to
which the global index should be assigend; each entry must satisfy
<!-- MATH
$0\le pv(i) < np$
-->
<IMG
WIDTH="107" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
SRC="img87.png"
ALT="$0\le pv(i) &lt; np$">; if <IMG
WIDTH="51" HEIGHT="30" ALIGN="MIDDLE" BORDER="0"
SRC="img88.png"
ALT="$nv&gt;1$"> we have an index assigned to multiple
processes, i.e. we have an overlap among the subdomains.
</DD>
</DL>
</DD>
<DT><STRONG>vg</STRONG></DT>
<DD>In this case the association between an index and a process
is specified via an integer vector <code>vg(1:mg)</code>;
each index <!-- MATH
$i \in \{1\dots mg\}$
-->
<IMG
WIDTH="99" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
SRC="img79.png"
ALT="$i\in \{1\dots mg\}$"> is assigned to process <IMG
WIDTH="38" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
SRC="img80.png"
ALT="$vg(i)$">.
The vector <code>vg</code> must be identical on all
calling processes; its entries may have the ranges <IMG
WIDTH="94" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
SRC="img89.png"
ALT="$(0\dots np-1)$">
or <IMG
WIDTH="65" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
SRC="img90.png"
ALT="$(1\dots np)$"> according to the value of <code>flag</code>.
The size <IMG
WIDTH="27" HEIGHT="30" ALIGN="MIDDLE" BORDER="0"
SRC="img91.png"
ALT="$mg$"> may be specified via the optional argument <code>mg</code>;
the default is to use the entire vector <code>vg</code>, thus having
<code>mg=size(vg)</code>.
</DD>
<DT><STRONG>vl</STRONG></DT>
<DD>In this case we are specifying the list of indices
<code>vl(1:nl)</code> assigned to the current process; thus, the global
problem size <IMG
WIDTH="27" HEIGHT="30" ALIGN="MIDDLE" BORDER="0"
SRC="img91.png"
ALT="$mg$"> is given by
the range of the aggregate of the individual vectors <code>vl</code> specified
in the calling processes. The size may be specified via the optional
argument <code>nl</code>; the default is to use the entire vector
<code>vl</code>, thus having <code>nl=size(vl)</code>.
If <code>globalcheck=.true.</code> the subroutine will check how many
times each entry in the global index space <IMG
WIDTH="70" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
SRC="img92.png"
ALT="$(1\dots mg)$"> is
specified in the input lists <code>vl</code>, thus allowing for the
presence of overlap in the input, and checking for ``orphan''
indices. If <code>globalcheck=.false.</code>, the subroutine will not
check for overlap, and may be significantly faster, but the user
is implicitly guaranteeing that there are neither orphan nor
overlap indices.
</DD>
<DT><STRONG>lidx</STRONG></DT>
<DD>The optional argument <code>lidx</code> is available for
those cases in which the user has already established a
global-to-local mapping; if it is specified, each index in
<code>vl(i)</code> will be mapped to the corresponding local index
<code>lidx(i)</code>. When specifying the argument <code>lidx</code> the user
would also likely employ <code>lidx</code> in calls to <code>psb_cdins</code>
and <code>local</code> in calls to <code>psb_spins</code> and <code>psb_geins</code>;
see also sec.&nbsp;<A HREF="node7.html#sec:usermaps">2.3.1</A>.
</DD>
<DT><STRONG>nl</STRONG></DT>
<DD>If this argument is specified alone (i.e. without <code>vl</code>)
the result is a generalized row-block distribution in which each
process <IMG
WIDTH="13" HEIGHT="14" ALIGN="BOTTOM" BORDER="0"
SRC="img93.png"
ALT="$I$"> gets assigned a consecutive chunk of <IMG
WIDTH="60" HEIGHT="30" ALIGN="MIDDLE" BORDER="0"
SRC="img94.png"
ALT="$N_I=nl$"> global
indices.
</DD>
<DT><STRONG>repl</STRONG></DT>
<DD>This arguments specifies to replicate all indices on
all processes. This is a special purpose data allocation that is
useful in the construction of some multilevel preconditioners.
</DD>
</DL>
</LI>
<LI>On exit from this routine the descriptor is in the build
state.
</LI>
<LI>Calling the routine with <code>vg</code> or <code>parts</code> implies that
every process will scan the entire index space to figure out the
local indices.
</LI>
<LI>Overlapped indices are possible with both <code>parts</code> and
<code>vl</code> invocations.
</LI>
<LI>When the subroutine is invoked with <code>vl</code> in
conjunction with <code>globalcheck=.true.</code>, it will perform a scan
of the index space to search for overlap or orphan indices.
</LI>
<LI>When the subroutine is invoked with <code>vl</code> in
conjunction with <code>globalcheck=.false.</code>, no index space scan
will take place. Thus it is the responsibility of the user to make
sure that the indices specified in <code>vl</code> have neither orphans nor
overlaps; if this assumption fails, results will be
unpredictable.
</LI>
<LI>Orphan and overlap indices are
impossible by construction when the subroutine is invoked with
<code>nl</code> (alone), or <code>vg</code>.
</LI>
</OL>
<P>
<HR>
<!--Navigation Panel-->
<A NAME="tex2html962"
HREF="node60.html">
<IMG WIDTH="37" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="next" SRC="next.png"></A>
<A NAME="tex2html958"
HREF="node58.html">
<IMG WIDTH="26" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="up" SRC="up.png"></A>
<A NAME="tex2html952"
HREF="node58.html">
<IMG WIDTH="63" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="previous" SRC="prev.png"></A>
<A NAME="tex2html960"
HREF="node1.html">
<IMG WIDTH="65" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="contents" SRC="contents.png"></A>
<BR>
<B> Next:</B> <A NAME="tex2html963"
HREF="node60.html">psb_cdins Communication</A>
<B> Up:</B> <A NAME="tex2html959"
HREF="node58.html">Data management routines</A>
<B> Previous:</B> <A NAME="tex2html953"
HREF="node58.html">Data management routines</A>
&nbsp; <B> <A NAME="tex2html961"
HREF="node1.html">Contents</A></B>
<!--End of Navigation Panel-->
</BODY>
</HTML>