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/src/toolsrout.tex

1829 lines
55 KiB
TeX

\section{Data management routines}
\label{sec:toolsrout}
%
%% psb_cdall %%
%
\subsection{psb\_cdall --- Allocates a communication descriptor}
\begin{verbatim}
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=.false.,lidx=lidx])
call psb_cdall(icontxt, desc_a, info,nl=nl)
call psb_cdall(icontxt, desc_a, info,mg=mg,repl=.true.)
\end{verbatim}
This subroutine initializes the communication descriptor associated
with an index space. One of the optional arguments
\verb|parts|, \verb|vg|, \verb|vl|, \verb|nl| or \verb|repl|
must be specified, thereby choosing
the specific initialization strategy.
\begin{description}
\item[\bf On Entry ]
\item[Type:] Synchronous.
\item[icontxt] the communication context.\\
Scope:{\bf global}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer value.
\item[vg] Data allocation: each index $i\in \{1\dots mg\}$ is allocated
to process $vg(i)$.\\
Scope:{\bf global}.\\
Type:{\bf optional}.\\
Intent: {\bf in}.\\
Specified as: an integer array.
\item[flag] Specifies whether entries in $vg$ are zero- or one-based.\\
Scope:{\bf global}.\\
Type:{\bf optional}.\\
Intent: {\bf in}.\\
Specified as: an integer value $0,1$, default $0$.
\item[mg] the (global) number of rows of the problem.\\
Scope:{\bf global}.\\
Type:{\bf optional}.\\
Intent: {\bf in}.\\
Specified as: an integer value. It is required if \verb|parts| or
\verb|repl| is specified, it is optional if \verb|vg| is specified.
\item[parts] the subroutine that defines the partitioning scheme.\\
Scope:{\bf global}.\\
Type:{\bf required}.\\
Specified as: a subroutine.
\item[vl] Data allocation: the set of global indices
$vl(1:nl)$ belonging to the calling process. \\
Scope:{\bf local}.\\
Type:{\bf optional}.\\
Intent: {\bf in}.\\
Specified as: an integer array.
\item[nl] Data allocation: in a generalized block-row distribution the
number of indices belonging to the current process. \\
Scope:{\bf local}.\\
Type:{\bf optional}.\\
Intent: {\bf in}.\\
Specified as: an integer value. May be specified together with
\verb|vl|.
\item[repl] Data allocation: build a replicated index space
(i.e. all processes own all indices).\\
Scope:{\bf global}.\\
Type:{\bf optional}.\\
Intent: {\bf in}.\\
Specified as: the logical value \verb|.true.|
\item[globalcheck] Data allocation: do global checks on the local
index lists \verb|vl|\\
Scope:{\bf global}.\\
Type:{\bf optional}.\\
Intent: {\bf in}.\\
Specified as: a logical value, default: \verb|.false.|
\item[lidx] Data allocation: the set of local indices
$lidx(1:nl)$ to be assigned to the global indices $vl$. \\
Scope:{\bf local}.\\
Type:{\bf optional}.\\
Intent: {\bf in}.\\
Specified as: an integer array.
\end{description}
\begin{description}
\item[\bf On Return]
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf out}.\\
Specified as: a structured data of type \descdata.
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item One of the optional arguments \verb|parts|, \verb|vg|,
\verb|vl|, \verb|nl| or \verb|repl| must be specified, thereby choosing the
initialization strategy as follows:
\begin{description}
\item[parts] 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 \verb|mg| as well.
The subroutine must conform to the following interface:
\begin{verbatim}
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
\end{verbatim}
The input arguments are:
\begin{description}
\item[glob\_index] The global index to be mapped;
\item[np] The number of processes in the mapping;
\item[mg] The total number of global rows in the mapping;
\end{description}
The output arguments are:
\begin{description}
\item[nv] The number of entries in \verb|pv|;
\item[pv] A vector containing the indices of the processes to
which the global index should be assigend; each entry must satisfy
$0\le pv(i) < np$; if $nv>1$ we have an index assigned to multiple
processes, i.e. we have an overlap among the subdomains.
\end{description}
\item[vg] In this case the association between an index and a process
is specified via an integer vector \verb|vg(1:mg)|;
each index $i \in \{1\dots mg\}$ is assigned to process $vg(i)$.
The vector \verb|vg| must be identical on all
calling processes; its entries may have the ranges $(0\dots np-1)$
or $(1\dots np)$ according to the value of \verb|flag|.
The size $mg$ may be specified via the optional argument \verb|mg|;
the default is to use the entire vector \verb|vg|, thus having
\verb|mg=size(vg)|.
\item[vl] In this case we are specifying the list of indices
\verb|vl(1:nl)| assigned to the current process; thus, the global
problem size $mg$ is given by
the range of the aggregate of the individual vectors \verb|vl| specified
in the calling processes. The size may be specified via the optional
argument \verb|nl|; the default is to use the entire vector
\verb|vl|, thus having \verb|nl=size(vl)|.
If \verb|globalcheck=.true.| the subroutine will check how many
times each entry in the global index space $(1\dots mg)$ is
specified in the input lists \verb|vl|, thus allowing for the
presence of overlap in the input, and checking for ``orphan''
indices. If \verb|globalcheck=.false.|, 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.
\item[lidx] The optional argument \verb|lidx| is available for
those cases in which the user has already established a
global-to-local mapping; if it is specified, each index in
\verb|vl(i)| will be mapped to the corresponding local index
\verb|lidx(i)|. When specifying the argument \verb|lidx| the user
would also likely employ \verb|lidx| in calls to \verb|psb_cdins|
and \verb|local| in calls to \verb|psb_spins| and \verb|psb_geins|;
see also sec.~\ref{sec:usermaps}.
\item[nl] If this argument is specified alone (i.e. without \verb|vl|)
the result is a generalized row-block distribution in which each
process $I$ gets assigned a consecutive chunk of $N_I=nl$ global
indices.
\item[repl] 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.
\end{description}
\item On exit from this routine the descriptor is in the build
state.
\item Calling the routine with \verb|vg| or \verb|parts| implies that
every process will scan the entire index space to figure out the
local indices.
\item Overlapped indices are possible with both \verb|parts| and
\verb|vl| invocations.
\item When the subroutine is invoked with \verb|vl| in
conjunction with \verb|globalcheck=.true.|, it will perform a scan
of the index space to search for overlap or orphan indices.
\item When the subroutine is invoked with \verb|vl| in
conjunction with \verb|globalcheck=.false.|, no index space scan
will take place. Thus it is the responsibility of the user to make
sure that the indices specified in \verb|vl| have neither orphans nor
overlaps; if this assumption fails, results will be
unpredictable.
\item Orphan and overlap indices are
impossible by construction when the subroutine is invoked with
\verb|nl| (alone), or \verb|vg|.
\end{enumerate}
%
%% psb_cdins %%
%
\clearpage\subsection{psb\_cdins --- Communication descriptor insert
routine}
\begin{verbatim}
call psb_cdins(nz, ia, ja, desc_a, info [,ila,jla])
call psb_cdins(nz,ja,desc,info[,jla,mask,lidx])
\end{verbatim}
This subroutine examines the edges of the graph associated with the
discretization mesh (and isomorphic to the sparsity pattern of a
linear system coefficient matrix), storing them as necessary into the
communication descriptor. In the first form the edges are specified as
pairs of indices $ia(i),ja(i)$; the starting index $ia(i)$ should
belong to the current process.
In the second form only the remote indices $ja(i)$ are specified.
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[nz] the number of points being inserted.\\
Scope: {\bf local}.\\
Type: {\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer value.
\item[ia] the indices of the starting vertex of the edges being inserted.\\
Scope: {\bf local}.\\
Type: {\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer array of length $nz$.
\item[ja] the indices of the end vertex of the edges being inserted.\\
Scope: {\bf local}.\\
Type: {\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer array of length $nz$.
\item[mask] Mask entries in \verb|ja|, they are inserted only when the
corresponding \verb|mask| entries are \verb|.true.|\\
Scope: {\bf local}.\\
Type: {\bf optional}.\\
Intent: {\bf in}.\\
Specified as: a logical array of length $nz$, default \verb|.true.|.
\item[lidx] User defined local indices for \verb|ja|.\\
Scope: {\bf local}.\\
Type: {\bf optional}.\\
Intent: {\bf in}.\\
Specified as: an integer array of length $nz$.
%% \item[is] the row offset.\\
%% Scope:{\bf local}.\\
%% Type:{\bf optional}.\\a
%% Specified as: an integer value.
%% \item[js] the column offset.\\
%% Scope: {\bf local}.\\
%% Type: {\bf optional}.\\
%% Specified as: an integer value.
\end{description}
\begin{description}
\item[\bf On Return]
\item[desc\_a] the updated communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf inout}.\\
Specified as: a structured data of type \descdata.
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\item[ila] the local indices of the starting vertex of the edges being inserted.\\
Scope: {\bf local}.\\
Type: {\bf optional}.\\
Intent: {\bf out}.\\
Specified as: an integer array of length $nz$.
\item[jla] the local indices of the end vertex of the edges being inserted.\\
Scope: {\bf local}.\\
Type: {\bf optional}.\\
Intent: {\bf out}.\\
Specified as: an integer array of length $nz$.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item This routine may only be called if the descriptor is in the
build state;
\item This routine automatically ignores edges that do not
insist on the current process, i.e. edges for which neither the starting
nor the end vertex belong to the current process.
\item The second form of this routine will be useful when dealing with
user-specified index mappings; see also~\ref{sec:usermaps}.
\end{enumerate}
%
%% psb_cdasb %%
%
\clearpage\subsection{psb\_cdasb --- Communication descriptor assembly
routine}
\begin{verbatim}
call psb_cdasb(desc_a, info [, mold])
\end{verbatim}
\begin{description}
\item[Type:] Synchronous.
\item[\bf On Entry]
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf inout}.\\
Specified as: a structured data of type \descdata.
\item[mold] The desired dynamic type for the internal index storage.\\
Scope: {\bf local}.\\
Type: {\bf optional}.\\
Intent: {\bf in}.\\
Specified as: a object of type derived from (integer) \vbasedata.
\end{description}
\begin{description}
\item[\bf On Return]
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf inout}.\\
Specified as: a structured data of type \descdata.
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
%\item[arg]
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item On exit from this routine the descriptor is in the assembled
state.
\end{enumerate}
This call will set up all the necessary information for the halo data
exchanges. In doing so, the library will need to identify the set of
processes owning the halo indices through the use of the
\verb|desc%fnd_owner()| method; the owning processes are the
topological neighbours of the calling process. If the user has some
background information on the processes that are neighbours of the
current one, it is possible to specify explicitly the list of adjacent
processes with a call to \verb|desc%set_p_adjcncy(list)|; this will
speed up the subsequent call to \verb|psb_cdasb|.
%
%% psb_cdcpy %%
%
\clearpage\subsection{psb\_cdcpy --- Copies a communication descriptor}
\begin{verbatim}
call psb_cdcpy(desc_in, desc_out, info)
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[desc\_in] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\end{description}
\begin{description}
\item[\bf On Return]
\item[desc\_out] the communication descriptor copy.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf out}.\\
Specified as: a structured data of type \descdata.
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
%
%% psb_cdfree %%
%
\clearpage\subsection{psb\_cdfree --- Frees a communication descriptor}
\begin{verbatim}
call psb_cdfree(desc_a, info)
\end{verbatim}
\begin{description}
\item[Type:] Synchronous.
\item[\bf On Entry]
\item[desc\_a] the communication descriptor to be freed.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf inout}.\\
Specified as: a structured data of type \descdata.
\end{description}
\begin{description}
\item[\bf On Return]
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
%
%% psb_cdcpy %%
%
\clearpage\subsection{psb\_cdbldext --- Build an extended communication
descriptor}
\begin{verbatim}
call psb_cdbldext(a,desc_a,nl,desc_out, info, extype)
\end{verbatim}
This subroutine builds an extended communication descriptor, based on
the input descriptor \verb|desc_a| and on the stencil specified
through the input sparse matrix \verb|a|.
\begin{description}
\item[Type:] Synchronous.
\item[\bf On Entry]
\item[a] A sparse matrix
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data type.
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \spdata.
\item[nl] the number of additional layers desired.\\
Scope:{\bf global}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer value $nl\ge 0$.
\item[extype] the kind of estension required.\\
Scope:{\bf global}.\\
Type:{\bf optional }.\\
Intent: {\bf in}.\\
Specified as: an integer value
\verb|psb_ovt_xhal_|, \verb|psb_ovt_asov_|, default: \verb|psb_ovt_xhal_|
\end{description}
\begin{description}
\item[\bf On Return]
\item[desc\_out] the extended communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf inout}.\\
Specified as: a structured data of type \descdata.
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item Specifying \verb|psb_ovt_xhal_| for the \verb|extype| argument
the user will obtain a descriptor for a domain partition in which
the additional layers are fetched as part of an (extended) halo;
however the index-to-process mapping is identical to that of the
base descriptor;
\item Specifying \verb|psb_ovt_asov_| for the \verb|extype| argument
the user will obtain a descriptor with an overlapped decomposition:
the additional layer is aggregated to the local subdomain (and thus
is an overlap), and a new halo extending beyond the last additional
layer is formed.
\end{enumerate}
%% %
%% %% psb_cdren %%
%% %
%% \subsection{psb\_cdren --- Applies a renumeration to a
%% communication descriptor}
%%% \addcontentsline{toc}{subsection}{psb\_cdren}
%% \syntax{call psb\_cdren}{trans, iperm, desc\_a, info}
%% \begin{description}
%% \item[\bf On Entry]
%% \item[Type:] Asynchronous.
%% \item[trans] A character that specifies whether to permute $A$ or $A^T$.\\
%% Scope: {\bf local} \\
%% Type: {\bf required}\\
%% Specified as: a single character with value 'N' for $A$ or 'T' for $A^T$.\\
%% \item[iperm] An integer array containing permutation information.\\
%% Scope: {\bf local} \\
%% Type: {\bf required}\\
%% Specified as: an integer one-dimensional array.\\
%% \item[desc\_a] the communication descriptor.\\
%% Scope:{\bf local}.\\
%% Type:{\bf required}.\\
%% Specified as: a structured data of type \descdata.
%% \end{description}
%% \begin{description}
%% \item[\bf On Return]
%% \item[info] Error code.
%% Scope: {\bf local} \\
%% Type: {\bf required}\\
%% Specified as: an integer variable.
%% \end{description}
%
%% psb_descprt %%
%
%% \subsection{psb\_cdprt --- Prints a descriptor}
%% \syntax{call psb\_cdprt}{iout, desc\_a, glob, short}
%% \begin{description}
%% \item[Type:] Asynchronous.
%% \item[\bf On Entry]
%% \item[iout] An integer that defines the output unit.
%% Scope: {\bf local} \\
%% Type: {\bf required}\\
%% Specified as: Integer scalar.\\
%% \item[desc\_a] The communication descriptor of type \descdata that
%% must be printed.\\
%% Scope: {\bf local} \\
%% Type: {\bf required}\\
%% Specified as: a variable of type \descdata.\\
%% \end{description}
%% \begin{description}
%% \item[\bf On Return]
%% \item[glob] ??????
%% \item[short] ??????
%% \end{description}
%
%% psb_spalloc %%
%
\clearpage\subsection{psb\_spall --- Allocates a sparse matrix}
\begin{verbatim}
call psb_spall(a, desc_a, info, nnz)
\end{verbatim}
\begin{description}
\item[Type:] Synchronous.
\item[\bf On Entry]
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\item[nnz] An estimate of the number of nonzeroes in the local
part of the assembled matrix.\\
Scope: {\bf global}.\\
Type: {\bf optional}.\\
Intent: {\bf in}.\\
Specified as: an integer value.
\end{description}
\begin{description}
\item[\bf On Return]
\item[a] the matrix to be allocated.\\
Scope:{\bf local}\\
Type:{\bf required}\\
Intent: {\bf out}.\\
Specified as: a structured data of type \spdata.
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item On exit from this routine the sparse matrix is in the build
state.
\item The descriptor may be in either the build or assembled state.
\item Providing a good estimate for the number of nonzeroes $nnz$ in
the assembled matrix may substantially improve performance in the
matrix build phase, as it will reduce or eliminate the need for
(potentially multiple) data reallocations.
\end{enumerate}
%
%% psb_spins %%
%
\clearpage\subsection{psb\_spins --- Insert a set of coefficients into a sparse
matrix}
\begin{verbatim}
call psb_spins(nz, ia, ja, val, a, desc_a, info [,local])
call psb_spins(nr, irw, irp, ja, val, a, desc_a, info [,local])
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[nz] the number of coefficients to be inserted.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer scalar.
\item[nr] the number of rows to be inserted.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer scalar.
\item[irw] the first row to be inserted.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer scalar.
\item[ia] the row indices of the coefficients to be inserted.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer array of size $nz$.
\item[irp] the row pointers of the coefficients to be inserted.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer array of size $nr+1$.
\item[ja] the column indices of the coefficients to be inserted.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer array of size $nz$.
\item[val] the coefficients to be inserted.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: an array of size $nz$. Must be of the same type and kind
of the coefficients of the sparse matrix $a$.
\item[desc\_a] The communication descriptor.\\
Scope: {\bf local}. \\
Type: {\bf required}.\\
Intent: {\bf inout}.\\
Specified as: a variable of type \descdata.\\
\item[local] Whether the entries in the indices vectors \verb|ia|,
\verb|ja| are already in local numbering. \\
Scope:{\bf local}.\\
Type:{\bf optional}.\\
Specified as: a logical value; default: \verb|.false.|.
%% \item[is] the starting row on matrix $a$.\\
%% Scope:{\bf local}.\\
%% Type:{\bf optional}.\\
%% Specified as: an integer vaule.
%% \item[js] the starting column on matrix $a$.\\
%% Scope:{\bf local}.\\
%% Type:{\bf optional}\\
%% Specified as: an integer value
\end{description}
\begin{description}
\item[\bf On Return]
\item[a] the matrix into which coefficients will be inserted.\\
Scope:{\bf local}\\
Type:{\bf required}\\
Intent: {\bf inout}.\\
Specified as: a structured data of type \spdata.
\item[desc\_a] The communication descriptor.\\
Scope: {\bf local}. \\
Type: {\bf required}.\\
Intent: {\bf inout}.\\
Specified as: a variable of type \descdata.\\
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item On entry to this routine the descriptor may be in either the
build or assembled state.
\item On entry to this routine the sparse matrix may be in either the
build or update state.
\item If the descriptor is in the build state, then the sparse matrix
must also be in the build state; the action of the routine is to
(implicitly) call \verb|psb_cdins| to add entries to the sparsity
pattern; each sparse matrix entry implicitly defines a graph edge,
that is passed to the descriptor routine for the appropriate
processing;
\item The input data can be passed in either COO or CSR formats;
\item In COO format the coefficients to be inserted are represented by
the ordered triples $ia(i),ja(i),val(i)$, for $i=1,\dots,nz$;
these triples should belong to the current process, i.e. $ia(i)$
should be one of the local indices, but are otherwise arbitrary;
\item In CSR format the coefficients to be inserted for each input row $i=1,nr$
are represented by the ordered triples $(i+irw-1),ja(j),val(j)$, for
$j=irp(i),\dots,irp(i+1)-1$;
these triples should belong to the current process, i.e. $i+irw-1$
should be one of the local indices, but are otherwise arbitrary;
\item There is no requirement that a given row must be passed in its
entirety to a single call to this routine: the buildup of a row
may be split into as many calls as desired (even in the CSR format);
\item Coefficients from different rows may also be mixed up freely
in a single call, according to the application needs;
\item Any coefficients from matrix rows not owned by the calling
process are silently ignored;
\item If the descriptor is in the assembled state, then any entries in
the sparse matrix that would generate additional communication
requirements are ignored;
\item If the matrix is in the update state, any entries in positions
that were not present in the original matrix are ignored.
\end{enumerate}
%
%% psb_spasb %%
%
\clearpage\subsection{psb\_spasb --- Sparse matrix assembly routine}
\begin{verbatim}
call psb_spasb(a, desc_a, info, afmt, upd, dupl, mold)
\end{verbatim}
\begin{description}
\item[Type:] Synchronous.
\item[\bf On Entry]
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\item[afmt] the storage format for the sparse matrix.\\
Scope: {\bf local}.\\
Type: {\bf optional}.\\
Intent: {\bf in}.\\
Specified as: an array of characters. Defalt: 'CSR'.
\item[upd] Provide for updates to the matrix coefficients.\\
Scope: {\bf global}.\\
Type: {\bf optional}.\\
Intent: {\bf in}.\\
Specified as: integer, possible values: \verb|psb_upd_srch_|, \verb|psb_upd_perm_|
\item[dupl] How to handle duplicate coefficients.\\
Scope: {\bf global}.\\
Type: {\bf optional}.\\
Intent: {\bf in}.\\
Specified as: integer, possible values: \verb|psb_dupl_ovwrt_|,
\verb|psb_dupl_add_|, \verb|psb_dupl_err_|.
\item[mold] The desired dynamic type for the internal matrix storage.\\
Scope: {\bf local}.\\
Type: {\bf optional}.\\
Intent: {\bf in}.\\
Specified as: an object of a class derived from \spbasedata.
\end{description}
\begin{description}
\item[\bf On Return]
\item[a] the matrix to be assembled.\\
Scope:{\bf local}\\
Type:{\bf required}\\
Intent: {\bf inout}.\\
Specified as: a structured data of type \spdata.
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item On entry to this routine the descriptor must be in the
assembled state, i.e. \verb|psb_cdasb| must already have been called.
\item The sparse matrix may be in either the build or update state;
\item Duplicate entries are detected and handled in both build and
update state, with the exception of the error action that is only
taken in the build state, i.e. on the first assembly;
\item If the update choice is \verb|psb_upd_perm_|, then subsequent
calls to \verb|psb_spins| to update the matrix must be arranged in
such a way as to produce exactly the same sequence of coefficient
values as encountered at the first assembly;
\item The output storage format need not be the same on all
processes;
\item On exit from this routine the matrix is in the assembled state,
and thus is suitable for the computational routines.
\end{enumerate}
%% %
%% %% psb_spcnv %%
%% %
%% \subsection{psb\_spcnv --- Converts a sparse matrix storage
%% format}
%% \syntax{call psb\_spcnv}{a, b, desc\_a, info}
%% \begin{description}
%% \item[\bf On Entry]
%% \item[a] the matrix to be converted.\\
%% Scope:{\bf local}\\
%% Type:{\bf required}\\
%% Specified as: a structured data of type \spdata.
%% \item[desc\_a] the communication descriptor.\\
%% Scope:{\bf local}.\\
%% Type:{\bf required}.\\
%% Specified as: a structured data of type \descdata.
%% \end{description}
%% \begin{description}
%% \item[\bf On Return]
%% \item[b] the converted matrix.\\
%% Scope:{\bf local}\\
%% Type:{\bf required}\\
%% Specified as: a structured data of type \spdata.
%% \item[info] Error code.
%% Scope: {\bf local} \\
%% Type: {\bf required}\\
%% Specified as: an integer variable.
%% \end{description}
%
%% psb_spfree %%
%
\clearpage\subsection{psb\_spfree --- Frees a sparse matrix}
\begin{verbatim}
call psb_spfree(a, desc_a, info)
\end{verbatim}
\begin{description}
\item[Type:] Synchronous.
\item[\bf On Entry]
\item[a] the matrix to be freed.\\
Scope:{\bf local}\\
Type:{\bf required}\\
Intent: {\bf inout}.\\
Specified as: a structured data of type \spdata.
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\end{description}
\begin{description}
\item[\bf On Return]
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
%
%% psb_sprn %%
%
\clearpage\subsection{psb\_sprn --- Reinit sparse matrix structure for psblas
routines.}
\begin{verbatim}
call psb_sprn(a, decsc_a, info, clear)
\end{verbatim}
\begin{description}
\item[Type:] Synchronous.
\item[\bf On Entry]
\item[a] the matrix to be reinitialized.\\
Scope:{\bf local}\\
Type:{\bf required}\\
Intent: {\bf inout}.\\
Specified as: a structured data of type \spdata.
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\item[clear] Choose whether to zero out matrix coefficients\\
Scope:{\bf local}.\\
Type:{\bf optional}.\\
Intent: {\bf in}.\\
Default: true.
\end{description}
\begin{description}
\item[\bf On Return]
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item On exit from this routine the sparse matrix is in the update
state.
\end{enumerate}
%
%% psb_spupdate %%
%
%% \subsection{psb\_spupdate --- Updates a sparse matrix.}
%% \syntax{call psb\_spupdate}{a, ia, ja, blck, desc\_a, info, ix, jx, updflag}
%% \begin{description}
%% \item[\bf On Entry]
%% \end{description}
%% \begin{description}
%% \item[\bf On Return]
%% \end{description}
%% %
%% %% psb_csrp %%
%% %
%% \subsection{psb\_csrp --- Applies a right permutation to a sparse
%% matrix}
%% \syntax{call psb\_csrp}{trans, iperm, a, info}
%% \begin{description}
%% \item[\bf On Entry]
%% \item[trans] A character that specifies whether to permute $A$ or $A^T$.\\
%% Scope: {\bf local} \\
%% Type: {\bf required}\\
%% Specified as: a single character with value 'N' for $A$ or 'T' for $A^T$.\\
%% \item[iperm] An integer array containing permutation information.\\
%% Scope: {\bf local} \\
%% Type: {\bf required}\\
%% Specified as: an integer one-dimensional array.\\
%% \item[a] The sparse matrix to be permuted.\\
%% Scope: {\bf local} \\
%% Type: {\bf required}\\
%% Specified as: a \spdata variable.\\
%% \begin{description}
%% \item[\bf On Return]
%% \item[info] Error code.\\
%% Scope: {\bf local} \\
%% Type: {\bf required}\\
%% Specified as: Integer scalar.\\
%% \end{description}
%
%% psb_alloc %%
%
\clearpage\subsection{psb\_geall --- Allocates a dense matrix}
%\addcontentsline{toc}{subsection}{psb\_geall}
\begin{verbatim}
call psb_geall(x, desc_a, info, n, lb)
\end{verbatim}
\begin{description}
\item[Type:] Synchronous.
\item[\bf On Entry]
\item[desc\_a] The communication descriptor.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in}.\\
Specified as: a variable of type \descdata.\\
\item[n] The number of columns of the dense matrix to be allocated.\\
Scope: {\bf local} \\
Type: {\bf optional}\\
Intent: {\bf in}.\\
Specified as: Integer scalar, default $1$. It is not a valid argument if $x$ is a
rank-1 array.
\item[lb] The lower bound for the column index range of the dense matrix to be allocated.\\
Scope: {\bf local} \\
Type: {\bf optional}\\
Intent: {\bf in}.\\
Specified as: Integer scalar, default $1$. It is not a valid argument if $x$ is a
rank-1 array.
\end{description}
\begin{description}
\item[\bf On Return]
\item[x] The dense matrix to be allocated.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf out}.\\
Specified as: a rank one or two array with the ALLOCATABLE attribute
or an object of type \vdata, of type real, complex or integer.\\
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
%
%% psb_ins %%
%
\clearpage\subsection{psb\_geins --- Dense matrix insertion routine}
%\addcontentsline{toc}{subsection}{psb\_geins}
\begin{verbatim}
call psb_geins(m, irw, val, x, desc_a, info [,dupl,local])
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[m] Number of rows in $val$ to be inserted.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer value.
\item[irw] Indices of the rows to be inserted. Specifically, row $i$
of $val$ will be inserted into the local row corresponding to the
global row index $irw(i)$.
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: an integer array.
\item[val] the dense submatrix to be inserted.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a rank 1 or 2 array.
Specified as: an integer value.
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\item[dupl] How to handle duplicate coefficients.\\
Scope: {\bf global}.\\
Type: {\bf optional}.\\
Intent: {\bf in}.\\
Specified as: integer, possible values: \verb|psb_dupl_ovwrt_|,
\verb|psb_dupl_add_|.
\item[local] Whether the entries in the index vector \verb|irw|,
are already in local numbering. \\
Scope:{\bf local}.\\
Type:{\bf optional}.\\
Specified as: a logical value; default: \verb|.false.|.
\end{description}
\begin{description}
\item[\bf On Return]
\item[x] the output dense matrix.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf inout}.\\
Specified as: a rank one or two array or an object of type \vdata, of
type real, complex or integer.\\
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item Dense vectors/matrices do not have an associated state;
\item Duplicate entries are either overwritten or added, there is no
provision for raising an error condition.
\end{enumerate}
%
%% psb_asb %%
%
\clearpage\subsection{psb\_geasb --- Assembly a dense matrix}
%\addcontentsline{toc}{subsection}{psb\_geasb}
\begin{verbatim}
call psb_geasb(x, desc_a, info, mold)
\end{verbatim}
\begin{description}
\item[Type:] Synchronous.
\item[\bf On Entry]
\item[desc\_a] The communication descriptor.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in}.\\
Specified as: a variable of type \descdata.\\
\item[mold] The desired dynamic type for the internal vector storage.\\
Scope: {\bf local}.\\
Type: {\bf optional}.\\
Intent: {\bf in}.\\
Specified as: an object of a class derived from \vbasedata; this is
only allowed when $x$ is of type \vdata.
\end{description}
\begin{description}
\item[\bf On Return]
\item[x] The dense matrix to be assembled.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf inout}.\\
Specified as: a rank one or two array with the ALLOCATABLE or an
object of type \vdata, of type real, complex or integer.\\
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
%
%% psb_free %%
%
\clearpage\subsection{psb\_gefree --- Frees a dense matrix}
%\addcontentsline{toc}{subsection}{psb\_gefree}
\begin{verbatim}
call psb_gefree(x, desc_a, info)
\end{verbatim}
\begin{description}
\item[Type:] Synchronous.
\item[\bf On Entry]
\item[x] The dense matrix to
be freed.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf inout}.\\
Specified as: a rank one or two array with the ALLOCATABLE or an
object of type \vdata, of type real, complex or integer.\\
\item[desc\_a] The communication descriptor.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in}.\\
Specified as: a variable of type \descdata.\\
\end{description}
\begin{description}
\item[\bf On Return]
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
%
%% psb_gelp %%
%
\clearpage\subsection{psb\_gelp --- Applies a left permutation to a dense
matrix}
%\addcontentsline{toc}{subsection}{psb\_gelp}
\begin{verbatim}
call psb_gelp(trans, iperm, x, info)
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[trans] A character that specifies whether to permute $A$ or $A^T$.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in}.\\
Specified as: a single character with value 'N' for $A$ or 'T' for $A^T$.\\
\item[iperm] An integer array containing permutation information.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in}.\\
Specified as: an integer one-dimensional array.\\
\item[x] The dense matrix to be permuted.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf inout}.\\
Specified as: a one or two dimensional array.\\
\end{description}
\begin{description}
\item[\bf On Return]
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
%
%% psb_glob_to_loc %%
%
\clearpage\subsection{psb\_glob\_to\_loc --- Global to local indices
convertion}
%\addcontentsline{toc}{subsection}{psb\_glob\_to\_loc}
\begin{verbatim}
call psb_glob_to_loc(x, y, desc_a, info, iact,owned)
call psb_glob_to_loc(x, desc_a, info, iact,owned)
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[x] An integer vector of indices to be converted.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in, inout}.\\
Specified as: a rank one integer array.\\
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\item[iact] specifies action to be taken in case of range errors.
Scope: {\bf global} \\
Type: {\bf optional}\\
Intent: {\bf in}.\\
Specified as: a character variable \verb|I|gnore, \verb|W|arning or
\verb|A|bort, default \verb|I|gnore.
\item[owned] Specfies valid range of input
Scope: {\bf global} \\
Type: {\bf optional}\\
Intent: {\bf in}.\\
If true, then only indices strictly owned by the current process are
considered valid, if false then halo indices are also
accepted. Default: false.
\end{description}
\begin{description}
\item[\bf On Return]
\item[x] If $y$ is not present,
then $x$ is overwritten with the translated integer indices.
Scope: {\bf global} \\
Type: {\bf required}\\
Intent: {\bf inout}.\\
Specified as: a rank one integer array.
\item[y] If $y$ is present,
then $y$ is overwritten with the translated integer indices, and $x$
is left unchanged.
Scope: {\bf global} \\
Type: {\bf optional}\\
Intent: {\bf out}.\\
Specified as: a rank one integer array.
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item If an input index is out of range, then the corresponding output
index is set to a negative number;
\item The default \verb|I|gnore means that the negative output is the
only action taken on an out-of-range input.
\end{enumerate}
\clearpage\subsection{psb\_loc\_to\_glob --- Local to global indices
conversion}
%\addcontentsline{toc}{subsection}{psb\_loc\_to\_glob}
\begin{verbatim}
call psb_loc_to_glob(x, y, desc_a, info, iact)
call psb_loc_to_glob(x, desc_a, info, iact)
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[x] An integer vector of indices to be converted.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in, inout}.\\
Specified as: a rank one integer array.\\
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\item[iact] specifies action to be taken in case of range errors.
Scope: {\bf global} \\
Type: {\bf optional}\\
Intent: {\bf in}.\\
Specified as: a character variable \verb|I|gnore, \verb|W|arning or
\verb|A|bort, default \verb|I|gnore.
\end{description}
\begin{description}
\item[\bf On Return]
\item[x] If $y$ is not present,
then $x$ is overwritten with the translated integer indices.
Scope: {\bf global} \\
Type: {\bf required}\\
Intent: {\bf inout}.\\
Specified as: a rank one integer array.
\item[y] If $y$ is not present,
then $y$ is overwritten with the translated integer indices, and $x$
is left unchanged.
Scope: {\bf global} \\
Type: {\bf optional}\\
Intent: {\bf out}.\\
Specified as: a rank one integer array.
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
%
%% psb_loc_to_glob %%
%
\clearpage\subsection{psb\_is\_owned --- }
%\addcontentsline{toc}{subsection}{psb\_is\_owned }
\begin{verbatim}
call psb_is_owned(x, desc_a)
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[x] Integer index.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in}.\\
Specified as: a scalar integer.\\
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\end{description}
\begin{description}
\item[\bf On Return]
\item[Function value] A logical mask which is true if
$x$ is owned by the current process
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf out}.\\
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item This routine returns a \verb|.true.| value for an index
that is strictly owned by the current process, excluding the halo
indices
\end{enumerate}
\clearpage\subsection{psb\_owned\_index --- }
%\addcontentsline{toc}{subsection}{psb\_owned\_index }
\begin{verbatim}
call psb_owned_index(y, x, desc_a, info)
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[x] Integer indices.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in, inout}.\\
Specified as: a scalar or a rank one integer array.\\
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\item[iact] specifies action to be taken in case of range errors.
Scope: {\bf global} \\
Type: {\bf optional}\\
Intent: {\bf in}.\\
Specified as: a character variable \verb|I|gnore, \verb|W|arning or
\verb|A|bort, default \verb|I|gnore.
\end{description}
\begin{description}
\item[\bf On Return]
\item[y] A logical mask which is true for all corresponding entries of
$x$ that are owned by the current process
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf out}.\\
Specified as: a scalar or rank one logical array.
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item This routine returns a \verb|.true.| value for those indices
that are strictly owned by the current process, excluding the halo
indices
\end{enumerate}
\clearpage\subsection{psb\_is\_local --- }
%\addcontentsline{toc}{subsection}{psb\_is\_local }
\begin{verbatim}
call psb_is_local(x, desc_a)
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[x] Integer index.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in}.\\
Specified as: a scalar integer.\\
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\end{description}
\begin{description}
\item[\bf On Return]
\item[Function value] A logical mask which is true if
$x$ is local to the current process
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf out}.\\
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item This routine returns a \verb|.true.| value for an index
that is local to the current process, including the halo
indices
\end{enumerate}
\clearpage\subsection{psb\_local\_index --- }
%\addcontentsline{toc}{subsection}{psb\_local\_index }
\begin{verbatim}
call psb_local_index(y, x, desc_a, info)
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[x] Integer indices.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in, inout}.\\
Specified as: a scalar or a rank one integer array.\\
\item[desc\_a] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\item[iact] specifies action to be taken in case of range errors.
Scope: {\bf global} \\
Type: {\bf optional}\\
Intent: {\bf in}.\\
Specified as: a character variable \verb|I|gnore, \verb|W|arning or
\verb|A|bort, default \verb|I|gnore.
\end{description}
\begin{description}
\item[\bf On Return]
\item[y] A logical mask which is true for all corresponding entries of
$x$ that are local to the current process
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf out}.\\
Specified as: a scalar or rank one logical array.
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item This routine returns a \verb|.true.| value for those indices
that are local to the current process, including the halo
indices.
\end{enumerate}
%
%% psb_ins %%
%
\clearpage\subsection{psb\_get\_boundary --- Extract list of boundary
elements}
%\addcontentsline{toc}{subsection}{psb\_get\_boundary}
\begin{verbatim}
call psb_get_boundary(bndel, desc, info)
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[desc] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\end{description}
\begin{description}
\item[\bf On Return]
\item[bndel] The list of boundary elements on the calling process, in
local numbering.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf out}.\\
Specified as: a rank one array with the ALLOCATABLE
attribute, of type integer.\\
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item If there are no boundary elements (i.e., if the local part of
the connectivity graph is self-contained) the output vector is set
to the ``not allocated'' state.
\item Otherwise the size of \verb|bndel| will be exactly equal to the
number of boundary elements.
\end{enumerate}
\clearpage\subsection{psb\_get\_overlap --- Extract list of overlap
elements}
%\addcontentsline{toc}{subsection}{psb\_get\_overlap}
\begin{verbatim}
call psb_get_overlap(ovrel, desc, info)
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[desc] the communication descriptor.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\end{description}
\begin{description}
\item[\bf On Return]
\item[ovrel] The list of overlap elements on the calling process, in
local numbering.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf out}.\\
Specified as: a rank one array with the ALLOCATABLE
attribute, of type integer.\\
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item If there are no overlap elements the output vector is set
to the ``not allocated'' state.
\item Otherwise the size of \verb|ovrel| will be exactly equal to the
number of overlap elements.
\end{enumerate}
\clearpage\subsection{psb\_sp\_getrow --- Extract row(s) from a sparse
matrix}
%\addcontentsline{toc}{subsection}{psb\_sp\_getrow}
\begin{verbatim}
call psb_sp_getrow(row, a, nz, ia, ja, val, info, &
& append, nzin, lrw)
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[row] The (first) row to be extracted.\\
Scope:{\bf local}\\
Type:{\bf required}\\
Intent: {\bf in}.\\
Specified as: an integer $>0$.
\item[a] the matrix from which to get rows.\\
Scope:{\bf local}\\
Type:{\bf required}\\
Intent: {\bf in}.\\
Specified as: a structured data of type \spdata.
\item[append] Whether to append or overwrite existing output.\\
Scope:{\bf local}\\
Type:{\bf optional}\\
Intent: {\bf in}.\\
Specified as: a logical value default: false (overwrite).
\item[nzin] Input size to be appended to.\\
Scope:{\bf local}\\
Type:{\bf optional}\\
Intent: {\bf in}.\\
Specified as: an integer $>0$. When append is true, specifies how many
entries in the output vectors are already filled.
\item[lrw] The last row to be extracted.\\
Scope:{\bf local}\\
Type:{\bf optional}\\
Intent: {\bf in}.\\
Specified as: an integer $>0$, default: $row$.
%% \item[is] the starting row on matrix $a$.\\
%% Scope:{\bf local}.\\
%% Type:{\bf optional}.\\
%% Specified as: an integer vaule.
%% \item[js] the starting column on matrix $a$.\\
%% Scope:{\bf local}.\\
%% Type:{\bf optional}\\
%% Specified as: an integer value
\end{description}
\begin{description}
\item[\bf On Return]
\item[nz] the number of elements returned by this call.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf out}.\\
Returned as: an integer scalar.
\item[ia] the row indices.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf inout}.\\
Specified as: an integer array with the \verb|ALLOCATABLE| attribute.
\item[ja] the column indices of the elements to be inserted.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf inout}.\\
Specified as: an integer array with the \verb|ALLOCATABLE| attribute.
\item[val] the elements to be inserted.\\
Scope:{\bf local}.\\
Type:{\bf required}.\\
Intent: {\bf inout}.\\
Specified as: a real array with the \verb|ALLOCATABLE| attribute.
\item[info] Error code.\\
Scope: {\bf local} \\
Type: {\bf required} \\
Intent: {\bf out}.\\
An integer value; 0 means no error has been detected.
\end{description}
{\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item The output $nz$ is always the size of the output generated by
the current call; thus, if \verb|append=.true.|, the total output
size will be $nzin+nz$, with the newly extracted coefficients stored in
entries \verb|nzin+1:nzin+nz| of the array arguments;
\item When \verb|append=.true.| the output arrays are reallocated as
necessary;
\item The row and column indices are returned in the local numbering
scheme; if the global numbering is desired, the user may employ the
\verb|psb_loc_to_glob| routine on the output.
\end{enumerate}
\clearpage\subsection{psb\_sizeof --- Memory occupation}
%\addcontentsline{toc}{subsection}{psb\_sizeof}
This function computes the memory occupation of a PSBLAS object.
\begin{verbatim}
isz = psb_sizeof(a)
isz = psb_sizeof(desc_a)
isz = psb_sizeof(prec)
\end{verbatim}
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry]
\item[a] A sparse matrix
$A$. \\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in}.\\
Specified as: a structured data of type \spdata.
\item[desc\_a] Communication descriptor.\\
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in}.\\
Specified as: a structured data of type \descdata.
\item[prec]
Scope: {\bf local} \\
Type: {\bf required}\\
Intent: {\bf in}.\\
Specified as: a preconditioner data structure \precdata.
\item[\bf On Return]
\item[Function value] The memory occupation of the object specified in
the calling sequence, in bytes.\\
Scope: {\bf local} \\
Returned as: an \verb|integer(psb_long_int_k_)| number.
\end{description}
\clearpage\subsection{Sorting utilities --- }
%\addcontentsline{toc}{subsection}{Sorting utilities}
{\par\noindent\large\bfseries psb\_msort --- Sorting by the Merge-sort
algorithm}
{\par\noindent\large\bfseries psb\_qsort --- Sorting by the Quicksort
algorithm}
{\par\noindent\large\bfseries psb\_hsort --- Sorting by the Heapsort algorithm}
\begin{verbatim}
call psb_msort(x,ix,dir,flag)
call psb_qsort(x,ix,dir,flag)
call psb_hsort(x,ix,dir,flag)
\end{verbatim}
These serial routines sort a sequence $X$ into ascending or
descending order. The argument meaning is identical for the three
calls; the only difference is the algorithm used to accomplish the
task (see Usage Notes below).
\begin{description}
\item[Type:] Asynchronous.
\item[\bf On Entry ]
\item[x] The sequence to be sorted.\\
Type:{\bf required}.\\
Specified as: an integer, real or complex array of rank 1.
\item[ix] A vector of indices.\\
Type:{\bf optional}.\\
Specified as: an integer array of (at least) the same size as $X$.
\item[dir] The desired ordering.\\
Type:{\bf optional}.\\
Specified as: an integer value: \begin{description}
\item[Integer and real data:] \verb|psb_sort_up_|,
\verb|psb_sort_down_|, \verb|psb_asort_up_|, \verb|psb_asort_down_|;
default \verb|psb_sort_up_|.
\item[Complex data:] \verb|psb_lsort_up_|,
\verb|psb_lsort_down_|, \verb|psb_asort_up_|, \verb|psb_asort_down_|;
default \verb|psb_lsort_up_|.
\end{description}
\item[flag] Whether to keep the original values in $IX$.\\
Type:{\bf optional}.\\
Specified as: an integer value \verb|psb_sort_ovw_idx_| or
\verb|psb_sort_keep_idx_|; default \verb|psb_sort_ovw_idx_|.
\end{description}
\begin{description}
\item[\bf On Return]
\item[x] The sequence of values, in the chosen ordering.\\
Type:{\bf required}.\\
Specified as: an integer, real or complex array of rank 1.
\item[ix] A vector of indices.\\
Type: {\bf Optional} \\
An integer array of rank 1, whose entries are moved to the same
position as the corresponding entries in $x$.
\end{description}
{\goodbreak\par\noindent\large\bfseries Notes}
\begin{enumerate}
\item For integer or real data the sorting can be performed in the up/down direction, on the
natural or absolute values;
\item For complex data the sorting can be done in a lexicographic
order (i.e.: sort on the real part with ties broken according to
the imaginary part) or on the absolute values;
\item The routines return the items in the chosen ordering; the
output difference is the handling of ties (i.e. items with an
equal value) in the original input. With the merge-sort algorithm
ties are preserved in the same relative order as they had in the
original sequence, while this is not guaranteed for quicksort or
heapsort;
\item If $flag = psb\_sort\_ovw\_idx\_$ then the entries in $ix(1:n)$
where $n$ is the size of $x$ are initialized to $ix(i) \leftarrow
i$; thus, upon return from the subroutine, for each
index $i$ we have in $ix(i)$ the position that the item $x(i)$
occupied in the original data sequence;
\item If $flag = psb\_sort\_keep\_idx\_$ the routine will assume that
the entries in $ix(:)$ have already been initialized by the user;
\item The three sorting algorithms have a similar $O(n \log n)$ expected
running time; in the average case quicksort will be the
fastest and merge-sort the slowest. However note that:
\begin{enumerate}
\item The worst case running time for quicksort is $O(n^2)$; the algorithm
implemented here follows the well-known median-of-three heuristics,
but the worst case may still apply;
\item The worst case running time for merge-sort and heap-sort is
$O(n\log n)$ as the average case;
\item The merge-sort algorithm is implemented to take advantage of
subsequences that may be already in the desired ordering prior to
the subroutine call; this situation is relatively common when
dealing with groups of indices of sparse matrix entries, thus
merge-sort is the preferred choice when a sorting is needed
by other routines in the library.
\end{enumerate}
\end{enumerate}
%%% Local Variables:
%%% mode: latex
%%% TeX-master: "userguide"
%%% End: