fdurastante/amg4psblas
1
0
Fork 0
mirror of https://github.com/sfilippone/amg4psblas.git synced 2026-10-07 07:04:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed table splitting among pages

Browse Source
This commit is contained in:
Cirdans-Home
2021-03-11 09:28:02 +01:00
parent d1447297c5
commit ea6411c730
25 changed files with 1203 additions and 1055 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/src/bibliography.tex
+5
View File
@@ -12,6 +12,11 @@ P.~R.~Amestoy, C.~Ashcraft, O.~Boiteau, A.~Buttari, J.~L'Excellent, C.~Weisbecke
SIAM Journal on Scientific Computing, volume 37 (3), 2015, A1452--A1474.
See also {\tt http://mumps.enseeiht.fr}.
%
\bibitem{BERTACCINIFILIPPONE}
D. Bertaccini\ and\ S. Filippone,
{\em Sparse approximate inverse preconditioners on high performance GPU platforms},
Comput. Math. Appl. {\bf 71} (2016), no.~3, 693--711.
%
\bibitem{BREZINA_VANEK}
M.~Brezina, P.~Van\v{e}k,
{\em A Black-Box Iterative Solver Based on a Two-Level Schwarz Method},
docs/src/overview.tex
+1 -1
View File
@@ -25,7 +25,7 @@ coarse-level matrices and operators, without explicitly using any information on
geometry of the original problem, e.g., the discretization of a PDE. To this end,
two different coarsening strategies, based on aggregation, are available:
\begin{itemize}
\item a decoupled version of the well known smoothed aggregation procedure proposed in~\cite{BREZINA_VANEK,VANEK_MANDEL_BREZINA}, and already included in the previous versions of the package~\cite{BDDF2007,MLD2P4_TOMS};
\item a decoupled version of the well known smoothed aggregation procedure proposed in~\cite{BREZINA_VANEK,VANEK_MANDEL_BREZINA}, and already included in the previous versions of the package~\cite{MLD2P4_TOMS,BDDF2007};
\item the first parallel implementation of a coupled version of Coarsening based on Compatible Weighted Matching introduced in~\cite{DV2013,DFV2018} and described in details in~\cite{DDF2020};
\end{itemize}
docs/src/userguide.tex
+1
View File
@@ -16,6 +16,7 @@
\usepackage{html}
\usepackage{ifthen}
\usepackage{graphicx}
\usepackage{subfig}
\newtheorem{theorem}{Theorem}
\newtheorem{corollary}{Corollary}
\usepackage{rotating}
docs/src/userinterface.tex
+91 -69
View File
@@ -223,10 +223,10 @@ See also Sec.~\ref{sec:adding}.
\fortinline|what| & \textsc{data type} & \fortinline|val| & \textsc{default} &
\textsc{comments} \\ \hline
\fortinline|'ML_CYCLE'| & \fortinline|character(len=*)|
& \texttt{'VCYCLE'} \par \texttt{'WCYCLE'} \par \texttt{'KCYCLE'} \par \texttt{'ADD'}
& \texttt{'VCYCLE'}
& \fortinline|'VCYCLE'| \par \fortinline|'WCYCLE'| \par \fortinline|'KCYCLE'| \par \fortinline|'ADD'|
& \fortinline|'VCYCLE'|
&Multilevel cycle: V-cycle, W-cycle, K-cycle, and additive composition. \\ \hline
\fortinline|'OUTER_SWEEPS'| & \texttt{integer} &
\fortinline|'OUTER_SWEEPS'| & \fortinline|integer| &
Any integer \par number $\ge 1$ & 1 &
Number of multilevel cycles. \\ \hline
@@ -279,54 +279,63 @@ be applied.
& 20
& Maximum number of levels. The aggregation stops
if the number of levels reaches this value (see Note). \\ \hline
\fortinline|'PAR_AGGR_ALG'| & \fortinline|character(len=*)| \hspace*{-3mm}
& \texttt{'DEC'}, \texttt{'SYMDEC'}, \texttt{'COUPLED'}
& \texttt{'DEC'}
& Parallel aggregation algorithm. \par the
\fortinline|SYMDEC| option applies decoupled
aggregation to the sparsity pattern
of $A+A^T$.\\ \hline
\fortinline|'AGGR_TYPE'| & \fortinline|character(len=*)| \hspace*{-3mm}
& \textbf{\texttt{'SOC1'}} &
\textbf{\texttt{'SOC1'}},
\textbf{\texttt{'SOC2'}},
\textbf{\texttt{'MATCHBOXP'}}
& Type of aggregation algorithm: currently,
for the decoupled aggregation we implement two measures of strength of
connection, the one by Van\v{e}k, Mandel
and Brezina~\cite{VANEK_MANDEL_BREZINA},
and the one by Gratton et al~\cite{GrHeJi:16}. The coupled
aggregation is based on a parallel version of the half-approximate
matching implemented in the MatchBox-P software package
{\bf AGGIUNGERE LINK AL PACKAGE?}\\ \hline
\fortinline|'AGGR_SIZE'| & \fortinline|integer| \hspace*{-3mm}
& Any integer \par number power of $2$ and $> 2$
& 4
& Maximum size of aggregates when the coupled aggregation based on
matching is applied. For aggressive coarsening with size of
aggregate larger than $8$ we recommend the use of smoothed prolongators.
{\bf MODIFICARE CODICE}\\ \hline
\fortinline|'AGGR_PROL'| & \fortinline|character(len=*)| \hspace*{-3mm}
& \texttt{'SMOOTHED'}, \texttt{'UNSMOOTHED'} & \texttt{'SMOOTHED'}
& Prolongator used by the aggregation algorithm: smoothed or unsmoothed
(i.e., tentative prolongator). \\
\hline
\multicolumn{5}{|l|}{{\bfseries Note.} The aggregation algorithm stops when
at least one of the following criteria is met:
the coarse size threshold, the coarse size threshold per process, the} \\
\multicolumn{5}{|l|}{minimum coarsening ratio, or the maximum number
of levels is reached. Therefore, the actual number of levels may be} \\
\multicolumn{5}{|l|}{smaller than the specified maximum number
of levels. } \\
\hline
& \texttt{'DEC'}, \texttt{'SYMDEC'}, \texttt{'COUPLED'}
& \texttt{'DEC'}
& Parallel aggregation algorithm. \par the
\fortinline|SYMDEC| option applies decoupled
aggregation to the sparsity pattern
of $A+A^T$.\\ \hline
\ifpdf
\end{tabular}
\end{center}
\esideways
\bsideways
\ContinuedFloat
\begin{center}
\begin{tabular}{|p{5.7cm}|l|p{2.3cm}|p{2.5cm}|p{5.9cm}|}
\hline
\fi
\fortinline|what| & \textsc{data type} & \fortinline|val| & \textsc{default} &
\textsc{comments} \\ \hline
\fortinline|'AGGR_TYPE'| & \fortinline|character(len=*)| \hspace*{-3mm}
& \fortinline|'SOC1'| &
\fortinline|'SOC1'|,
\fortinline|'SOC2'|,
\fortinline|'MATCHBOXP'|
& Type of aggregation algorithm: currently,
for the decoupled aggregation we implement two measures of strength of
connection, the one by Van\v{e}k, Mandel
and Brezina~\cite{VANEK_MANDEL_BREZINA},
and the one by Gratton et al~\cite{GrHeJi:16}. The coupled
aggregation is based on a parallel version of the half-approximate
matching implemented in the MatchBox-P software package~\cite{MatchBoxP}.\\ \hline
\fortinline|'AGGR_SIZE'| & \fortinline|integer| \hspace*{-3mm}
& Any integer \par number power of $2$ and $> 2$
& 4
& Maximum size of aggregates when the coupled aggregation based on
matching is applied. For aggressive coarsening with size of
aggregate larger than $8$ we recommend the use of smoothed prolongators.
{\bf MODIFICARE CODICE}\\ \hline
\fortinline|'AGGR_PROL'| & \fortinline|character(len=*)| \hspace*{-3mm}
& \fortinline|'SMOOTHED'|, \fortinline|'UNSMOOTHED'| & \fortinline|'SMOOTHED'|
& Prolongator used by the aggregation algorithm: smoothed or unsmoothed
(i.e., tentative prolongator). \\
\hline
\multicolumn{5}{|l|}{{\bfseries Note.} The aggregation algorithm stops when
at least one of the following criteria is met:
the coarse size threshold, } \\
\multicolumn{5}{|l|}{the coarse size threshold per process, the minimum coarsening ratio, or the maximum number
of levels is reached.} \\
\multicolumn{5}{|l|}{Therefore, the actual number of levels may be smaller than the specified maximum number
of levels. } \\
\hline
\end{tabular}
\caption{Parameters defining the aggregation algorithm.
\label{tab:p_aggregation}}
\end{center}
\esideways
\bsideways
@@ -378,14 +387,14 @@ the parameter \texttt{ilev}.} \\
\fortinline|what| & \textsc{data type} & \fortinline|val| & \textsc{default} &
\textsc{comments} \\ \hline
\fortinline|'COARSE_MAT'| & \fortinline|character(len=*)|
& \texttt{'DIST'} \par \texttt{'REPL'}
& \texttt{'REPL'}
& \fortinline|'DIST'| \par \fortinline|'REPL'|
& \fortinline|'REPL'|
& Coarsest matrix layout: distributed among the processes or
replicated on each of them. \\ \hline
\fortinline|'COARSE_SOLVE'| & \fortinline|character(len=*)|
& \texttt{'MUMPS'} \par \texttt{'UMF'} \par
\texttt{'SLU'} \par \texttt{'SLUDIST'} \par
\texttt{'JACOBI'} \par \texttt{'GS'} \par \texttt{'BJAC'} \par \texttt{'PCG'}
& \fortinline|'MUMPS'| \par \fortinline|'UMF'| \par
\fortinline|'SLU'| \par \fortinline|'SLUDIST'| \par
\fortinline|'JACOBI'| \par \fortinline|'GS'| \par \fortinline|'BJAC'| \par \fortinline|'RKR'|
& See~Note.
& Solver used at the coarsest level: sequential
LU from MUMPS, UMFPACK, or SuperLU
@@ -394,7 +403,7 @@ the parameter \texttt{ilev}.} \\
(plus triangular solve);
point-Jacobi, hybrid Gauss-Seidel or block-Jacobi and related $\ell_1$-versions;
{\bf preconditioned Conjugate Gradient coupled with the block-Jacobi preconditioner
with ILU(0) on the blocks}. \par
with ILU(0) on the blocks}.
Note that \texttt{UMF} and \texttt{SLU} require the coarsest
matrix to be replicated, \texttt{SLUDIST}, \texttt{JACOBI},
\texttt{GS}, \texttt{BJAC} and \texttt{PCG} require it to be
@@ -404,15 +413,28 @@ the parameter \texttt{ilev}.} \\
value which allows the use of the solver (see Remark 3, p.~24).
Note also that UMFPACK and SuperLU\_Dist
are available only in double precision. \\ \hline
\ifpdf
\end{tabular}
\end{center}
\esideways
\bsideways
\ContinuedFloat
\begin{center}
\begin{tabular}{|p{3.9cm}|l|p{1.7cm}|p{1.7cm}|p{8.6cm}|}
\hline
\fi
\fortinline|'COARSE_SUBSOLVE'| & \fortinline|character(len=*)|
& \texttt{'ILU'} \par \texttt{'ILUT'} \par \texttt{'MILU'} \par
\texttt{'MUMPS'} \par \texttt{'SLU'} \par \texttt{'UMF'}
& \fortinline|'ILU'| \par \fortinline|'ILUT'| \par \fortinline|'MILU'| \par
\fortinline|'MUMPS'| \par \fortinline|'SLU'| \par \fortinline|'UMF'| \par
\fortinline|'INVT'| \par \fortinline|'INVK'| \par \fortinline|'AINV'|
& See~Note.
& Solver for the diagonal blocks of the coarse matrix,
in case the block Jacobi solver
is chosen as coarsest-level solver: ILU($p$), ILU($p,t$),
MILU($p$), LU from MUMPS, SuperLU or UMFPACK
(plus triangular solve). {\bf Aggiungere Sparse Approssimate per GPU?}
(plus triangular solve). Suitable for GPUs (no triangular solve)
approximate inverse solvers INVK($p,q$), INVT($p_1,p2,t_1,t_2$) and
AINV($t$), see~\cite{BERTACCINIFILIPPONE}.
Note that UMFPACK and SuperLU\_Dist
are available only in double precision. \\
\hline
@@ -425,16 +447,16 @@ the parameter \texttt{ilev}.} \\
then \texttt{MUMPS} if installed, then \texttt{SLU} if
installed, \texttt{ILU} otherwise.}\\
\hline
\end{tabular}
\end{center}
\caption{Parameters defining the coarse-space correction at the coarsest
level.\label{tab:p_coarse}}
\esideways
\bsideways
\begin{center}
\begin{tabular}{|p{3.9cm}|l|p{2cm}|p{1.5cm}|p{7.5cm}|}
\hline
%\end{tabular}
%\end{center}
%\caption{Parameters defining the coarse-space correction at the coarsest
%level.\label{tab:p_coarse}}
%\esideways
%
%\bsideways
%\begin{center}
%\begin{tabular}{|p{3.9cm}|l|p{2cm}|p{1.5cm}|p{7.5cm}|}
%\hline
\fortinline|what| & \textsc{data type} & \fortinline|val| & \textsc{default} &
\textsc{comments} \\ \hline
\fortinline|'COARSE_SWEEPS'| & \fortinline|integer|
@@ -476,10 +498,10 @@ level (continued).\label{tab:p_coarse_1}}
Additive Schwarz. \par
It is ignored by one-level preconditioners. \\ \hline
\fortinline|'SUB_SOLVE'| & \fortinline|character(len=*)|
& \texttt{'JACOBI'} \par
\texttt{'GS'} \par \texttt{'BGS'} \par \texttt{'ILU'} \par
\texttt{'ILUT'} \par \texttt{'MILU'} \par
\par \texttt{'MUMPS'} \par \texttt{'SLU'} \par \texttt{'UMF'}
& \fortinline|'JACOBI'| \par
\fortinline|'GS'| \par \texttt{'BGS'} \par \fortinline|'ILU'| \par
\fortinline|'ILUT'| \par \fortinline|'MILU'| \par
\par \fortinline|'MUMPS'| \par \fortinline|'SLU'| \par \fortinline|'UMF'|
& \texttt{GS} and \texttt{BGS} for pre- and post-smoothers
of multilevel preconditioners, respectively \par
\texttt{ILU} for block-Jacobi and Additive Schwarz