%\section{Bibliography\label{sec:bib}}
\begin{thebibliography}{99}
\ifpdf
\addcontentsline{toc}{section}{\refname}
\fi
\markboth{\textsc{MLD2P4 User's and Reference Guide}}
         {\textsc{References}}

%\let\refname\relax
%
\bibitem{MUMPS}
P.~R.~Amestoy, C.~Ashcraft, O.~Boiteau, A.~Buttari, J.~L'Excellent, C.~Weisbecker,
{\em Improving multifrontal methods by means of block low-rank representations},
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},
Computing, 63, 1999, 233--263.
%
\bibitem{Briggs2000}
W.~L.~Briggs, V.~E.~Henson, S.~F.~McCormick,
{\em A Multigrid Tutorial, Second Edition},
SIAM, 2000.
%
\bibitem{para_04}
A.~Buttari, P.~D'Ambra, D.~di Serafino, S.~Filippone,
{\em Extending PSBLAS to Build Parallel Schwarz Preconditioners},
in J.~Dongarra, K.~Madsen, J.~Wasniewski, editors,
Proceedings of PARA~04 Workshop on State of the Art
in Scientific Computing, Lecture Notes in Computer Science,
Springer, 2005, 593--602.
%
\bibitem{aaecc_07}
A.~Buttari, P.~D'Ambra, D.~di~Serafino, S.~Filippone,
{\em 2LEV-D2P4: a package of high-performance preconditioners
for scientific and engineering applications},
Applicable Algebra in Engineering, Communications and Computing,
18 (3) 2007, 223--239.
%
%Published online: 13 February 2007, {\tt http://dx.doi.org/10.1007/s00200-007-0035-z}
%
\bibitem{CAI_SARKIS}
X.~C.~Cai, M.~Sarkis,
{\em A Restricted Additive Schwarz Preconditioner for General Sparse Linear Systems},
SIAM Journal on Scientific Computing, 21 (2), 1999, 792--797.
%
\bibitem{MatchBoxP}
U..~V.~Catalyurek, F.~Dobrian, A.~Gebremedhin, M.~Halappanavar, and A.~Pothen,
{\em Distributed-memory parallel algorithms for matching and coloring}, in PCO’11 New Trends
in Parallel Computing and Optimization, IEEE International Symposium on Parallel and
Distributed Processing Workshops, IEEE CS, 2011.
%
%\bibitem{dd1_94}
%T.~Chan and T.~Mathew,
%{\em Domain Decomposition Algorithms},
%in A.~Iserles, editor, Acta Numerica 1994, 61--143.
%Cambridge University Press.
%
\bibitem{apnum_07}
P.~D'Ambra, S.~Filippone,  D.~di~Serafino,
{\em On the Development of PSBLAS-based Parallel Two-level Schwarz Preconditioners},
Applied Numerical Mathematics, Elsevier Science,
57 (11-12), 2007, 1181-1196.
%published online 3 February 2007, {\tt
%  http://dx.doi.org/10.1016/j.apnum.2007.01.006}
%
\bibitem{MLD2P4_TOMS}
P.~D'Ambra, D.~di~Serafino, S.~Filippone,
\emph{MLD2P4: a Package of Parallel Multilevel
Algebraic Domain Decomposition Preconditioners
in Fortran 95},  ACM Trans. Math. Softw., 37(3), 2010, art. 30.
%
\bibitem{DV2013}
P.~D'Ambra and P.\,S.~Vassilevski,
{\em Adaptive AMG with coarsening based on compatible weighted matching},
Computing and Visualization in Science, 16, (2013) 59--76.
%
\bibitem{DFV2018}
P.~D'Ambra, S.~Filippone and P.\,S.~Vassilevski,
{\em BootCMatch: a software package for bootstrap AMG based on graph weighted matching},
ACM Transactions on Mathematical Software, 44, (2018) 39:1--39:25.
%
\bibitem{DDF2020}
P.~D'Ambra, F~Durastante, S.~Filippone, 
\emph{AMG preconditioners for Linear Solvers towards Extreme Scale}, 2020, \href{https://arxiv.org/abs/2006.16147v3arXiv:2006.16147v2}{arXiv:2006.16147v3}.
%
\bibitem{UMFPACK}
T.~A.~Davis,
{\em Algorithm 832: UMFPACK - an Unsymmetric-pattern Multifrontal
Method with a Column Pre-ordering Strategy},
ACM Transactions on Mathematical Software, 30, 2004, 196--199.
(See also \texttt{http://www.cise.ufl.edu/{\textasciitilde}davis/})
%
\bibitem{SUPERLU}
J.~W.~Demmel, S.~C.~Eisenstat, J.~R.~Gilbert, X.~S.~Li, J.~W.~H.~Liu,
{\em A supernodal approach to sparse partial pivoting},
SIAM Journal on Matrix Analysis and Applications, 20 (3), 1999, 720--755.
%
\bibitem{blas3}
J.~J.~Dongarra, J.~Du Croz, I.~S.~Duff, S.~Hammarling,
\emph{A set of Level 3 Basic Linear Algebra Subprograms},
ACM Transactions on Mathematical Software, 16 (1) 1990, 1--17.
%
\bibitem{blas2}
J.~J.~Dongarra, J.~Du Croz, S.~Hammarling, R.~J.~Hanson,
\emph{An extended set of FORTRAN Basic Linear Algebra Subprograms},
ACM Transactions on Mathematical Software, 14 (1) 1988, 1--17.
%
%\bibitem{BLACS}
%J.~J.~Dongarra, R.~C.~Whaley,
%{\em A User's Guide to the BLACS v.~1.1},
%Lapack Working Note 94, Tech.\ Rep.\ UT-CS-95-281, University of
%Tennessee, March 1995 (updated May 1997).
%
%\bibitem{EFSTATHIOU}
%E.~Efstathiou, J.~G.~Gander,
%{\em Why Restricted Additive Schwarz Converges Faster than Additive Schwarz},
%BIT Numerical Mathematics, 43 (5), 2003, 945--959.
%
\bibitem{PSBLASGUIDE}
S.~Filippone, A.~Buttari,
{\em PSBLAS 3.5.0 User's Guide. A Reference Guide for the Parallel Sparse BLAS Library}, 2012,
available from \texttt{https://github.com/sfilippone/psblas3/tree/master/docs}.
%
\bibitem{PSBLAS3}
S.~Filippone, A.~Buttari,
{\em Object-Oriented Techniques for Sparse Matrix Computations in Fortran 2003}.
ACM Transactions on on Mathematical Software, 38 (4), 2012, art.~23.
%
\bibitem{psblas_00}
S.~Filippone, M.~Colajanni,
{\em PSBLAS: A Library for Parallel Linear Algebra
Computation on Sparse Matrices},
ACM Transactions on Mathematical Software, 26 (4), 2000, 527--550.
%
\bibitem{GrHeJi:16}
S. Gratton, P. Henon, P. Jiranek and X. Vasseur,
  {\em Reducing complexity of algebraic multigrid by aggregation},
Numerical Lin. Algebra with Applications, 2016, 23:501-518
%
\bibitem{MPI2}
W.~Gropp, S.~Huss-Lederman, A.~Lumsdaine, E.~Lusk, B.~Nitzberg, W.~Saphir, M.~Snir,
{\em MPI: The Complete Reference. Volume 2 - The MPI-2 Extensions},
MIT Press, 1998.
%
\bibitem{blas1}
C.~L.~Lawson, R.~J.~Hanson, D.~Kincaid, F.~T.~Krogh,
\emph{Basic Linear Algebra Subprograms for FORTRAN usage},
ACM Transactions on Mathematical Software, 5 (3), 1979, 308--323.
%
\bibitem{SUPERLUDIST}
X.~S.~Li, J.~W.~Demmel,
{\em SuperLU\_DIST: A Scalable Distributed-memory
Sparse Direct Solver for Unsymmetric Linear Systems},
ACM Transactions on Mathematical Software, 29 (2), 2003, 110--140.
%
\bibitem{Notay2008}
Y.~Notay, P.~S.~Vassilevski,
{\em Recursive Krylov-based multigrid cycles},
Numerical Linear Algebra with Applications, 15 (5), 2008, 473--487.
%
\bibitem{Saad_book}
Y.~Saad,
{\em Iterative methods for sparse linear systems}, 2nd edition, SIAM, 2003.
%
\bibitem{dd2_96}
B.~Smith, P.~Bjorstad, W.~Gropp,
{\em Domain Decomposition: Parallel Multilevel Methods for Elliptic
Partial Differential Equations},
Cambridge University Press, 1996.
%
\bibitem{MPI1}
M.~Snir, S.~Otto, S.~Huss-Lederman, D.~Walker, J.~Dongarra,
{\em MPI: The Complete Reference. Volume 1 - The MPI Core}, second edition,
MIT Press, 1998.
%
\bibitem{Stuben_01}
K.~St\"{u}ben,
{\em An Introduction to Algebraic Multigrid},
in A.~Sch\"{u}ller, U.~Trottenberg, C.~Oosterlee, Multigrid,
Academic Press, 2001.
%
\bibitem{TUMINARO_TONG}
R.~S.~Tuminaro, C.~Tong,
{\em Parallel Smoothed Aggregation Multigrid: Aggregation Strategies on Massively Parallel Machines}, in J. Donnelley, editor, Proceedings of SuperComputing 2000, Dallas, 2000.
%
\bibitem{VANEK_MANDEL_BREZINA}
P.~Van\v{e}k, J.~Mandel, M.~Brezina,
{\em Algebraic Multigrid by Smoothed Aggregation for Second and Fourth Order Elliptic Problems},
Computing, 56 (3) 1996, 179--196.
%
\end{thebibliography}