M. Baboulin, S. Donfack, J. Dongarra, L. Grigori, A. Rémy, S. Tomov A class of communication-avoiding algorithms for solving general dense linear systems on CPU/GPU parallel machines.
Inria Research Report 7854
(02/2012). Proceedings of International Conference on Computational Science (ICCS 2012).
M. Baboulin, D. Becker, J. Dongarra A parallel tiled solver for dense symmetric indefinite systems on multicore architectures.
Inria Research Report 7762
(12/2011),
also appeared as LAPACK Working Note 261. Proceedings of IEEE International Parallel & Distributed Processing Symposium (IPDPS 2012).
D. Becker, M. Baboulin, J. Dongarra Reducing the amount of pivoting in symmetric indefinite systems.
Inria Research Report 7621
(05/2011),
University of Tennessee Technical Report ICL-UT-11-06. Proceedings of the 9th International Conference on Parallel Processing and Applied Mathematics (PPAM 2011).
Lecture Notes in Computer Science, Springer-Verlag, Vol. 7203, pp. 133-142 (2012).
M. Baboulin, J. Dongarra, J. Herrmann, S. Tomov Accelerating linear system solutions using randomization techniques.
Inria Research Report 7616
(05/2011),
also appeared as LAPACK Working Note 246.
Revised version to appear in ACM Transactions on Mathematical Software (TOMS).
M. Baboulin, S. Gratton A contribution to the conditioning of the total least squares problem.
Inria Research Report 7488
(12/2010),
also appeared as LAPACK Working Note 236. SIAM Journal on Matrix Analysis and Applications,Vol. 32, No 3, pp. 685-699 (2011),
PDF File.
S. Tomov, J. Dongarra, M. Baboulin Towards dense linear algebra for hybrid GPU accelerated manycore systems. Parallel Computing , Vol. 36, No 5&6, pp. 232-240 (2010),
PDF File.
M. Baboulin, A. Buttari, J. Dongarra, J. Kurzak, J. Langou, J. Langou,
P. Luszczek, S. Tomov Accelerating scientific computations with mixed precision algorithms. Computer Physics Communications , Vol. 180, No 12, pp. 2526-2533 (2009),
PDF File.
M. Baboulin, J. Dongarra, S. Gratton, J. Langou Computing the conditioning of the components of a linear least squares solution. Numerical Linear Algebra with Applications , Vol. 16, No7, pp. 517-533 (2009), PDF File.
M. Baboulin, S. Gratton Using dual techniques to derive componentwise and mixed condition numbers
for a linear function of a linear least squares solution. BIT Numerical Mathematics , Vol. 49, No1, pp. 3-19 (2009),
PDF File.
M. Baboulin, J. Dongarra, S. Tomov Some issues in dense linear algebra for multicore and special
purpose architectures.
In Proceedings of the 9th International Workshop on State-of-the-Art
in Scientific and Parallel Computing (PARA'08) .
M. Baboulin, L. Giraud, S. Gratton, J. Langou Parallel tools for solving incremental dense least squares problems. Application to space geodesy. Journal of Algorithms and Computational Technology, Vol. 3, No 1, pp. 117-133 (2009),
PDF File.
M. Baboulin, L. Giraud, S. Gratton, J. Langou A distributed packed storage for large dense parallel in-core calculations.
Concurrency and Computation: Practice and Experience, Vol. 19, No 4, pp. 483-502 (2007),
PDF File.
M. Arioli, M. Baboulin, S. Gratton A partial condition number for linear least squares problems.
SIAM Journal on Matrix Analysis and Applications,Vol. 29, No 2, pp. 413-433 (2007),
PDF File.
M. Baboulin, L. Giraud, S. Gratton A parallel distributed solver for large dense symmetric systems:
applications to geodesy and electromagnetism problems.
International Journal of
High Performance Computing Applications, Vol. 19, No 4, pp. 353-363 (2005),
PDF File.
Thesis
Title: Solving large dense linear least squares problems on parallel
distributed computers. Application to the Earth's gravity field computation. Ph.D. in Computer Science from
Institut National Polytechnique de Toulouse, defended March 21 2006.
Committee: G. Balmino (CNES/CNRS), J. Dongarra (University of Tennessee, referee), I.S. Duff (RAL/CERFACS), L. Giraud (ENSEEIHT), S. Gratton (CERFACS), N.J. Higham (University of Manchester, referee), J. Noailles (ENSEEIHT).
Ph.D. dissertation
This thesis was awarded the Léopold Escande Prize by
Institut National Polytechnique de Toulouse.
Talks in Conferences (selection)
Invited speaker: A parallel tiled solver for dense symmetric indefinite systems on multicore architectures.
Workshop on ''Recent developments in the solution of indefinite systems'', Eindhoven, Netherlands, April 17, 2012
Invited speaker: Accelerating linear system solutions on new parallel architectures.
20th ACM High Performance Computing Symposium (HPC 2012), Orlando (FL), USA, March 26-29, 2012
A class of fast solvers for dense linear systems on hybrid GPU-multicore machines.
SIAM Conference on Parallel Processing for Scientific Computing, Savannah (GA), USA, Feb. 15-17, 2012
A parallel tiled solver for dense symmetric indefinite systems on multicore architectures.
The sixth workshop of the INRIA-Illinois Joint Laboratory for Petascale Computing, Urbana-Champaign (IL), USA, November 21-23, 2011.
Getting fast linear system solutions on new parallel architectures.
The fifth workshop of the INRIA-Illinois Joint Laboratory for Petascale Computing, Grenoble, France, June 27-29, 2011.
Accelerating linear algebra calculations using statistical techniques.
Minisymposium: Innovative algorithms for dense linear algebra (organizer).
SIAM Conference on Computational Science and Engineering, Reno (NV), USA, Feb. 28 - March 4, 2011.
Accelerating linear algebra computations with hybrid GPU-multicore systems.
The fourth workshop of the INRIA-Illinois Joint Laboratory for Petascale Computing, Urbana-Champaign (IL), USA, November 22-24, 2010.
Computational issues in least squares conditioning.
Parallel Matrix Algorithms and Applications (PMAA'10), Basel, Switzerland, June 29 - July 2, 2010.
Invited speaker: Summer school on e-science with many-core CPU/GPU processors.
Lecture on "Dense linear algebra for hybrid GPU-Multicore systems", Braga, Portugal, June 14-18, 2010.
Dense linear algebra for hybrid GPU accelerated manycore systems.
Numerical Methods in Engineering (METNUM 09), Barcelona, Spain, June 29 - July 2, 2009.
Deriving componentwise condition numbers using dual techniques.
Application to linear least squares.
SIAM Annual Meeting, San Diego, USA, July 7-11, 2008.
Computing the conditioning of the components of a linear least squares solution.
VECPAR'08, Toulouse, France, June 24-27, 2008.
Some issues in dense linear algebra for multicore.
Minisymposium: Recent developments in dense linear algebra
Organizers: Marc Baboulin and Jack Dongarra
SIAM Conference on Parallel Processing for Scientific Computing, Atlanta, USA, March 12-14, 2008.
Computing the conditioning of dense linear least squares with (Sca)LAPACK.
SIAM Conference on Parallel Processing for Scientific Computing, Atlanta, USA, March 12-14, 2008.
Very large least-squares for parameter estimation:
Algorithm and application.
SciDAC workshop on libraries and algorithms, Snowbird (Utah), USA,
July 30- August 2, 2007.
HPC tools for solving accurately the large dense linear least squares problems arising in gravity field calculations.
PARA'06, Workshop on State-of-the-Art in Scientific and Parallel Computing, Umeå, Sweden, June 18-21, 2006.
A distributed packed storage for large parallel calculations.
SIAM Conference on Parallel Processing for Scientific Computing, San Francisco, USA, Feb. 22-24, 2006.
Parallel distributed solvers for accurate and efficient gravity field computation.
SIAM Conference on Mathematical and Computational Issues in the Geosciences, Avignon, France, June 7-10, 2005.
Solveur parallèle pour moindres carrés.
Séminaire Mécanique Orbitale, Centre National d'Etudes Spatiales, Toulouse, France, Sept. 30, 2004.
Partial condition number for linear least squares problems.
International Congress on Computational and Applied Mathematics, Katholieke Universiteit Leuven, Belgium, July 26-30, 2004.
Parallel distributed Cholesky factorization for in-core large dense problems.
SIAM Conference on Parallel Processing for Scientific Computing, San Francisco, USA, Feb. 25-27, 2004.
Posters
Ehancing the performance of dense linear algebra on GPUs.
Marc Baboulin, James Demmel, Jack Dongarra, Stanimire Tomov, Vasily Volkov.
Supercomputing (SC'08), Austin, USA, Nov. 15-21, 2008,
Poster.
Gravity field parameter estimation using QR factorization.
Marc Baboulin, G. Balmino, S. Bruinsma, S. Gratton, J-C Marty.
European Geosciences Union General Assembly (EGU 2008),
Vienna, Austria, Apr. 13-18, 2008,
Poster.