Alfredo Buttari

Table of Contents

CNRS researcher @ IRIT
2 rue Camichel, 31071 Toulouse, France (map)
telephone: +33 5 34 32 22 08
email: abuttari at n7 dot fr

fb.png gp.png pi.png in.png

Bio

I am currently a CNRS (Centre National de la Recherche Scientifique) researcher at the IRIT (Institut de Recherche en Informatique de Toulouse) laboratory in Toulouse (France) where I am a member of the APO (Algorithmes Parallèles et Optimisation). My interest are in High Performance Computing, parallel computing, computational linear algebra (numerical software in general). Here is my CV and a short bio:

Research

Current projects

  • qr_mumps. I am the main developer of the qr_mumps software. qr_mumps is a software package for the solution of sparse, linear systems on multicore computers. It implements a direct solution method based on the QR factorization of the input matrix. Therefore, it is suited to solving sparse least-squares problems and to computing the minimum-norm solution of sparse, underdetermined problems. qr_mumps is a parallel, multithreaded software based on the OpenMP standard.Parallelism is achieved by dividing the workload into fine grained tasks that are arranged in a Direct Acyclic Graph (DAG). The execution of these tasks is guiged by an asynchronous and dynamic data-flow programming model which provides high efficiency and scalability. Here is a poster I presented at the 2011 Householder meeting. In this context I am currently working on the integration of runtime systems (such as StarPU or Parsec) and on the usage of GPUs.
  • MUMPS. I am a member of the MUltifrontal Massively Parallel sparse direct Solver (MUMPS) project. The MUMPS package implements a multifrontal (direct) solver for sparse linear systems. It is an SPMD parallel code based on MPI and provides a wide range of features. Within this project I am principally involved in investigating the use of Low-Rank approximation techniques to reduce the execution time as well as the memory footprint.
  • PSBLAS. I collaborate to the Parallel Sparse BLAS (PSBLAS) project. The PSBLAS software implements basic kernels for sparse computations as well as a bunch of iterative methods (CG, GMRES, BiCG,…) and preconditioners (Block-Jacobi, Additive-Schwarz, Multilevel,…) for the solution of sparse linear systems. It is an SPMD parallel code based on MPI and it is written in Fortran2003.

Past projects

Teaching

Algèbre Linéaire Creuse

Systèmes Concurrents

Publications

Journals

[1] Patrick Amestoy, Cleve Ashcraft, Olivier Boiteau, Alfredo Buttari, Jean-Yves L'Excellent, and Clément Weisbecker. Improving multifrontal methods by means of block low-rank representations. SIAM Journal on Scientific Computing, 37(3):A1451--A1474, 2015. [ DOI | arXiv | http ]
[2] Laurent Bouchet, Patrick Amestoy, Alfredo Buttari, François-Henry Rouet, and Maxime Chauvin. INTEGRAL/SPI data segmentation to retrieve sources intensity variations. Astronomy & Astrophysics, A52:(on line), July 2013. [ DOI ]
[3] Laurent Bouchet, Patrick Amestoy, Alfredo Buttari, Francois-Henry Rouet, and Maxime Chauvin. Simultaneous analysis of large INTEGRAL/SPI datasets: optimizing the computation of the solution and its variance using sparse matrix algorithms. Astronomy and Computing, 1:59--69, 2013. [ DOI ]
[4] Alfredo Buttari. Fine-grained multithreading for the multifrontal QR factorization of sparse matrices. SIAM Journal on Scientific Computing, 35(4):C323--C345, 2013. [ arXiv | http ]
[5] Salvatore Filippone and Alfredo Buttari. Object-oriented techniques for sparse matrix computations in Fortran 2003. ACM Transactions on Mathematical Software, 38(4):23:1--23:20, August 2012. [ DOI ]
[6] Mark Baboulin, Alfredo Buttari, Jack Dongarra, Jakub Kurzak, Julien Langou, Julie Langou, Piotr Luszczek, and Stanimire Tomov. Accelerating scientific computations with mixed precision algorithms. Computer Physics Communications, 180(12):2526--2533, 2009. [ DOI ]
[7] Alfredo Buttari, Julien Langou, Jakub Kurzak, and Jack Dongarra. A class of parallel tiled linear algebra algorithms for multicore architectures. Parallel Comput., 35:38--53, January 2009. [ DOI | http ]
[8] Alfredo Buttari, Jack Dongarra, Jakub Kurzak, Piotr Luszczek, and Stanimire Tomov. Using mixed precision for sparse matrix computations to enhance the performance while achieving 64-bit accuracy. ACM Trans. Math. Softw., 34(4):1--22, 2008. [ DOI ]
[9] Alfredo Buttari, Julien Langou, Jakub Kurzak, and Jack Dongarra. Parallel tiled QR factorization for multicore architectures. Concurr. Comput. : Pract. Exper., 20(13):1573--1590, 2008. [ DOI ]
[10] Jakub Kurzak, Alfredo Buttari, and Jack Dongarra. Solving systems of linear equations on the cell processor using cholesky factorization. IEEE Trans. Parallel Distrib. Syst., 19(9):1175--1186, 2008. [ DOI ]
[11] Jakub Kurzak, Alfredo Buttari, Piotr Luszczek, and Jack Dongarra. The playstation 3 for high-performance scientific computing. Computing in Science and Eng., 10(3):84--87, 2008. [ DOI ]
[12] Alfredo Buttari, Pasqua D'Ambra, Daniela Di Serafino, and Salvatore Filippone. 2LEV-D2P4: a package of high-performance preconditioners for scientific and engineering applications. Appl. Algebra Eng., Commun. Comput., 18(3):223--239, 2007. [ DOI ]
[13] Alfredo Buttari, Jack Dongarra, Julien Langou, Julie Langou, Piotr Luszczek, and Jakub Kurzak. Mixed precision iterative refinement techniques for the solution of dense linear systems. Int. J. High Perform. Comput. Appl., 21(4):457--466, 2007. [ DOI ]
[14] Alfredo Buttari, V. Eijkhout, Julien Langou, and Salvatore Filippone. Performance optimization and modeling of blocked sparse kernels. Int. J. High Perform. Comput. Appl., 21(4):467--484, 2007. [ DOI ]

This file was generated by bibtex2html 1.98.

Conferences

[1] Emmanuel Agullo, Patrick R Amestoy, Alfredo Buttari, Abdou Guermouche, Guillaume Joslin, Jean-Yves L'Excellent, Xiaoye S Li, Artem Napov, François-Henry Rouet, Mohamed Sid-Lakhdar, et al. Recent advances in sparse direct solvers. In Conference on Structural Mechanicsin Reactor Technology, 2013.
[2] Emmanuel Agullo, Alfredo Buttari, Abdou Guermouche, and Florent Lopez. Multifrontal QR factorization for multicore architectures over runtime systems. In Euro-Par 2013 Parallel Processing, pages 521--532. Springer Berlin Heidelberg, 2013. [ http ]
[3] Patrick Amestoy, Alfredo Buttari, Guillaume Joslin, Jean-Yves L'Excellent, Mohamed Sid-Lakhdar, Clement Weisbecker, Michele Forzan, Cristian Pozza, Remy Perrin, and Valene Pellissier. Shared memory parallelism and low-rank approximation techniques applied to direct solvers in FEM simulation (regular paper). In IEEE International Conference on the Computation of Electromagnetic Fields (COMPUMAG), Budapest, Hungary, 30/06/2013-04/07/2013. IEEE, juin 2013. [ DOI ]
[4] Laurent Bouchet, Patrick Amestoy, Alfredo Buttari, Francois-Henry Rouet, and Maxime Chauvin. INTEGRAL/SPI data segmentation to retrieve sources intensity variations (regular paper). In A. Goldwurm, F. Lebrun, and C. Winkler, editors, An INTEGRAL view of the high-energy sky (the first 10 years), Paris, France, 15/10/2012-19/10/2012, 2013.
[5] Clement Weisbecker, Patrick Amestoy, Olivier Boiteau, Romain Brossier, Alfredo Buttari, Jean-Yves L'Excellent, Stephane Operto, and Jean Virieux. 3d frequency-domain seismic modeling with a block low-rank algebraic multifrontal direct solver. In SEG Technical Program Expanded Abstracts 2013, pages 3411--3416, 2013. [ DOI ]
[6] Alfredo Buttari. Fine granularity sparse QR factorization for multicore based systems. In Proceedings of the 10th international conference on Applied Parallel and Scientific Computing - Volume 2, PARA'10, pages 226--236, Berlin, Heidelberg, 2012. Springer-Verlag. [ http ]
[7] Alfredo Buttari, Julien Langou, Jakub Kurzak, and Jack Dongarra. Parallel tiled QR factorization for multicore architectures. In PPAM'07: Proceedings of the 7th international conference on Parallel processing and applied mathematics, pages 639--648, Berlin, Heidelberg, 2008. Springer-Verlag. [ DOI ]
[8] Alfredo Buttari, Jack Dongarra, Parry Husbands, Jakub Kurzak, and Katherine Yelick. Multithreading for synchronization tolerance in matrix factorization. In Proceedings of the SciDAC 2007 Conference, Boston, Massachusetts, 2007. Journal of Physics: Conference Series. [ DOI ]
[9] Alfredo Buttari, Jack Dongarra, Jakub Kurzak, Julien Langou, Piotr Luszczek, and Stanimire Tomov. The impact of multicore on math software. In Proceedings of the 8th international conference on Applied parallel computing: state of the art in scientific computing, PARA'06, pages 1--10, Berlin, Heidelberg, 2007. Springer-Verlag. [ http ]
[10] Jim Demmel, Jack Dongarra, Beresford Parlett, William Kahan, Ming Gu, Bindel Bindel, Yozo Hida, Xiaoye Sherry Li, Osni Marques, Jason Riedy, Christof Vomel, Julien Langou, Piotr Luszczek, Jakub Kurzak, Alfredo Buttari, Julie Langou, and Stanimire Tomov. Prospectus for the next lapack and scalapack libraries. In PARA'06: State-of-the-Art in Scientific and Parallel Computing, Umeå, Sweden, June 2006. High Performance Computing Center North (HPC2N) and the Department of Computing Science, UmeåUniversity, Springer. [ DOI ]
[11] Alfredo Buttari, Pasqua D'Ambra, Di Serafino Di Serafino, and Salvatore Filippone. Extending PSBLAS to Build Parallel Schwarz Preconditioners. In Springer, editor, Applied Parallel Computing. State of the Art in Scientific Computing: 7th International Conference, PARA 2004, Lyngby, Denmark, June 20-23, 2004., volume 3732 of Lecture Notes in Computer Science, pages 593--602, February 2006. [ DOI ]
[12] Julien Langou, Julie Langou, Piotr Luszczek, Jakub Kurzak, Alfredo Buttari, and Jack Dongarra. Exploiting the performance of 32 bit floating point arithmetic in obtaining 64 bit accuracy (revisiting iterative refinement for linear systems). In SC '06: Proceedings of the 2006 ACM/IEEE conference on Supercomputing, page 113, New York, NY, USA, 2006. ACM. [ DOI ]
[13] Gino Bella, Alfredo Buttari, Alessandro De Maio, Francesco Del Citto, Salvatore Filippone, and Fabiano Gasperini. FAST-EVP: an engine simulation tool. In Springer, editor, High Perfromance Computing and Communications. First International Conference, HPCC 2005, Proceedings, volume 3726 of Lecture Notes in Computer Science, pages 976--986, September 2005. [doi:10.1007/11557654_108].

This file was generated by bibtex2html 1.98.

Book Chapters

[1] Patrick Amestoy, Alfredo Buttari, I. Duff, A. Guermouche, Jean-Yves L'Excellent, and Bora Uçar. MUMPS. In David Padua, editor, Encyclopedia of Parallel Computing. Springer Verlag, 2011.
[2] Patrick Amestoy, Alfredo Buttari, Iain Duff, Abdou Guermouche, Jean-Yves L'Excellent, and Bora Uçar. The Multifrontal Method. In David Padua, editor, Encyclopedia of Parallel Computing. Springer Verlag, 2011.
[3] Jim Demmel, Jack Dongarra, Beresford Parlett, William Kahan, Ming Gu, Bindel Bindel, Yozo Hida, Xiaoye Sherry Li, Osni Marques, Jason Riedy, Christof Vomel, Julien Langou, Piotr Luszczek, Jakub Kurzak, Alfredo Buttari, Julie Langou, and Stanimire Tomov. Prospectus for a linear algebra software library for dense matrix problems. In Sanguthevar Rajasekaran and John Reif, editors, Handbook of Parallel Computing: Models, Algorithms and Applications, volume 17 of Chapman & HallCRC Computer & Information Science. CRC Press, 1 edition, December 2007. ISBN: 9781584886235.
[4] Alfredo Buttari, Jack Dongarra, Jakub Kurzak, Julien Langou, Julie Langou, Piotr Luszczek, and Stanimire Tomov. Exploiting mixed precision floating point hardware in scientific computations. In L. Grandinetti, editor, High Performance Computing and Grids in Action. IOS Press, 2007.
[5] Alfredo Buttari, Jack Dongarra, Jakub Kurzak, and Julien Langou. Parallel dense linear algebra software in the multicore era. In Junwei Cao, editor, Cyberinfrastructure Technologies and Applications. Nova Science Publishers, 2007.

This file was generated by bibtex2html 1.98.

Technical reports

[1] Emmanuel Agullo, Alfredo Buttari, Abdou Guermouche, and Florent Lopez. Task-based multifrontal QR solver for GPU-accelerated multicore architectures. Rapport de recherche IRI/RT--2015--02--FR, IRIT, Université Paul Sabatier, Toulouse, June 2015. Submitted to the HiPC 2015 conference. [ http ]
[2] Emmanuel Agullo, Alfredo Buttari, Abdou Guermouche, and Florent Lopez. Implementing multifrontal sparse solvers for multicore architectures with Sequential Task Flow runtime systems. Rapport de recherche IRI/RT--2014-03--FR, IRIT, Université Paul Sabatier, Toulouse, novembre 2014. Submitted to ACM Transactions On Mathematical Software. [ .pdf ]
[3] Alfredo Buttari, Jakub Kurzak, and Jack Dongarra. Limitations of the PlayStation 3 for High Performance Cluster Computing. Technical Report UT-CS-07-597, Innovative Computing Laboratory, University of Tennessee Knoxville, April 2007. LAPACK Working Note 185.
[4] Alfredo Buttari, Piotr Luszczek, Jakub Kurzak, Jack Dongarra, and George Bosilca. SCOP3: A rough guide to scientific computing on the PlayStation 3. version 0.1. Technical Report UT-CS-07-595, Innovative Computing Laboratory, University of Tennessee Knoxville, April 2007.

This file was generated by bibtex2html 1.98.