EN FR
EN FR


Bibliography

Major publications by the team in recent years
  • 1E. Agullo, J. Dongarra, B. Hadri, H. Ltaief.

    Tile QR factorization with parallel panel processing for multicore architectures, in: SIAM Conference on Parallel Processing for Scientific Computing (PP10), United States Seattle, 2010.

    http://hal.inria.fr/inria-00548907/en
  • 2O. Coulaud, P. Fortin, J. Roman.

    High-performance BLAS formulation of the Adaptive Fast Multipole Method, in: Mathematical and Computer Modelling, 2009, vol. 51, no 3-4, pp. 177-188.
  • 3J. Dongarra, M. Faverge, T. Hérault, M. Jacquelin, J. Langou, Y. Robert.

    Hierarchical QR factorization algorithms for multi-core clusters, in: Parallel Computing, 2013, vol. 39, no 4-5, pp. 212-232. [ DOI : 10.1016/j.parco.2013.01.003 ]

    http://hal.inria.fr/hal-00809770
  • 4L. Giraud, S. Gratton, X. Pinel, X. Vasseur.

    Flexible GMRES with deflated restarting, in: SIAM Journal on Scientific Computing, October 2010, vol. 32, no 4, pp. 1858–1878. [ DOI : 10.1137/080741847 ]

    http://hal.inria.fr/inria-00542426/en
  • 5L. Giraud, A. Haidar, Y. Saad.

    Sparse approximations of the Schur complement for parallel algebraic hybrid linear solvers in 3D, in: Numerical Mathematics: Theory, Methods and Applications, August 2010, vol. 3, no 3, pp. 276-294.

    http://hal.inria.fr/inria-00542450/en
  • 6P. Hénon, P. Ramet, J. Roman.

    On finding approximate supernodes for an efficient ILU(k) factorization, in: Parallel Computing, 2008, vol. 34, pp. 345–362.

    http://hal.inria.fr/inria-00346018
  • 7P. Koval, D. Foerster, O. Coulaud.

    A Parallel Iterative Method for Computing Molecular Absorption Spectra, in: Journal of Chemical Theory and Computation, 2010, vol. 6, no 9, pp. 2654–2668. [ DOI : 10.1021/ct100280x ]

    http://hal.inria.fr/inria-00488048/en
  • 8C. Vuchener, A. Esnard.

    Dynamic Load-Balancing with Variable Number of Processors based on Graph Repartitioning, in: HIPC 2012, Pune, India, 2012, pp. 1-9.

    http://hal.inria.fr/hal-00722731
Publications of the year

Doctoral Dissertations and Habilitation Theses

  • 9R. Abdelkhalek.

    Acceleration materielle pour l'imagerie sismique : modelisation, migration et interpretation, Université Sciences et Technologies - Bordeaux I, December 2013.

    http://hal.inria.fr/tel-00936989
  • 10P. Salas.

    Aspects numeriques et physiques des instabilites thermoacoustiques dans les chambres de combustion annulaires, Université Sciences et Technologies - Bordeaux I, November 2013.

    http://hal.inria.fr/tel-00937020

Articles in International Peer-Reviewed Journals

  • 11E. Agullo, B. Bramas, O. Coulaud, E. Darve, M. Messner, T. Takahashi.

    Task-Based FMM for Multicore Architectures, in: SIAM Journal on Scientific Computing, 2013.

    http://hal.inria.fr/hal-00911856
  • 12G. Bosilca, A. Bouteiller, A. Danalis, M. Faverge, T. Hérault, J. Dongarra.

    PaRSEC: A programming paradigm exploiting heterogeneity for enhancing scalability, in: Computing in Science and Engineering, 2013, vol. 99, 1 p. [ DOI : 10.1109/MCSE.2013.98 ]

    http://hal.inria.fr/hal-00930217
  • 13M. Chanaud, L. Giraud, D. Goudin, J.-J. Pesqué, J. Roman.

    A Parallel Full Geometric Multigrid Solver for Time Harmonic Maxwell Problems, in: SIAM Journal on Scientific Computing, December 2013.

    http://hal.inria.fr/hal-00933526
  • 14J. Dongarra, M. Faverge, T. Hérault, M. Jacquelin, J. Langou, Y. Robert.

    Hierarchical QR factorization algorithms for multi-core clusters, in: Parallel Computing, 2013, vol. 39, no 4-5, pp. 212-232. [ DOI : 10.1016/j.parco.2013.01.003 ]

    http://hal.inria.fr/hal-00809770
  • 15J. J. Dongarra, M. Faverge, H. Ltaief, P. Luszczek.

    Achieving Numerical Accuracy and High Performance using Recursive Tile LU Factorization, in: Concurrency and Computation: Practice and Experience, September 2013. [ DOI : 10.1002/cpe.3110 ]

    http://hal.inria.fr/hal-00865472

Invited Conferences

  • 16L. Giraud.

    Algebraic preconditioners for parallel hybrid solvers, in: High Performance Computing in Science and Engineering, Ostrava, Czech Republic, May 2013.

    http://hal.inria.fr/hal-00933517

International Conferences with Proceedings

  • 17G. Aupy, M. Faverge, Y. Robert, J. Kurzak, P. Luszczek, J. Dongarra.

    Implementing a systolic algorithm for QR factorization on multicore clusters with PaRSEC, in: PROPER 2013 - 6th Workshop on Productivity and Performance, Aachen, Germany, August 2013.

    http://hal.inria.fr/hal-00844492
  • 18M. Faverge, J. Herrmann, J. Langou, B. Lowery, Y. Robert, J. Dongarra.

    Designing LU-QR hybrid solvers for performance and stability, in: IEEE International Parallel & Distributed Processing Symposium, Phoenix, United States, December 2013.

    http://hal.inria.fr/hal-00930238
  • 19A.-E. Hugo, A. Guermouche, R. Namyst, P.-A. Wacrenier.

    Composing multiple StarPU applications over heterogeneous machines: a supervised approach, in: Third International Workshop on Accelerators and Hybrid Exascale Systems, Boston, United States, May 2013.

    http://hal.inria.fr/hal-00824514
  • 20G. Latu, J. Roman, F. Rozar.

    Achieving Memory Scalability in the Gysela Code to Fit Exascale Constraints, in: 10th International Conference on Parallel Processing and Applied Mathematics, Warsaw, Poland, Lecture Note in Computer Science, Springer, September 2013, To appear.

    http://hal.inria.fr/hal-00935519
  • 21S. Moustafa, I. Dutka Malen, L. Plagne, A. Ponçot, P. Ramet.

    Shared Memory Parallelism for 3D Cartesian Discrete Ordinates Solver, in: Joint International Conference on Supercomputing in Nuclear Applications and Monte Carlo 2013, Paris, France, October 2013.

    http://hal.inria.fr/hal-00924989
  • 22C. Vuchener, A. Esnard.

    Graph Repartitioning with both Dynamic Load and Dynamic Processor Allocation, in: International Conference on Parallel Computing - ParCo2013, München, Germany, Advances of Parallel Computing, 2013.

    http://hal.inria.fr/hal-00857881

Conferences without Proceedings

  • 23E. Agullo, B. Bramas, O. Coulaud, E. Darve, M. Messner, T. Takahashi.

    Pipelining the Fast Multipole Method over a Runtime System, in: SIAM Conference on Computational Science and Engineering - CSE 2013, Boston, United States, February 2013.

    http://hal.inria.fr/hal-00797403
  • 24E. Agullo, B. Bramas, O. Coulaud, E. Darve, M. Messner, T. Takahashi.

    Task-based Parallelization of the Fast Multipole Method on NVIDIA GPUs and Multicore Processors, in: GPU Technology Conference, San Jose, California, United States, NVIDIA, 2013.

    http://hal.inria.fr/hal-00879291
  • 25E. Agullo, L. Giraud, A. Guermouche, S. Nakov, J. Roman.

    Pipelining the CG Solver Over a Runtime System, in: GPU Technology Conference, San Jose, United States, NVIIDA, March 2013.

    http://hal.inria.fr/hal-00934948
  • 26E. Agullo, L. Giraud, A. Guermouche, J. Roman.

    Towards resilient parallel linear Krylov solvers with recover-restart strategies, in: European Numerical Mathematics and Advanced Applications, Lausanne, Switzerland, August 2013.

    http://hal.inria.fr/hal-00933640
  • 27E. Agullo, L. Giraud, A. Guermouche, J. Roman, M. Zounon.

    Towards resilient parallel linear Krylov solvers: recover-restart strategies, in: Sparse days 2013, Toulouse, France, CERFACS, 2013.

    http://hal.inria.fr/hal-00935685
  • 28L. Boillot, E. Agullo, H. Barucq, G. Bosilca, H. Calandra, J. Diaz.

    Optimized propagators for elastic waves with anisotropy Part 1: Applied Mathematics Part 2: High-Performance Computing, in: XSEDE – International Summer School on HPC Challenges in Computational Sciences (PRACE workshop), New York, United States, June 2013.

    http://hal.inria.fr/hal-00868169
  • 29L. Boillot, E. Agullo, G. Bosilca, H. Calandra.

    3D Geophysics over a runtime system on a ccNUMA machine, in: MATHIAS - TOTAL Symposium on Mathematics, Paris, France, October 2013.

    http://hal.inria.fr/hal-00877316
  • 30L. Boillot, E. Agullo, G. Bosilca, H. Calandra.

    Combining recent HPC techniques for 3D geophysics acceleration, in: 2nd ECCOMAS Young Investigators Conference (YIC 2013), Bordeaux, France, September 2013.

    http://hal.inria.fr/hal-00855878
  • 31G. Bosilca, A. Bouteiller, M. Faverge, T. Hérault.

    Linear Algebra Libraries with DAG Runtimes on GPUs, in: SIAM CSE 2013, Boston, United States, February 2013.

    http://hal.inria.fr/hal-00934573
  • 32A. Casadei, L. Giraud, P. Ramet, J. Roman.

    Towards Domain Decomposition with Balanced Halo, in: Workshop Celebrating 40 Years of Nested Dissection, Waterloo, Canada, July 2013.

    http://hal.inria.fr/hal-00924977
  • 33E. Darve, M. Messner, M. Schanz, O. Coulaud.

    Optimizing the Black-box FMM for Smooth and Oscillatory Kernels, in: SIAM Conference on Computational Science and Engineering, Boston, United States, SIAM, February 2013.

    http://hal.inria.fr/hal-00799885
  • 34Y. Dudouit, L. Giraud, F. Millot, S. Pernet.

    Parallel local time-stepping for elastodynamic equations, in: Conference on Mathematical and Computational Issues in the Geosciences, Padua, Italy, SIAM, June 2013.

    http://hal.inria.fr/hal-00933533
  • 35L. Giraud, F. Cappello.

    Resilience at extreme scale : system level, algorithmic level or both ?, in: SIAM Conference on Computational Science and Engineering - CSE 2013, Boston, United States, SIAM, March 2013.

    http://hal.inria.fr/hal-00799309
  • 36L. Giraud, P. Salas, X. Vasseur.

    Eigensolvers for thermoacoustics instabilities in combustion chambers, in: Conference on Computational Sciences and Engineering, Boston, United States, SIAM, March 2013.

    http://hal.inria.fr/hal-00933498
  • 37X. Lacoste.

    Work stealing and granularity optimizations for a sparse solver on manycores, in: Sparse days 2013, Toulouse, France, June 2013.

    http://hal.inria.fr/hal-00932823
  • 38P. Ramet.

    From hybrid architectures to hybrid solvers, in: Workshop Celebrating 40 Years of Nested Dissection, Waterloo, Canada, July 2013.

    http://hal.inria.fr/hal-00924979

Scientific Books (or Scientific Book chapters)

  • 39O. Coulaud, L. Giraud, P. Ramet, X. Vasseur.

    Deflation and augmentation techniques in Krylov linear solvers, in: Developments in Parallel - Distributed - Grid and Cloud Computing for Engineering, B. Topping, P. Ivanyi (editors), Saxe-Coburg Publications, March 2013.

    http://hal.inria.fr/hal-00860339

Internal Reports

  • 40E. Agullo, B. Bramas, O. Coulaud, E. Darve, M. Messner, T. Takahashi.

    Task-based FMM for multicore architectures, Inria, March 2013, no RR-8277, 33 p, Preliminary version of a paper to appear in SIAM SISC.

    http://hal.inria.fr/hal-00807368
  • 41E. Agullo, L. Giraud, A. Guermouche, J. Roman, M. Zounon.

    Towards resilient parallel linear Krylov solvers: recover-restart strategies, Inria, July 2013, no RR-8324, 36 p.

    http://hal.inria.fr/hal-00843992
  • 42M. Chanaud, L. Giraud, D. Goudin, J.-J. Pesqué, J. Roman.

    A Parallel Full Geometric Multigrid Solver for Time Harmonic Maxwell Problems, Inria, July 2013, no RR-8335, 25 p, Preliminary version of a paper to appear in SIAM SISC.

    http://hal.inria.fr/hal-00847966
  • 43O. Coulaud, P. Bordat, P. Fayon, V. Lebris, I. Baraille, R. Brown.

    Extensions of the Siesta DFT Code for Simulation of Molecules, Inria, February 2013, no RR-8221, 25 p.

    http://hal.inria.fr/hal-00787088
  • 44O. Coulaud, L. Giraud, P. Ramet, X. Vasseur.

    Deflation and augmentation techniques in Krylov linear solvers, Inria, February 2013, no RR-8265, 25 p.

    http://hal.inria.fr/hal-00803225
  • 45S. Donfack, J. Dongarra, M. Faverge, M. Gates, J. Kurzak, P. Luszczek, I. Yamazaki.

    On Algorithmic Variants of Parallel Gaussian Elimination: Comparison of Implementations in Terms of Performance and Numerical Properties, 2013.

    http://hal.inria.fr/hal-00867837
  • 46X. Lacoste, M. Faverge, P. Ramet, S. Thibault, G. Bosilca.

    Taking advantage of hybrid systems for sparse direct solvers via task-based runtimes, Inria, January 2014, no RR-8446, 25 p.

    http://hal.inria.fr/hal-00925017