@Article{FavRam09ParCo,
author = {Mathieu Faverge and Pierre Ramet},
title = {A {NUMA} Aware Scheduler for a Parallel Sparse Direct Solver},
journal = {{P}arallel {C}omputing},
year = {2009},
note = {Submitted},
keywords = {NUMA} 
}

@InProceedings{AguAugDonFavLanLtaTomAICCSA11,
author = {Emmanuel Agullo and C{\'e}dric Augonnet and Jack Dongarra and Mathieu Faverge and Julien Langou and Hatem Ltaief and Stanimire Tomov},
title = {{LU} factorization for accelerator-based systems},
booktitle = {9th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA 11)},
year = 2011,
month = JUNE,
address = {Sharm El-Sheikh, Egypt},
url = {http://hal.inria.fr/hal-00654193},
keywords = {StarPU} 
}

@InProceedings{AguAugDonFavLtaThiTom11IPDPS,
HAL_ID = {inria-00547614},
author={Emmanuel Agullo and C{\'{e}}dric Augonnet and Jack Dongarra and Mathieu Faverge and Hatem Ltaief and Samuel Thibault and Stanimire Tomov},
title = {{QR Factorization on a Multicore Node Enhanced with Multiple GPU Accelerators}},
booktitle = {{25th IEEE International Parallel \& Distributed Processing Symposium (IEEE IPDPS 2011)}},
ADDRESS={Anchorage, Alaska, USA},
language = {{A}nglais},
audience = {internationale },
DAYS=16,
MONTH=5,
YEAR=2011,
keywords = {StarPU},
doi = {10.1109/IPDPS.2011.90},
URL = {http://hal.inria.fr/inria-00547614} 
}

@InProceedings{Fav09I3M,
author = {Mathieu Faverge},
title = {A NUMA Aware Scheduler for a Parallel Sparse Direct Solver},
booktitle = "Journ\'ees Informatique Massivement Multiprocesseur et Multicoeur",
year = {2009},
address = {Rocquencourt, France},
month = feb,
url = {http://www.labri.fr/~ramet/restricted/i3m.pdf.gz},
keywords = {NUMA} 
}

@InProceedings{Fav09Renpar19,
author = {Mathieu Faverge},
title = {Vers un solveur de systèmes linéaires creux adapté aux machines {NUMA}},
booktitle = {19{\`e}mes Rencontres Francophones du Parall{\'e}lisme},
year = 2009,
month = SEP,
address = {Toulouse / France},
keywords = {NUMA},
url = {http://hal.inria.fr/inria-00416496} 
}

@InProceedings{FavLacRam08PMAA,
author = "Mathieu Faverge and Xavier Lacoste and Pierre Ramet",
title = {{A NUMA Aware Scheduler for a Parallel Sparse Direct Solver}},
booktitle = "Proceedings of {PMAA}'2008, Neuch\^atel, Suisse",
year = "2008",
url = {http://hal.inria.fr/inria-00344709},
keywords = {NUMA},
abstract = {Over the past few years, parallel sparse direct solvers made significant progress and are now able to solve efficiently industrial three-dimensional problems with several millions of unknowns. An hybrid MPI-thread implementation of our direct solver PaStiX is already well suited for SMP nodes or new multi-core architectures and drastically reduced the memory overhead and improved scalability. In the context of distributed NUMA architectures, a dynamic scheduler based on a work-stealing algorithm has been developed to fill in communication idle times. On these architectures, it is important to take care of NUMA effects and to preserve memory affinity during the work-stealing. The scheduling of communications also needs to be adapted, especially to ensure the overlap by computations. Experiments on numerical test cases will be presented to prove the efficiency of the approach on NUMA architectures. If memory is not large enough to treat a given problem, disks must be used to store data that cannot fit in memory (out-of-core storage). The idle-times due to disk access have to be managed by our dynamic scheduler to prefetch and save datasets. Thus, we design and study specific scheduling algorithms in this particular context.} 
}

@InProceedings{FavRam08PARA,
author = {Mathieu Faverge and Pierre Ramet},
title = {{Dynamic Scheduling for sparse direct Solver on NUMA architectures}},
booktitle = {Proceedings of PARA'2008, Trondheim, Norway},
year = {2008},
url = {http://hal.inria.fr/inria-00344026},
OPTurl = {http://www.labri.fr/~ramet/restricted/para08.pdf.gz},
keywords = {NUMA},
abstract = {Over the past few years, parallel sparse direct solvers made significant progress and are now able to efficiently work on problems with several millions of equations. This paper presents some improvements on our sparse direct solver PaStiX1 for distributed Non-Uniform Memory Access architectures. We show results on two preliminary works: a memory allocation scheme more adapted to these architectures and a better overlap of communication by computation. We also present a dynamic scheduler that takes care of memory affinity and data locality.} 
}