M
Mathieu Faverge
Researcher at University of Bordeaux
Publications - 71
Citations - 1390
Mathieu Faverge is an academic researcher from University of Bordeaux. The author has contributed to research in topics: LU decomposition & Solver. The author has an hindex of 19, co-authored 65 publications receiving 1210 citations. Previous affiliations of Mathieu Faverge include University of Tennessee & French Institute for Research in Computer Science and Automation.
Papers
More filters
Journal ArticleDOI
PaRSEC: Exploiting Heterogeneity to Enhance Scalability
George Bosilca,Aurelien Bouteiller,Anthony Danalis,Mathieu Faverge,Thomas Herault,Jack Dongarra +5 more
TL;DR: In this article, the authors present an approach based on task parallelism that reveals the application's parallelism by expressing its algorithm as a task flow, which allows the algorithm to be decoupled from the data distribution and the underlying hardware.
Proceedings ArticleDOI
Flexible Development of Dense Linear Algebra Algorithms on Massively Parallel Architectures with DPLASMA
George Bosilca,Aurelien Bouteiller,Anthony Danalis,Mathieu Faverge,Azzam Haidar,Thomas Herault,Jakub Kurzak,Julien Langou,Pierre Lemarinier,Hatem Ltaief,Piotr Luszczek,Asim YarKhan,Jack Dongarra +12 more
TL;DR: It is demonstrated through experimental results on the Cray XT5 Kraken system that the DAG-based approach has the potential to achieve sizable fraction of peak performance which is characteristic of the state-of-the-art distributed numerical software on current and emerging architectures.
Proceedings ArticleDOI
QR Factorization on a Multicore Node Enhanced with Multiple GPU Accelerators
Emmanuel Agullo,Cédric Augonnet,Jack Dongarra,Mathieu Faverge,Hatem Ltaief,Samuel Thibault,Stanimire Tomov +6 more
TL;DR: The design of a highly efficient QR factorization for a hybrid accelerators-based node enhanced with GPU accelerators is presented and it is demonstrated that the obtained performance is very close to the theoretical upper bounds that were obtained using Linear Programming.
Journal ArticleDOI
Achieving High Performance on Supercomputers with a Sequential Task-based Programming Model
Emmanuel Agullo,Olivier Aumage,Mathieu Faverge,Nathalie Furmento,Florent Pruvost,Marc Sergent,Samuel Thibault +6 more
TL;DR: This paper has extended the StarPU runtime system with an advanced inter-node data management layer that supports the sequential task-based programming model, and shows that this paradigm can also be employed to achieve high performance on modern supercomputers composed of multiple such nodes, with extremely limited changes in the user code.
Proceedings ArticleDOI
LU factorization for accelerator-based systems
Emmanuel Agullo,Cédric Augonnet,Jack Dongarra,Mathieu Faverge,Julien Langou,Hatem Ltaief,Stanimire Tomov +6 more
TL;DR: It is shown that the numerical results of the tile LU factorization will be accurate enough for most applications as long as the computations are performed in double precision arithmetic.