Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Florent Lopez"'
Publikováno v:
SIAM Journal on Scientific Computing. 45:C1-C19
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a04df229cd4f265910000a49ab1e36fb
https://doi.org/10.1137/21m1465032
https://doi.org/10.1137/21m1465032
Publikováno v:
SIAM Journal on Scientific Computing. 42:C23-C42
The factorization of sparse symmetric indefinite systems is particularly challenging since pivoting is required to maintain stability of the factorization. Pivoting techniques generally offer limit...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::39d89453b0e2243458635ca126b6d2c7
https://doi.org/10.1137/18m1225963
https://doi.org/10.1137/18m1225963
Publikováno v:
SIAM Journal on Scientific Computing
SIAM Journal on Scientific Computing, Society for Industrial and Applied Mathematics, 2020, 42 (3), pp.C124-C141. ⟨10.1137/19M1289546⟩
SIAM Journal on Scientific Computing, Society for Industrial and Applied Mathematics, 2020, 42 (3), pp.C124-C141. ⟨10.1137/19M1289546⟩
International audience; Computing units that carry out a fused multiply-add (FMA) operation with matrix arguments, referred to as tensor units by some vendors, have great potential for use in scientific computing. However, these units are inherently
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d4662b96a9900853dc9ab819792bb315
https://hal.archives-ouvertes.fr/hal-02491076v2/file/BlockFMA.pdf
https://hal.archives-ouvertes.fr/hal-02491076v2/file/BlockFMA.pdf
Publikováno v:
IPDPS Workshops
We present a parallel asynchronous Stochastic Gradient Descent algorithm for shared memory architectures. Different from previous asynchronous algorithms, we consider the case where the gradient updates are not particularly sparse. In the context of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::83e917f6f1d1bf4217d3c9017175fe27
https://doi.org/10.1109/ipdpsw50202.2020.00168
https://doi.org/10.1109/ipdpsw50202.2020.00168
Autor:
Jack Dongarra, Eduardo D'Azevedo, Junqi Yin, Stanimire Tomov, Florent Lopez, Rocco Febbo, Markus Eisenbach, Edmond Chow, Rick Archibald, Kwai Wong, Daniel Nichols
Publikováno v:
Communications in Computer and Information Science ISBN: 9783030633929
SMC
SMC
This paper presents some of the current challenges in designing deep learning artificial intelligence (AI) and integrating it with traditional high-performance computing (HPC) simulations. We evaluate existing packages for their ability to run deep l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e5c05f45358a5f96a5977b8d737cbbcd
https://doi.org/10.1007/978-3-030-63393-6_3
https://doi.org/10.1007/978-3-030-63393-6_3
Autor:
Florent Lopez, Iain S. Duff
Publikováno v:
Parallel Processing and Applied Mathematics ISBN: 9783319780238
PPAM (1)
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Parallel Processing and Applied Mathematics
Parallel Processing and Applied Mathematics
PPAM (1)
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Parallel Processing and Applied Mathematics
Parallel Processing and Applied Mathematics
We describe the design of a sparse direct solver for symmetric positive-definite systems using the PaRSEC runtime system. In this approach the application is represented as a DAG of tasks and the runtime system runs the DAG on the target architecture
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b200c61461c26ae9877b71d4544a9661
https://doi.org/10.1007/978-3-319-78024-5_18
https://doi.org/10.1007/978-3-319-78024-5_18
Publikováno v:
Numerical Algebra, Control & Optimization
We describe the development of a prototype code for the solution of large sparse symmetric positive definite systems that is efficient on parallel architectures. We implement a DAG-based Cholesky factorization that offers good performance and scalabi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::35bf264340d207912027082268257859
Publikováno v:
Numerical Analysis and Optimization ISBN: 9783319900254
Numerical Analysis and Optimization
Springer Proceedings in Mathematics & Statistics
Springer Proceedings in Mathematics & Statistics-Numerical Analysis and Optimization
Numerical Analysis and Optimization
Springer Proceedings in Mathematics & Statistics
Springer Proceedings in Mathematics & Statistics-Numerical Analysis and Optimization
We describe our recent work on designing algorithms and software for solving sparse systems using direct methods on parallel computers. This work has been conducted within an EU Horizon 2020 Project called NLAFET. We first discuss the solution of lar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0a11a5e342bb9d293ddb977a993b6134
https://doi.org/10.1007/978-3-319-90026-1_4
https://doi.org/10.1007/978-3-319-90026-1_4
Publikováno v:
Euro-Par 2016: Parallel Processing Workshops
Euro-Par 2016: Parallel Processing Workshops, Aug 2016, Grenoble, France. ⟨10.1007/978-3-319-58943-5_14⟩
Euro-Par 2016: Parallel Processing Workshops ISBN: 9783319589428
Euro-Par Workshops
Euro-Par 2016: Parallel Processing Workshops, Aug 2016, Grenoble, France. ⟨10.1007/978-3-319-58943-5_14⟩
Euro-Par 2016: Parallel Processing Workshops ISBN: 9783319589428
Euro-Par Workshops
International audience; The advent of multicore processors requires to reconsider the design of high performance computing libraries to embrace portable and effective techniques of parallel software engineering. One of the most promising approaches c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::799f3b6394e127c84e50fb9ba96129ba
https://hal.science/hal-01337748/file/iwmse16_round1.pdf
https://hal.science/hal-01337748/file/iwmse16_round1.pdf
Publikováno v:
ACM Transactions on Mathematical Software
ACM Transactions on Mathematical Software, Association for Computing Machinery, 2016, ⟨10.1145/2898348⟩
ACM Transactions on Mathematical Software, 2016, ⟨10.1145/2898348⟩
ACM Transactions on Mathematical Software, Association for Computing Machinery, 2016, ⟨10.1145/2898348⟩
ACM Transactions on Mathematical Software, 2016, ⟨10.1145/2898348⟩
International audience; To face the advent of multicore processors and the ever increasing complexity of hardware architectures, programming models based on DAG parallelism regained popularity in the high performance, scientific computing community.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e3aedb19347d6fc10fe8eccde2badd5f
https://hal.inria.fr/hal-01333645/file/toms_qrm_starpu.pdf
https://hal.inria.fr/hal-01333645/file/toms_qrm_starpu.pdf