Metaprogramming dense linear algebra solvers. Applications to multi and many-core architectures
| Autor: | Masliah, Ian, Baboulin, Marc, Falcou, Joel |
|---|---|
| Přispěvatelé: | Laboratoire de Recherche en Informatique (LRI), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Performance Optimization by Software Transformation and Algorithms & Librairies Enhancement (POSTALE), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Baboulin, Marc |
| Jazyk: | angličtina |
| Rok vydání: | 2015 |
| Předmět: |
010302 applied physics
active libraries 02 engineering and technology GPU computing [INFO.INFO-NA]Computer Science [cs]/Numerical Analysis [cs.NA] 01 natural sciences 020202 computer hardware & architecture Numerical libraries dense linear systems [INFO.INFO-NA] Computer Science [cs]/Numerical Analysis [cs.NA] 0103 physical sciences 0202 electrical engineering electronic engineering information engineering [INFO.INFO-DC] Computer Science [cs]/Distributed Parallel and Cluster Computing [cs.DC] Computer Science::Mathematical Software generative programming mixed precision algorithms [INFO.INFO-DC]Computer Science [cs]/Distributed Parallel and Cluster Computing [cs.DC] |
| Zdroj: | 13th IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA 2015) 13th IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA 2015), Aug 2015, Helsinki, Finland |
| Popis: | International audience; The increasing complexity of new parallel architectures has widened the gap between adaptability and efficiency of the codes. As high performance numerical libraries tend to focus more on performance, we wish to address this issue using a C++ library called NT2. By analyzing the properties of the linear algebra domain that can be extracted from numerical libraries and combining them with architectural features, we developed a generic approach to solve dense linear systems on various architectures including CPU and GPU. We have then extended our work with an example of a least squares solver based on semi-normal equations in mixed precision that cannot be found in current libraries. For the automatically generated solvers, we report performance comparisons with state-of-the-art codes, and show that it is possible to obtain a generic code with a high-level interface (similar to MATLAB) which runs either on CPU or GPU without generating a significant overhead. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|