Machine Learning to Design an Auto-tuning System for the Best Compressed Format Detection for Parallel Sparse Computations
| Autor: | Olfa Hamdi-Larbi, Ichrak Mehrez, Thomas Dufaud |
|---|---|
| Přispěvatelé: | Université de Tunis El Manar (UTM), Taibah University, Laboratoire d'Informatique Parallélisme Réseaux Algorithmes Distribués (LI-PaRAD), Université de Versailles Saint-Quentin-en-Yvelines (UVSQ), Maison de la Simulation (MDLS), Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Institut National de Recherche en Informatique et en Automatique (Inria)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS) |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Smart system
Computer science Computation Process (computing) 02 engineering and technology 01 natural sciences Theoretical Computer Science Auto tuning 010104 statistics & probability Computer engineering Work (electrical) Hardware and Architecture 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing 0101 mathematics [INFO.INFO-DC]Computer Science [cs]/Distributed Parallel and Cluster Computing [cs.DC] Software Sparse matrix |
| Zdroj: | Parallel Processing Letters Parallel Processing Letters, World Scientific Publishing, 2021, ⟨10.1142/S0129626421500195⟩ Parallel Processing Letters, 2021, 31 (04), pp.2150019. ⟨10.1142/S0129626421500195⟩ |
| ISSN: | 0129-6264 1793-642X |
| Popis: | International audience; Many applications in scientific computing process very large sparse matrices on parallel architectures. The presented work in this paper is a part of a project where our general aim is to develop an auto-tuner system for the selection of the best matrix compression format in the context of high-performance computing. The target smart system can automatically select the best compression format for a given sparse matrix, a numerical method processing this matrix, a parallel programming model and a target architecture. Hence, this paper describes the design and implementation of the proposed concept. We consider a case study consisting of a numerical method reduced to the sparse matrix vector product (SpMV), some compression formats, the data parallel as a programming model and, a distributed multi-core platform as a target architecture. This study allows extracting a set of important novel metrics and parameters which are relative to the considered programming model. Our metrics are used as input to a machine-learning algorithm to predict the best matrix compression format. An experimental study targeting a distributed multi-core platform and processing random and real-world matrices shows that our system can improve in average up to 7% the accuracy of the machine learning. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|