Fast and Accurate Simulation of Multithreaded Sparse Linear Algebra Solvers - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

Fast and Accurate Simulation of Multithreaded Sparse Linear Algebra Solvers

Abstract

The ever growing complexity and scale of parallel architectures imposes to rewrite classical monolithic HPC scientific applications and libraries as their portability and performance optimization only comes at a prohibitive cost. There is thus a recent and general trend in using instead a modular approach where numerical algorithms are written at a high level independently of the hardware architecture as Directed Acyclic Graphs (DAG) of tasks. A task-based runtime system then dynamically schedules the resulting DAG on the different computing resources, automatically taking care of data movement and taking into account the possible speed heterogeneity and variability. Evaluating the performance of such complex and dynamic systems is extremely challenging especially for irregular codes. In this article, we explain how we crafted a faithful simulation, both in terms of performance and memory usage, of the behavior of qr_mumps, a fully-featured sparse linear algebra library, on multi-core architectures. In our approach, the target high-end machines are calibrated only once to derive sound performance models. These models can then be used at will to quickly predict and study in a reproducible way the performance of such irregular and resource-demanding applications using solely a commodity laptop.
Fichier principal
Vignette du fichier
QRMSTARSG_article.pdf (1.79 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01180272 , version 1 (24-07-2015)
hal-01180272 , version 2 (26-01-2016)

Identifiers

  • HAL Id : hal-01180272 , version 2

Cite

Luka Stanisic, Emmanuel Agullo, Alfredo Buttari, Abdou Guermouche, Arnaud Legrand, et al.. Fast and Accurate Simulation of Multithreaded Sparse Linear Algebra Solvers. The 21st IEEE International Conference on Parallel and Distributed Systems, Dec 2015, Melbourne, Australia. ⟨hal-01180272v2⟩
853 View
831 Download

Share

Gmail Facebook X LinkedIn More