Efficient deadlock-free asynchronous approaches for a distributed-memory sparse direct solver (ICIAM 2015)

Mohamed Wissam Sid Lakhdar (1, 2) , Jean-Yves L'Excellent (3, 4) , Patrick Amestoy (5)

1 ENS de Lyon - École normale supérieure de Lyon
2 Texas A&M University [College Station]
3 LIP - Laboratoire de l'Informatique du Parallélisme
4 ROMA - Optimisation des ressources : modèles, algorithmes et ordonnancement
5 IRIT-APO - Algorithmes Parallèles et Optimisation

We describe how to enhance parallelism in an asynchronous distributed-memory environment with limited memory dedicated to communication. In order to maximize asynchronism, we characterize deadlock situations and establish global properties to prevent or avoid them. We also characterize some communication patterns and define a class of broadcast trees ensuring good efficiency for series of successive asynchronous broadcasts. The impact of this work is illustrated on asynchronous sparse multifrontal solvers but has a larger scope.

Domaines: Informatique [cs]; Mathématiques [math]

Mohamed Wissam Sid Lakhdar, Jean-Yves L'Excellent, Patrick Amestoy. Efficient deadlock-free asynchronous approaches for a distributed-memory sparse direct solver (ICIAM 2015). 8th International Congress on Industrial and Applied Mathematics (ICIAM 2015), International Council for Industrial and Applied Mathematics (ICIAM); National Natural Science Foundation of China; Chinese Academy of Sciences; China Association for Science and Technology; Ministry of Science and Technology of the People's Republic of China, Aug 2015, Beijing, China. ⟨hal-03209336⟩