Open AccessA Distributed and Parallel Asynchronous Unite and Conquer Method to Solve Large Scale Non-Hermitian Linear Systems
Author(s) -
Xinzhe Wu,
Serge G. Petiton
Publication year - 2018
Publication title -
hal (le centre pour la communication scientifique directe)
Language(s) - English
Resource type - Conference proceedings
DOI - 10.1145/3149457.3154481
Subject(s) - computer science , asynchronous communication , scalability , krylov subspace , speedup , parallel computing , scale (ratio) , computation , linear system , reusability , distributed computing , computer engineering , theoretical computer science , algorithm , iterative method , mathematics , software , physics , quantum mechanics , computer network , database , mathematical analysis , programming language
International audienceParallel Krylov Subspace Methods are commonly used for solving large-scale sparse linear systems. Facing the development of extreme scale platforms, the minimization of synchronous global communication becomes critical to obtain good efficiency and scal-ability. This paper highlights a recent development of a hybrid (unite and conquer) method, which combines three computation algorithms together with asynchronous communication to accelerate the resolution of non-Hermitian linear systems and to improve its fault tolerance and reusability. Experimentation shows that our method has an up to 5× speedup and better scalability than the conventional methods for the resolution on hierarchical clusters with hundreds of nodes
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom