Hybrid MPI/StarSs - a case study

Hybrid parallel programming models combining distributed and shared memory paradigms are well established in high-performance computing. The classical prototype of hybrid programming in HPC is MPI/OpenMP, but many other combinations are being investigated. Recently, the data-dependency driven, task...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2012-04
Main Authors: Gracia, Jose, Niethammer, Christoph, Hasert, Manuel, Brinkmann, Steffen, Keller, Rainer, Glass, Colin W
Format: Article
Language:English
Subjects:
Dependence
Distributed memory
Parallel programming
Servers
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hybrid parallel programming models combining distributed and shared memory paradigms are well established in high-performance computing. The classical prototype of hybrid programming in HPC is MPI/OpenMP, but many other combinations are being investigated. Recently, the data-dependency driven, task parallel model for shared memory parallelisation named StarSs has been suggested for usage in combination with MPI. In this paper we apply hybrid MPI/StarSs to a Lattice-Boltzmann code. In particular, we present the hybrid programming model, the benefits we expect, the challenges in porting, and finally a comparison of the performance of MPI/StarSs hybrid, MPI/OpenMP hybrid and the original MPI-only versions of the same code.
ISSN:2331-8422