Abstract | ||
---|---|---|
High-Performance Computing (HPC) clusters are made up of a variety of node types (usually compute, I/O, service, and GPGPU nodes) and applications don't use nodes of a different type the same way. Resulting communication patterns reflect organization of groups of nodes, and current optimal routing algorithms for all-to-all patterns will not always maximize performance for group-specific communications. Since application communication patterns are rarely available beforehand, we choose to rely on node types as a good guess for node usage. We provide a description of node type heterogeneity and analyse performance degradation caused by unlucky repartition of nodes of the same type. We provide an extension to routing algorithms for Parallel Generalized Fat-Tree topologies (PGFTs) which balances load amongst groups of nodes of the same type. We show how it removes these performance issues by comparing results in a variety of situations against corresponding classical algorithms. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/HiPINEB.2018.00010 | 2018 IEEE 4th International Workshop on High-Performance Interconnection Networks in the Exascale and Big-Data Era (HiPINEB) |
Keywords | Field | DocType |
HPC,routing,fat-tree,PGFT,Dmodk,Smodk,heterogeneity | Computer science,Load balancing (computing),Parallel computing,Network topology,General-purpose computing on graphics processing units,Fat tree,Routing algorithm | Conference |
ISSN | ISBN | Citations |
2018 IEEE 4th International Workshop on High-Performance
Interconnection Networks in the Exascale and Big-Data Era (HiPINEB), Feb
2018, Vienna, France. pp.9-15 | 978-1-5386-5089-9 | 0 |
PageRank | References | Authors |
0.34 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
John Gliksberg | 1 | 0 | 0.34 |
Jean-Noël Quintin | 2 | 28 | 4.11 |
Pedro Javier Garcia | 3 | 79 | 16.03 |