Fat-Trees Routing and Node Ordering Providing Contention Free Traffic for MPI Global Collectives

As the size of High Performance Computing clusters grows, the increasing probability of interconnect hot spots degrades the latency and effective bandwidth the network provides. This paper presents a solution to this scalability problem for real life constant bisectional-bandwidth fat-tree topologie...

Full description

Saved in:
Bibliographic Details
Main Author: Zahavi, E.
Format: Conference Proceeding
Language:eng ; jpn
Subjects:
Bandwidth
Clustering algorithms
Degradation
Indexes
Routing
Topology
Traffic control
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As the size of High Performance Computing clusters grows, the increasing probability of interconnect hot spots degrades the latency and effective bandwidth the network provides. This paper presents a solution to this scalability problem for real life constant bisectional-bandwidth fat-tree topologies. It is shown that maximal bandwidth and cut-through latency can be achieved for MPI global collective traffic. To form such congestion-free configuration, MPI programs should utilize collective communication, MPI-node-order should be topology aware, and the packets routing should match the MPI communication patterns. First, we show that MPI collectives can be classified into unidirectional and bidirectional shifts. Using this property, we propose a scheme for congestion-free routing of the global collectives in fully and partially populated fat trees running a single job. Simulation results of the proposed routing, MPI-node-order and communication patterns show a 40% throughput improvement over previously published results for all-to-all collectives.
ISSN:1530-2075
DOI:10.1109/IPDPS.2011.219