Paper Info
Title
Fault-Tolerant Routing for Exascale Supercomputer: The BXI Routing Architecture
Abstract
BXI, Bull eXascale Interconnect, is the new inter-connection network developed by Atos for High Performance Computing. It has been designed to meet the requirements of exascale supercomputers. At such scale, faults have to be expected and dealt with transparently so that applications remain unaffected by them. BXI features various mechanisms for this purpose, one of which is the BXI routing component presented in this paper. The BXI routing module computes the full routing tables for a 64k nodes fat-tree in a few minutes. But with partial re-computation it can withstand numerous inter-router link failures without any noticeable impact on running applications.
Year
DOI
Venue
2015
10.1109/CLUSTER.2015.135
Cluster Computing
Keywords
Field
DocType
Fabric Management, Routing, Fault-Tolerant Routing, BXI, Interconnect Management, High Performance Computing
Routing architecture,Algorithm design,Supercomputer,Computer science,System recovery,Parallel computing,Computer network,Real-time computing,Fault tolerance,Interconnection,Routing table,Distributed computing
Conference
ISSN
Citations 
PageRank 
1552-5244
2
0.39
References 
Authors
22
2
Name
Order
Citations
PageRank
P. Vignéras1132.54
Jean-Noël Quintin2284.11