Deadlock-Free Message Routing in Multiprocessor Interconnection Networks
IEEE Transactions on Computers
Multicomputer networks: message-based parallel processing
Multicomputer networks: message-based parallel processing
Parallel branch and bound algorithms on hypercube multiprocessors
C3P Proceedings of the third conference on Hypercube concurrent computers and applications - Volume 2
Intensive hypercube communication. Prearranged communication in link-bound machines
Journal of Parallel and Distributed Computing
Deadlock-free packet switching networks
STOC '79 Proceedings of the eleventh annual ACM symposium on Theory of computing
Deadlock- and livelock-free packet switching networks
STOC '80 Proceedings of the twelfth annual ACM symposium on Theory of computing
On the Performance of k-ary n-cube Interconnection Networks
On the Performance of k-ary n-cube Interconnection Networks
ACM SIGOPS Operating Systems Review
ISCA '90 Proceedings of the 17th annual international symposium on Computer Architecture
IEEE Transactions on Parallel and Distributed Systems
Hi-index | 0.00 |
In this paper we present a high performance message transport scheme that is based upon packet routing. The advantages of our scheme are derived from two observations. The first is that given sufficient support from communications hardware, decreasing the message latency time can be much more important to total program execution time than increasing the bandwidth. The second observation is that, from the standpoint of message latency, existing routing strategies tend not to make productive use of much of their available link capacity. The scheme that we propose addresses these issues and leads to substantial performance improvements across a broad range of message loads.