TY - CHAP
T1 - Exploiting multiple heterogeneous networks to reduce communication costs in parallel programs
AU - Kim, Jun Seong
AU - Lilja, David J.
PY - 1997
Y1 - 1997
N2 - The different types of messages used by a parallel application program executing in a distributed system can each have unique characteristics so that no single communication network can produce the lowest latency for all messages. For instance, short control messages may be sent with the lowest overhead on one type of network, such as Ethernet, while bulk data transfers may be better suited to a different type of network, such as Fibre Channel or HiPPI. In this paper, we investigate how to exploit multiple heterogeneous communication networks that interconnect the same set of processing nodes by dynamically selecting the best (lowest latency) network for each message based on the message size. We also show how to aggregate these multiple parallel networks into a single virtual network to further reduce the latency and increase the available bandwidth. We test this multiplexing and aggregation on a cluster of SGI multiprocessors interconnected with both Fibre Channel and Ethernet. We find that multiplexing between Ethernet and Fibre Channel can substantially reduce communication overhead in a synthetic benchmark compared to using either network alone. Aggregating these two networks into a single virtual network can further reduce communication delays for applications with many large messages. The best choice of either multiplexing or aggregation depends on the mix of message sizes in the application program and the relative overheads of the two networks.
AB - The different types of messages used by a parallel application program executing in a distributed system can each have unique characteristics so that no single communication network can produce the lowest latency for all messages. For instance, short control messages may be sent with the lowest overhead on one type of network, such as Ethernet, while bulk data transfers may be better suited to a different type of network, such as Fibre Channel or HiPPI. In this paper, we investigate how to exploit multiple heterogeneous communication networks that interconnect the same set of processing nodes by dynamically selecting the best (lowest latency) network for each message based on the message size. We also show how to aggregate these multiple parallel networks into a single virtual network to further reduce the latency and increase the available bandwidth. We test this multiplexing and aggregation on a cluster of SGI multiprocessors interconnected with both Fibre Channel and Ethernet. We find that multiplexing between Ethernet and Fibre Channel can substantially reduce communication overhead in a synthetic benchmark compared to using either network alone. Aggregating these two networks into a single virtual network can further reduce communication delays for applications with many large messages. The best choice of either multiplexing or aggregation depends on the mix of message sizes in the application program and the relative overheads of the two networks.
UR - http://www.scopus.com/inward/record.url?scp=0031362305&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0031362305&partnerID=8YFLogxK
M3 - Chapter
AN - SCOPUS:0031362305
T3 - Proceedings of the Heterogeneous Computing Workshop, HCW
SP - 83
EP - 95
BT - Proceedings of the Heterogeneous Computing Workshop, HCW
A2 - Anon, null
PB - IEEE
T2 - Proceedings of the 1997 6th Heterogeneous Computing Workshop, HCW'97
Y2 - 1 April 1997 through 1 April 1997
ER -