Virtual Network Transport Protocols for Myrinet
Brent N. Chun and Alan M. Mainwaring and David E. Culler
EECS Department, University of California, Berkeley
Technical Report No. UCB/CSD-98-988
, 1998
http://www2.eecs.berkeley.edu/Pubs/TechRpts/1998/CSD-98-988.pdf
This paper describes a protocol for a general-purpose cluster communication system that supports multiprogramming with virtual networks, direct and protected network access, reliable message delivery using message timeouts and retransmissions, a powerful return-to-send error model for applications, and automatic network mapping. The protocols use simple, low-cost mechanisms that exploit properties of our interconnect without limiting flexibility, usability or robustness. We have implemented the protocols in an active message communication system that runs a network of 100+ Sun UltraSPARC workstations interconnected with 40 Myrinet switches. A progression of microbenchmarks demonstrate good performance -- 42 microsecond round-trip times and 31 MB/s node to node bandwidth -- as well as scalability under heavy load and graceful performance degradation in the presence of high contention.
BibTeX citation:
@techreport{Chun:CSD-98-988, Author= {Chun, Brent N. and Mainwaring, Alan M. and Culler, David E.}, Title= {Virtual Network Transport Protocols for Myrinet}, Year= {1998}, Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/1998/5432.html}, Number= {UCB/CSD-98-988}, Abstract= {This paper describes a protocol for a general-purpose cluster communication system that supports multiprogramming with virtual networks, direct and protected network access, reliable message delivery using message timeouts and retransmissions, a powerful return-to-send error model for applications, and automatic network mapping. The protocols use simple, low-cost mechanisms that exploit properties of our interconnect without limiting flexibility, usability or robustness. We have implemented the protocols in an active message communication system that runs a network of 100+ Sun UltraSPARC workstations interconnected with 40 Myrinet switches. A progression of microbenchmarks demonstrate good performance -- 42 microsecond round-trip times and 31 MB/s node to node bandwidth -- as well as scalability under heavy load and graceful performance degradation in the presence of high contention.}, }
EndNote citation:
%0 Report %A Chun, Brent N. %A Mainwaring, Alan M. %A Culler, David E. %T Virtual Network Transport Protocols for Myrinet %I EECS Department, University of California, Berkeley %D 1998 %@ UCB/CSD-98-988 %U http://www2.eecs.berkeley.edu/Pubs/TechRpts/1998/5432.html %F Chun:CSD-98-988