The paper describes software architecture for supporting remote memory operations on clusters equipped with high-performance networks such as Myrinet and Giganet/Emulex cLAN. It presents protocols and strategies that bridge the gap between user-level API requirements and low-level network-specific interfaces such as GM and VIA. In particular, the issues of memory registration, management of network resources and memory consumption on the host, are discussed and solved to achieve an efficient implementation.
Revised: February 16, 2005 |
Published: April 15, 2002
Citation
Nieplocha J., V. Tipparaju, A. Saify, and D. Panda. 2002.Protocols and Strategies for Optimizing Performance of Remote Memory Operations on Clusters. In International Parallel and Distributed Processing Symposium, 164-173. Los Alamitos, California:IEEE Computer Society.PNNL-SA-36271.