DocumentCode :
2537085
Title :
Near-Optimal Rendezvous Protocols for RDMA-Enabled Clusters
Author :
Small, Matthew ; Gu, Zheng ; Yuan, Xin
Author_Institution :
Dept. of Comput. Sci., Florida State Univ., Tallahassee, FL, USA
fYear :
2010
fDate :
13-16 Sept. 2010
Firstpage :
644
Lastpage :
652
Abstract :
Optimizing Message Passing Interface (MPI) point-to-point communication for large messages is of paramount importance since most communications in MPI applications are performed by such operations. Remote Direct Memory Access (RDMA) allows one-sided data transfer and provides great flexibility in the design of efficient communication protocols for large messages. However, achieving high performance on RDMA-enabled clusters is still challenging due to the complexity both in communication protocols and in protocol invocation scenarios. In this work, we investigate a profile-driven compiled-assisted protocol customization approach for efficient communication on RDMA-enabled clusters. We analyze existing protocols and show that they are not ideal in many situations. By leveraging the RDMA capability, we develop a set of protocols that can provide near-optimal performance for all protocol invocation scenarios, which allows protocol customization to achieve near-optimal performance when the appropriate protocol is used for each communication. Finally, we evaluate the potential benefits of protocol customization using micro-benchmarks and application benchmarks. The results demonstrate that the proposed protocols can out-perform traditional rendezvous protocols to a large degree in many situations and that protocol customization can significantly improve MPI communication performance.
Keywords :
file organisation; message passing; MPI communication performance; RDMA enabled cluster; communication protocols; message passing interface; near optimal rendezvous protocol; one-sided data transfer; point-to-point communication; profile driven compiled assisted protocol customization approach; protocol invocation scenarios; remote direct memory access; Complexity theory; Delay; Instruction sets; Message systems; Protocols; Receivers; MPI; RDMA; Rendezvous protocol;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Parallel Processing (ICPP), 2010 39th International Conference on
Conference_Location :
San Diego, CA
ISSN :
0190-3918
Print_ISBN :
978-1-4244-7913-9
Electronic_ISBN :
0190-3918
Type :
conf
DOI :
10.1109/ICPP.2010.72
Filename :
5599241
Link To Document :
بازگشت