All-to-all personalized exchange is one of the most dense collective communication patterns and occurs in many important parallel computing/networking applications. In this paper,...
This paper examines two Network Interface Card microarchitectures that support low latency, high bandwidth userlevel message passing in multi-user environments. The two are at dif...
Boon Seong Ang, Derek Chiou, Larry Rudolph, Arvind
We study the issue of performance prediction on the SGIPower Challenge, a typical SMP. On such a platform, the cost of memory accesses depends on their locality and on contention ...
Nancy M. Amato, Jack Perdue, Mark M. Mathis, Andre...
In order to show that the parallel co-evolution of di erent heuristic methods may lead to an e cient search strategy, we have hybridized three heuristic agents of complementary beh...
In a distributed file system built on network attached storage, client computers access data directly from shared storage, rather than submitting I/O requests through a server. W...
Randal C. Burns, Robert M. Rees, Darrell D. E. Lon...