The SGI Origin 2000 is designedto support a wide range of applications and has low local and remote memory latencies. However, it often has a high ratio of remote to local misses....
Abstract--This paper explores the computation and communication overlap capabilities enabled by the new CORE-Direct hardware capabilities introduced in the InfiniBand (IB) Host Cha...
Richard L. Graham, Stephen W. Poole, Pavel Shamis,...
Abstract—Sharing patterns in shared-memory multiprocessors are the key to performance: uniprocessor latencytolerating techniques such as out-of-order execution and non-blocking c...
This paper evaluates the use of per-node multi-threading to hide remote memory and synchronization latencies in a software DSM. As with hardware systems, multi-threading in softwa...
A new method of retiming plesiochronous data is described. This method features latency of less than a cell-time and requires only minimal support circuitry. No flow control or ha...
Larry R. Dennison, William J. Dally, Thucydides Xa...