Using a single traditional gang scheduling algorithm cannot provide the best performance for all workloads and parallel architectures. A solution for this problem is the use of...
— SuperMatrix out-of-order scheduling leverages el abstractions and straightforward data dependency analysis to provide a general-purpose mechanism for obtaining parallelism from...
Ernie Chan, Field G. Van Zee, Enrique S. Quintana-...
SIMD extensions are the most common technique used in current processors for multimedia computing. In order to obtain more performance for emerging applications SIMD extensions ne...
In designing bus based systems with parallel and pipelined architecture, it is important to derive a real time budget (a specified execution time limit) for each task of a bus bas...
: In this paper, we have proposed a time efficient, energy saving and robust broadcast/multicast protocol for reconfigurable cluster-based sensor network. In our broadcast protocol...
Wei Chen, Islam A. K. M. Muzahidul, Mohan Malkani,...