Network-based parallel computing : communication, architecture, and applications ; proceedings. 3 (1999), Orlando, Florida, USA, January 9th, 1999
These refereed papers from CANPC '99 present late-1990s "state of the art" in network-based parallel computing employing clusters of workstations/PCs connected by off-the-shelf networks for cost-effective high performance computing.
VIII, 224 Seiten : Diagramme.
9783540659150, 3540659153
634325456
A Parallel Implementation of the Everglades Landscape Fire Model in Networks of Workstations.- Adaptation Models for Network-Aware Distributed Computations.- Prototyping Execution Models for HTMT Petaflop Machine in Java.- Is It Worth the Flexibility Provided by Irregular Topologies in Networks of Workstations?.- Performance Evaluation of the Multimedia Router with MPEG-2 Video Traffic.- A Scalable Flow Control Algorithm for the Fast Messages Communication Library.- High Performance Sockets and RPC over Virtual Interface (VI) Architecture.- The Scheduled Transfer (ST) Protocol.- The NIP Parallel Object-Oriented Computational Model.- The Aleph Toolkit: Support for Scalable Distributed Shared Objects.- Combining Adaptive and Deterministic Routing: Evaluation of a Hybrid Router.- Deadlock-Free Routing in Irregular Networks with Dynamic Reconfiguration.- Implementing Application-Specific Cache-Coherence Protocols in Configurable Hardware.- Supporting Shared Memory and Message Passing on Clusters of PCs with a SMiLE.- Low Latency Message-Passing for Reflective Memory Networks.
Literaturangaben