Thread-level speculation is a technique that enables parallel execution of sequential applications on a multiprocessor. This paper describes the complete implementation of the sup...
: The distributed recovery block (DRB) scheme is a widely applicable approach for realizing both hardware and software fault tolerance in real-time distributed and parallel compute...
The Reusable Software Fault Tolerance Testbed ReSoFT was developed to facilitate the development and evaluation of high-assurance systems that require tolerance of both hardware...
Kam S. Tso, Eltefaat Shokri, Roger J. Dziegiel Jr.
We report the performance of NOW-Sort, a collection of sorting implementations on a Network of Workstations (NOW). We find that parallel sorting on a NOW is competitive to sortin...
Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau,...
The current multiprocessors such asCray T3D support interprocessor communication using partitioned dimension-order routers (PDRs). In a PDR implementation, the routing logic and sw...