Service-based Grid infrastructures emphasize service composition rather than sharing of low level resources. The idea is to build Grid applications out of computational services p...
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...
We have built an eight node SMP cluster called COMPaS (Cluster Of Multi-Processor Systems), each node of which is a quadprocessor Pentium Pro PC. We have designed and implemented a...
The dual-cube is a newly proposed topology for interconnection networks, which uses low dimensional hypercubes as building blocks. The primary advantages of the dual-cube over the...
Sparse matrix-vector multiplication forms the heart of iterative linear solvers used widely in scientific computations (e.g., finite element methods). In such solvers, the matrix-v...