Load balancing is an important consideration when running data-parallel programs. While traditional techniques trade off the cost of load imbalance with the overhead of mitigating...
Passing messages through shared memory plays an important role on symmetric multiprocessors and on Clumps. The management of concurrent access to message queues is an important as...
This paper describes PI/OT, a template-based parallel I/O system. In PI/OT, I/O streams have annotations associated with them that are external to the source code. These annotatio...
Ian Parsons, Jonathan Schaeffer, Duane Szafron, Ro...
Code duplication is considered as bad practice that complicates the maintenance and evolution of software. Detecting duplicated code is a difficult task because of the large amoun...
Improving memory performance at software level is more effective in reducing the rapidly expanding gap between processor and memory performance. Loop transformations (e.g. loop un...
Surendra Byna, Xian-He Sun, William Gropp, Rajeev ...