Runtime incremental parallel scheduling (RIPS) for large-scale parallel computers
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 456-463
- https://doi.org/10.1109/fmpc.1995.380479
Abstract
Runtime incremental parallel scheduling (RIPS) is an alternative strategy to the commonly used dynamic scheduling. In this scheduling strategy, the system scheduling activity alternates with the underlying computation work. RIPS utilizes advanced parallel scheduling techniques to produce a low-overhead, high-quality load balancing and adapts to applications of nonuniform structures.Keywords
This publication has 11 references indexed in Scilit:
- Parallax: a tool for parallel program schedulingIEEE Parallel & Distributed Technology: Systems & Applications, 1993
- Strategies for dynamic load balancing on highly parallel computersIEEE Transactions on Parallel and Distributed Systems, 1993
- Load distributing for locally distributed systemsComputer, 1992
- PYRROSPublished by Association for Computing Machinery (ACM) ,1992
- Molecular dynamics simulation of superoxide interacting with superoxide dismutaseChemical Physics, 1991
- Execution time support for adaptive scientific algorithms on distributed memory machinesConcurrency: Practice and Experience, 1991
- Hypertool: a programming aid for message-passing systemsIEEE Transactions on Parallel and Distributed Systems, 1990
- Dynamic load balancing for distributed memory multiprocessorsJournal of Parallel and Distributed Computing, 1989
- A Partitioning Strategy for Nonuniform Problems on MultiprocessorsIEEE Transactions on Computers, 1987
- A comparison of receiver-initiated and sender-initiated adaptive load sharingPerformance Evaluation, 1986