List Scheduling Algorithm for Heterogeneous Systems by an Optimistic Cost Table
Universidade do Porto · Intel (United States)
Abstract
Efficient application scheduling algorithms are important for obtaining high performance in heterogeneous computing systems. In this paper, we present a novel list-based scheduling algorithm called Predict Earliest Finish Time (PEFT) for heterogeneous computing systems. The algorithm has the same time complexity as the state-of-the-art algorithm for the same purpose, that is, O(v2.p) for v tasks and p processors, but offers significant makespan improvements by introducing a look-ahead feature without increasing the time complexity associated with computation of an optimistic cost table (OCT). The calculated value is an optimistic cost because processor availability is not considered in the computation. Our…
Citation impact
- FWCI
- 43.90
- Percentile
- 100%
- References
- 30
Authors
2Topics & keywords
- Computer science
- Scheduling (production processes)
- Computation
- Algorithm
- Schedule
- Job shop scheduling
- Dynamic priority scheduling
- Parallel computing