Introduction to algorithms
Approximate algorithms scheduling parallelizable tasks
SPAA '92 Proceedings of the fourth annual ACM symposium on Parallel algorithms and architectures
Modeling the benefits of mixed data and task parallelism
Proceedings of the seventh annual ACM symposium on Parallel algorithms and architectures
Compiler support for task scheduling in hierarchical execution models
Journal of Systems Architecture: the EUROMICRO Journal - Special issue on tools and environments for parallel program development
Scheduling malleable and nonmalleable parallel tasks
SODA '94 Proceedings of the fifth annual ACM-SIAM symposium on Discrete algorithms
Performance-Effective and Low-Complexity Task Scheduling for Heterogeneous Computing
IEEE Transactions on Parallel and Distributed Systems
A Low-Cost Approach towards Mixed Task and Data Parallel Scheduling
ICPP '02 Proceedings of the 2001 International Conference on Parallel Processing
Scheduling Distributed Applications: the SimGrid Simulation Framework
CCGRID '03 Proceedings of the 3st International Symposium on Cluster Computing and the Grid
Simultaneous exploitation of task and data parallelism in regular scientific applications
Simultaneous exploitation of task and data parallelism in regular scientific applications
Critical Path and Area Based Scheduling of Parallel Task Graphs on Heterogeneous Platforms
ICPADS '06 Proceedings of the 12th International Conference on Parallel and Distributed Systems - Volume 1
A Comparison of Scheduling Approaches for Mixed-Parallel Applications on Heterogeneous Platforms
ISPDC '07 Proceedings of the Sixth International Symposium on Parallel and Distributed Computing
Validity of the single processor approach to achieving large scale computing capabilities
AFIPS '67 (Spring) Proceedings of the April 18-20, 1967, spring joint computer conference
CCGRID '10 Proceedings of the 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing
Hi-index | 0.00 |
Mixed-parallel applications can take advantage of large-scale computing platforms but scheduling them efficiently on such platforms is challenging. When relying on classic listscheduling algorithms, the issue of independent and selfish task allocation determination may arise. Indeed the allocation of the most critical task may lead to poor allocations for subsequent tasks. In this paper we propose a new mixed-parallel scheduling heuristic that takes into account that several tasks may have almost the same level of criticality during the allocation process. We then perform a comparison of this heuristic with other algorithms in simulation over a wide range of application and on platform conditions. We find that our heuristic achieves better performance in terms of schedule length, speedup and degradation from best.