An Integrated Approach to Locality-Conscious Processor Allocation and Scheduling of Mixed-Parallel Applications
Complex parallel applications can often be modeled as directed acyclic graphs of coarse-grained application-tasks with dependences. These applications exhibit both task- and data-parallelism, and combining these two (also called mixedparallelism), has been shown to be an effective model for their execution. In this paper, we present an algorithm to compute the appropriate mix of task- and data-parallelism required to minimize the parallel completion time (makespan) of these applications. In other words, our algorithm determines the set of tasks that should be run concurrently and the number of processors to be allocated to each task. The processor allocation and scheduling decisions are made in an integrated manner and are based on several factors such as the structure of the taskgraph, the runtime estimates and scalability characteristics of the tasks and the inter-task data communication volumes. A locality conscious scheduling strategy is used to improve inter-task data reuse. Evaluation through simulations and actual executions of task graphs derived from real applications as well as synthetic graphs shows that our algorithm consistently generates schedules with lower makespan as compared to CPR and CPA, two previously proposed scheduling algorithms. Our algorithm also produces schedules that have lower makespan than pure taskand data-parallel schedules. For task graphs with known optimal schedules or lower bounds on the makespan, our algorithm generates schedules that are closer to the optima than other scheduling approaches.
- Research Organization:
- Pacific Northwest National Laboratory (PNNL), Richland, WA (US)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-76RL01830
- OSTI ID:
- 964230
- Report Number(s):
- PNNL-SA-62411; KJ0402000
- Journal Information:
- IEEE Transactions on Parallel and Distributed Systems, 20(8):1158-1172, Journal Name: IEEE Transactions on Parallel and Distributed Systems, 20(8):1158-1172 Journal Issue: 8 Vol. 20
- Country of Publication:
- United States
- Language:
- English
Similar Records
Processor allocation for horizontal and vertical parallelism and related speedup bounds
Deadlock prevention in processor self-scheduling for parallel nested loops