Towards an architecture-independent analysis of parallel algorithms
SIAM Journal on Computing
LogP: towards a realistic model of parallel computation
PPOPP '93 Proceedings of the fourth ACM SIGPLAN symposium on Principles and practice of parallel programming
Proceedings of the seventh annual ACM symposium on Parallel algorithms and architectures
Task Clustering and Scheduling for Distributed Memory Parallel Architectures
IEEE Transactions on Parallel and Distributed Systems
Effects of communication latency, overhead, and bandwidth in a cluster architecture
Proceedings of the 24th annual international symposium on Computer architecture
A versatile cost modelling approach for multicomputer task scheduling
Parallel Computing - Special issue on task scheduling problems for parallel and distributed systems
Scheduling balanced task-graphs to LogP-machines
Parallel Computing - Special issue on new trends on scheduling in parallel and distributed systems
List scheduling of general task graphs under LogP
Parallel Computing - Special issue on new trends on scheduling in parallel and distributed systems
DSC: Scheduling Parallel Tasks on an Unbounded Number of Processors
IEEE Transactions on Parallel and Distributed Systems
On the Design of Clustering-based Scheduling Algorithms for Realistic Machine Models
IPDPS '01 Proceedings of the 15th International Parallel & Distributed Processing Symposium
Static Scheduling Using Task Replication for LogP and BSP Models
Euro-Par '98 Proceedings of the 4th International Euro-Par Conference on Parallel Processing
Scheduling Arbitrary Task Graphs on LogP Machines
Euro-Par '99 Proceedings of the 5th International Euro-Par Conference on Parallel Processing
Realistic Communication Model for Parallel Computing on Cluster
IWCC '99 Proceedings of the 1st IEEE Computer Society International Workshop on Cluster Computing
| Hi-index | 0.00 |
This paper briefly describes the mechanisms used to reduce the number of processors required by a class of task replication-based scheduling heuristics for the LogP model. These heuristics, which are based on the task clustering algorithm design methodology [3], are known to generate schedules with good makespans [3,5]. Results in this paper show that a significant reduction, on average, in the number of processors required can be obtained without degrading the makespan. These mechanisms can also be used to tradeoff quality in terms of an increase in the makespan for quantity in terms of a further reduction in the number of processors required.