A bridging model for parallel computation
Communications of the ACM
LogP: a practical model of parallel computation
Communications of the ACM
Truly efficient parallel algorithms: 1-optimal multisearch for an extension of the BSP model
ESA '95 Selected papers from the third European symposium on Algorithms
BSPlib: The BSP programming library
Parallel Computing
Portable and Efficient Parallel Computing Using the BSP Model
IEEE Transactions on Computers
The Paderborn University BSP (PUB) Library - Design, Implementation and Performance
IPPS '99/SPDP '99 Proceedings of the 13th International Symposium on Parallel Processing and the 10th Symposium on Parallel and Distributed Processing
Communication Efficient Parallel Searching
IRREGULAR '97 Proceedings of the 4th International Symposium on Solving Irregularly Structured Problems in Parallel
Submachine Locality in the Bulk Synchronous Setting (Extended Abstract)
Euro-Par '96 Proceedings of the Second International Euro-Par Conference on Parallel Processing-Volume II
Algorithm engineering for parallel computation
Experimental algorithmics
Algorithms for memory hierarchies: advanced lectures
Algorithms for memory hierarchies: advanced lectures
| Hi-index | 0.00 |
The aim of this paper is to demonstrate the impact of features of parallel computation models on the design of efficient parallel algorithms. For this purpose, we start with consideringValiant's BSP model and design an optimal multisearch algorithm. For a realistic extension of this model which takes the critical blocksize into account, namely the BSP* model due to B盲umker, Dittrich, and Meyer auf der Heide, this algorithm is far from optimal.We show how the critical blocksize can be taken into account by presenting a modified multisearch algorithm which is optimal in the BSP* model. Similarly, we consider the D-BSP model due to de la Torre and Kruskal which extends BSP by introducing a way to measure locality of communication. Its influence on algorithm design is demonstrated by considering the broadcast problem. Finally, we explain how our Paderborn University BSP (PUB) Library incorporates such BSP extensions.