Minimum-cost spanning tree as a path-finding problem
Information Processing Letters
Efficient parallel algorithms
A bridging model for parallel computation
Communications of the ACM
Introduction to parallel algorithms and architectures: array, trees, hypercubes
Introduction to parallel algorithms and architectures: array, trees, hypercubes
A new approach for automatic parallelization of blocked linear Algebra computations
Proceedings of the 1991 ACM/IEEE conference on Supercomputing
The Design and Analysis of Computer Algorithms
The Design and Analysis of Computer Algorithms
All-Pairs Shortest Paths Computation in the BSP Model
ICALP '01 Proceedings of the 28th International Colloquium on Automata, Languages and Programming,
On the PVM Computations of Transitive Closure and Algebraic Path Problems
Proceedings of the 5th European PVM/MPI Users' Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface
Hi-index | 0.00 |
We investigate experimentally a dependency graph approach to the distributed parallel computation of the generic transitive closure problem. A parallel coarse-grained algorithm is derived from a fine-grained algorithm. Its advantage is that approximately half of the work is organised as totally independent computation sequences of several processes. We consider conceptual description of dependencies between operations as partial order graphs of events. Such graphs can be split into disjoint subgraphs corresponding to different phases of the computation. This approach helps to design a parallel algorithm in a way which guarantees large independence of actions. We also show that a transformation of the fine-grained algorithm into the coarse-grained is rather nontrivial, and that the straightforward approach does not work.