A hypercube algorithm for the 0/1 knapsack problem
Journal of Parallel and Distributed Computing
POPL '88 Proceedings of the 15th ACM SIGPLAN-SIGACT symposium on Principles of programming languages
Tiling multidimensional iteration spaces for nonshared memory machines
Proceedings of the 1991 ACM/IEEE conference on Supercomputing
Integration, the VLSI Journal
Optimal orthogonal tiling of 2-D iterations
Journal of Parallel and Distributed Computing
Knapsack on VLSI: from Algorithm to Optimal Circuit
IEEE Transactions on Parallel and Distributed Systems
Tiling and Processors Allocation for Three Dimensional Iteration Space
HiPC '99 Proceedings of the 6th International Conference on High Performance Computing
Hi-index | 0.06 |
In this paper we present an efficient parallelization of the dynamicpro gramming applied to bi-knapsack problem, in distributed memory machines(MMD). Our approach develops the tiling technique in order to control the grain parallelism and find the optimal granularity. Our proposed approach has been intensively validated on the Intel Paragon and IBM/SP2 using NX and MPI libraries. The experimental results show a linear acceleration, which enables to solve huge instances of the hardest known 0/1 bi-knapsack problems in a very reasonable time.