Dependence-free clustering of shift-invariant data structures
Dependence-free clustering of data structures can be regarded as a general form of alignment and addresses the problem of finding the maximum amount of independent computation on non-connected data sets. The paper presents a unified concept for modelling both data spaces and affine dependence relations with the help of Abelian subgroups of Zn. This approach allows us to treat alignment at a very high level of abstraction exploiting results of computational algebra.
Unable to display preview. Download preview PDF.
- 1.M. Besch, H. W. Pohl: Communication-Driven Alignment of Sparse Data Structures-An Approach Towards Algebraic Mapping, RWCP Technical Report TR-96014, Japan, http://www.first.gmd.de/promoter/papers/, 1996Google Scholar
- 2.M. Besch, H. W. Pohl: Dependence-Free Structured Decomposition of Group-Based Index Spaces, RWCP Technical Report, Japan, http://www.first.gmd.de/promoter/papers/, 1996Google Scholar
- 3.M. Besch, H. W. Pohl: On Using Group-Based Structures for Modelling and Mapping Data Parallel Programs, Proc. Conf. on Parallel and Distributed Computing and Systems (PDCS'97), Washington, D.C., U.S.A., October 1997Google Scholar
- 4.H. Cohen: A Course in Computational Algebraic Number Theory, Graduate Texts in Mathematics, Springer, 1993Google Scholar
- 5.P. Feautrier: Parametric Integer Programming, Recherche operationelle / Operations Research, vol. 22, no. 3, 1988Google Scholar