Sciweavers

Share
ICPP
2000
IEEE

Partitioning Loops with Variable Dependence Distances

8 years 7 months ago
Partitioning Loops with Variable Dependence Distances
A new technique to parallelize loops with variable distance vectors is presented. The method extends previous methods in two ways. First, the present method makes it possible for array subscripts to be any linear combination of all loop indices. The solutions to the linear dependence equations established from such array subscripts are characterized by a pseudo distance matrix(PDM). Second, it allows us to exploit loop parallelism from the PDM by applying unimodular and partitioning transformations that preserve the lexicographical order of the dependent iterations. The algorithms to derive the PDM, to find a suitable loop transformation and to generate parallel code are described, showing that it is possible to parallelize a wider range of loops automatically. Keywords loop parallelization, dependence equation, distance vector, pseudo distance matrix, unimodular transformation, iteration space partitioning1
Yijun Yu, Erik H. D'Hollander
Added 31 Jul 2010
Updated 31 Jul 2010
Type Conference
Year 2000
Where ICPP
Authors Yijun Yu, Erik H. D'Hollander
Comments (0)
books