The Power Test for Data Dependence
IEEE Transactions on Parallel and Distributed Systems
Dependence Uniformization: A Loop Parallelization Technique
IEEE Transactions on Parallel and Distributed Systems
A Loop Parallelization Method for Nested Loops with Non-uniform Dependences
ICPADS '97 Proceedings of the 1997 International Conference on Parallel and Distributed Systems
(R) Unique Sets Oriented Partitioning of Nested Loops with Non-Uniform Dependences
ICPP '96 Proceedings of the Proceedings of the 1996 International Conference on Parallel Processing - Volume 3
Parallel Region Execution of Loops with Irregular Dependencies
ICPP '94 Proceedings of the 1994 International Conference on Parallel Processing - Volume 02
Minimum dependence distance tiling of nested loops with non-uniform dependences
SPDP '94 Proceedings of the 1994 6th IEEE Symposium on Parallel and Distributed Processing
| Hi-index | 0.00 |
The existing parallelizing compilers can parallelize most of the loops with uniform dependences, but they do not satisfactorily handle loops with non-uniform dependences. Most of the time, the compiler leaves such loops running sequentially. Unfortunately, loops with non-uniform dependences are not so uncommon in the real world. This paper presents the two parallel region partitioning method of nested loops with non-uniform dependences for maximizing parallelism. By parallelizing anti dependence region using variable re-naming, we will divide the iteration space into two parallel regions by a line in case that FDT (Flow Dependence Tail set) does not overlap FDH (Flow Dependence Head set). Comparison with some related works shows more parallelism than other existing methods.