Graph Partitioning with Acyclicity Constraints
This addresses a specific constraint in mapping computer vision and imaging applications to heterogeneous embedded multiprocessors, which is incremental as it builds on existing graph partitioning problems by adding acyclicity requirements.
The paper tackles the NP-complete problem of graph partitioning with acyclicity constraints for heterogeneous embedded multiprocessors, showing it is NP-complete and presenting heuristics that achieve close approximations to optimal solutions for small instances and better scalability for larger ones, with a real imaging application demonstrating improved communication volume and execution time.
Graphs are widely used to model execution dependencies in applications. In particular, the NP-complete problem of partitioning a graph under constraints receives enormous attention by researchers because of its applicability in multiprocessor scheduling. We identified the additional constraint of acyclic dependencies between blocks when mapping computer vision and imaging applications to a heterogeneous embedded multiprocessor. Existing algorithms and heuristics do not address this requirement and deliver results that are not applicable for our use-case. In this work, we show that this more constrained version of the graph partitioning problem is NP-complete and present heuristics that achieve a close approximation of the optimal solution found by an exhaustive search for small problem instances and much better scalability for larger instances. In addition, we can show a positive impact on the schedule of a real imaging application that improves communication volume and execution time.