An approach for code generation in the Sparse Polyhedral Framework

Applications that manipulate sparse data structures contain memory reference patterns that are unknown at compile time due to indirect accesses such as A[B[i]]. To exploit parallelism and improve locality in such applications, prior work has developed a number of Run-Time Reordering Transformations (RTRTs). This paper presents the Sparse Polyhedral Framework (SPF) for specifying RTRTs and compositions thereof and algorithms for automatically generating efficient inspector and executor code to implement such transformations. Experimental results indicate that the performance of automatically generated inspectors and executors competes with the performance of hand-written ones when further optimization is done.We thank Jon Roelofs for his implementation of the IEGenCC tool, which converts C programs into the specification format IEGen expects as input. We thank Christopher Krieger, Andrew Stone, Tomofumi Yuki, and anonymous reviewers for their careful reading and suggestions. This work was sponsored by NSF CAREER Grant CCF-0746693, DOE Early Career Grant DE-SC3956, the CSCAPES Institute DOE Grant 7F-00323, and the CACHE project DOE Grant DE-SC04030.Available online 4 March 2016. 24 month embargo.This item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu