Date: 26 Jul 2002

A Comparison of Locality Transformations for Irregular Codes

* Final gross prices may vary according to local VAT.

Get Access


Researchers have proposed several data and computation transformations to improve locality in irregular scientific codes. We ex- perimentally compare their performance and present gpart, a new tech- nique based on hierarchical clustering. Quality partitions are constructed quickly by clustering multiple neighboring nodes with priority on nodes with high degree, and repeating a few passes. Overhead is kept low by clustering multiple nodes in each pass and considering only edges between partitions. Experimental results show gpart matches the performance of more sophisticated partitioning algorithms to with 6%-8%, with a small fraction of the overhead. It is thus useful for optimizing programs whose running times are not known. This research was supported in part by NSF CAREER Development Award

#ASC9625531 in New Technologies, NSF CISE Institutional Infrastructure Award #CDA9401151, and NSF cooperative agreement ACI-9619020 with NPACI and NCSA.