Loop transformations: Convexity, pruning and optimization
Document Type
Conference Proceeding
Publication Date
1-1-2011
Abstract
High-level loop transformations are a key instrument in mapping computational kernels to effectively exploit resources in modern processor architectures. However, determining appropriate compositions of loop transformations to achieve this remains a significantly challenging task; current compilers may achieve significantly lower performance than hand-optimized programs. To address this fundamental challenge, we first present a convex characterization of all distinct, semantics-preserving, multidimensional affine transformations. We then bring together algebraic, algorithmic, and performance analysis results to design a tractable optimization algorithm over this highly expressive space. The framework has been implemented and validated experimentally on a representative set of benchmarks run on state-of-the-art multi-core platforms. Copyright © 2011 ACM.
Publication Source (Journal or Book title)
ACM SIGPLAN Notices
First Page
549
Last Page
561
Recommended Citation
Pouchet, L., Bondhugula, U., Bastoul, C., Cohen, A., Ramanujam, J., Sadayappan, P., & Vasilache, N. (2011). Loop transformations: Convexity, pruning and optimization. ACM SIGPLAN Notices, 46 (1), 549-561. https://doi.org/10.1145/1925844.1926449