Non-affine Extensions to Polyhedral Code Generation

  • Authors:

  • Anand Venkat;Manu Shantharam;Mary Hall;Michelle Mills Strout

  • Affiliations:

  • University of Utah Salt Lake City, Utah;University of Utah Salt Lake City, Utah;University of Utah Salt Lake City, Utah;Colorado State University Fort Collins, Colorado

  • Venue:
  • Proceedings of Annual IEEE/ACM International Symposium on Code Generation and Optimization
  • Year:
  • 2014

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper describes a loop transformation framework that extends a polyhedral representation of loop nests to represent and transform computations with non-affine index arrays in loop bounds and subscripts via a new interface between compile-time and run-time abstractions. Polyhedra scanning code generation, which historically applies an affine mapping to the subscript expressions of the statements in a loop nest, is modified to apply non-affine mappings involving index arrays that are represented at compile time by uninterpreted functions; non-affine loop bounds involving index arrays are also represented. When appropriate, an inspector is utilized to capture the non-affine subscript mappings, and a generalized loop coalescing transformation is introduced as a non-affine transformation to support non-affine loop bounds. With this support, complex sequences of new and existing transformations can then be composed. We demonstrate the effectiveness of this framework by optimizing sparse matrix vector multiplication operations targeting GPUs for different matrix structures and parallelization strategies. This approach achieves performance that is comparable to or greater than the hand-tuned CUSP library; for two of the implementations it achieves an average 1.14× improvement over CUSP across a collection of sparse matrices, while the third performs on average within 8% of CUSP.