Wed 15 Jun 2016 15:30 - 16:00 at Grand Ballroom San Rafael - Parsing & Compilation Chair(s): Michelle Strout

Efficient memory allocation is crucial for data-intensive applications as a smaller memory footprint ensures better cache performance and allows one to run a larger problem size given a fixed amount of main memory. In this paper, we describe a new automatic storage optimization technique to minimize the dimensionality and storage requirements of arrays used in sequences of loop nests with a pre-determined schedule. We formulate the problem of intra-array storage optimization as one of finding the right storage partitioning hyperplanes: each storage partition corresponds to a single storage location. Our heuristic is driven by a dual objective function that minimizes both, the dimensionality of the mapping and the extents along those dimensions. The technique is dimension optimal for most codes encountered in practice. The storage requirements of the mappings obtained also are asymptotically better than those obtained by any existing schedule-dependent technique. Storage reduction factors and other results we report from an implementation of our technique demonstrate its effectiveness on several real-world examples drawn from the domains of image processing, stencil computations, high-performance computing, and the class of tiled codes in general.

Wed 15 Jun

Displayed time zone: Tijuana, Baja California change

15:30 - 17:00
Parsing & CompilationResearch Papers at Grand Ballroom San Rafael
Chair(s): Michelle Strout The University of Arizona
15:30
30m
Talk
Automatic Storage Optimization for Arrays [TOPLAS]
Research Papers
Somashekaracharya G Bhaskaracharya Indian Institute of Science and National Instruments, Uday Bondhugula Indian Institute of Science, Albert Cohen INRIA
Media Attached
16:00
30m
Talk
Polyhedral AST generation is more than scanning polyhedra [TOPLAS]
Research Papers
Tobias Grosser ETH Zurich, Switzerland, Sven Verdoolaege , Albert Cohen INRIA
Media Attached
16:30
30m
Talk
On the Complexity and Performance of Parsing with Derivatives
Research Papers
Michael D. Adams University of Utah, Celeste Hollenbeck University of Utah, Matthew Might University of Utah, USA
Pre-print Media Attached