Write a Blog >>
Thu 21 Jan 2016 16:55 - 17:20 at Grand Bay North - Track 1: Optimization Chair(s): Mayur Naik

High-level compiler transformations, especially loop transformations, are widely recognized as critical optimizations to restructure programs to improve data locality and expose parallelism. Guaranteeing the correctness of program transformations is essential, and to date three main approaches have been developed: proof of equivalence of affine programs, matching the execution traces of programs, and checking bit-by-bit equivalence of the outputs of the programs. Each technique suffers from limitations in either the kind of transformations supported, space complexity, or the sensitivity to the testing dataset. In this paper, we take a novel approach addressing all three limitations to provide an automatic bug checker to verify any iteration reordering transformations on affine programs, including non-affine transformations, with space consumption proportional to the original program data, and robust to arbitrary datasets of a given size. We achieve this by exploiting the structure of affine program control- and data-flow to generate at compile-time lightweight checker code to be executed within the transformed program. Experimental results assess the correctness and effectiveness of our method, and its increased coverage over previous approaches.

Thu 21 Jan

POPL-2016-papers
16:30 - 17:45: Research Papers - Track 1: Optimization at Grand Bay North
Chair(s): Mayur NaikGeorgia Tech
POPL-2016-papers16:30 - 16:55
Talk
Somashekaracharya G BhaskaracharyaIndian Institute of Science and National Instruments, Uday BondhugulaIndian Institute of Science, Albert CohenINRIA
Media Attached File Attached
POPL-2016-papers16:55 - 17:20
Talk
Wenlei Bao, Sriram KrishnamoorthyPacific Northwest National Laboratories, Louis-Noel PouchetOhio State University, Fabrice RastelloINRIA, France, P. SadayappanOhio State University
Media Attached
POPL-2016-papers17:20 - 17:45
Talk
Marc AndryscoUniversity of California, San Diego, Ranjit JhalaUniversity of California, San Diego, Sorin LernerUniversity of California, San Diego
Media Attached