A Comparison of Compiler Tiling Algorithms [chapter]

Gabriel Rivera, Chau-Wen Tseng
1999 Lecture Notes in Computer Science  
Linear algebra codes contain data locality which can be exploited by tiling multiple loop nests. Several approaches to tiling have been suggested for avoiding con ict misses in low associativity caches. We propose a new technique based on intra-variable padding and compare its performance with existing techniques. Results show padding improves performance of matrix multiply by over 100% in some cases over a range of matrix sizes. Comparing the e cacy of di erent tiling algorithms, we discover
more » ... ctangular tiles are slightly more e cient than square tiles. Overall, tiling improves performance from 0-250%. Copying tiles at run time proves to be quite e ective.
doi:10.1007/978-3-540-49051-7_12 fatcat:cne6thlra5bk5damoozthrx7pu