Name
Abstract | ||
|---|---|---|
Caches have become increasingly important with the widening gap between main memory and processor speeds. Small and fast cache memories are designed to bridge this discrepancy. However, they are only effective when programs exhibit sufficient data locality.The performance of the memory hierarchy can be improved by means of data and loop transformations. Tiling is a loop transformation that aims at reducing capacity misses by shortening the reuse distance. Padding is a data layout transformation targeted to reduce conflict misses.This article presents an accurate cost model that describes misses across different hierarchy levels and considers the effects of other hardware components such as branch predictors. The cost model drives the application of tiling and padding transformations. We combine the cost model with a genetic algorithm to compute the tile and pad factors that enhance the program performance.To validate our strategy, we ran experiments for a set of benchmarks on a large set of modern architectures. Our results show that this scheme is useful to optimize programs' performance. When compared to previous approaches, we observe that with a reasonable compile-time overhead, our approach gives significant performance improvements for all studied kernels on all architectures. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1145/1086642.1086646 | ACM Trans. Program. Lang. Syst. |
Keywords | Field | DocType |
program performance,cache memory,locality transformation,genetic algorithms,large set,significant performance improvement,cost model,padding,loop transformation,sufficient data locality,guiding data,accurate cost model,tiling,cache memories,different hierarchy level,data layout transformation,genetic algorithm | Locality,Memory hierarchy,Programming language,Computer science,Cache,Reuse,CPU cache,Parallel computing,Optimizing compiler,Theoretical computer science,Padding,Genetic algorithm | Journal |
Volume | Issue | ISSN |
27 | 5 | 0164-0925 |
Citations | PageRank | References |
3 | 0.41 | 22 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xavier Vera | 1 | 552 | 30.31 |
| Jaume Abella | 2 | 1046 | 76.34 |
| Josep Llosa | 3 | 574 | 39.30 |
| Antonio González | 4 | 3178 | 229.66 |