Effective padding of multidimensional arrays to avoid cache conflict misses - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2016

Effective padding of multidimensional arrays to avoid cache conflict misses

Abstract

Caches are used to significantly improve performance. Even with high degrees of set associativity, the number of accessed data elements mapping to the same set in a cache can easily exceed the degree of associativity. This can cause conflict misses and lower performance, even if the working set is much smaller than cache capacity. Array padding (increasing the size of array dimensions) is a well-known optimization technique that can reduce conflict misses. In this paper, we develop the first algorithms for optimal padding of arrays aimed at a set-associative cache for arbitrary tile sizes. In addition, we develop the first solution to padding for nested tiles and multi-level caches. Experimental results with multiple benchmarks demonstrate a significant performance improvement from padding.
No file

Dates and versions

hal-01335346 , version 1 (21-06-2016)

Identifiers

  • HAL Id : hal-01335346 , version 1

Cite

Changwan Hong, Wenlei Bao, Albert Cohen, Sriram Krishnamoorthy, Louis-Noël Pouchet, et al.. Effective padding of multidimensional arrays to avoid cache conflict misses. PLDI 2016: Proceedings of the 37th ACM SIGPLAN Conference on Programming Language Design and Implementation, Jun 2016, Santa Barbara, United States. ⟨hal-01335346⟩
314 View
0 Download

Share

More