Skip to Main content Skip to Navigation
Reports

A New Case for Skewed-Associativity

André Seznec 1
1 CAPS - Compilation, parallel architectures and system
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Skewed-associative caches have been shown to statisticaly exhibit lower miss ratios than set-associative caches at equal associativity degrees. But for L1 caches, the performance of a four-way set-associative cache is known to be quite close to that of a 16-way set-associative cache. In this paper, we first show that BTBs and L2 caches featuring long line size may benefit a lot from a high associativity degree on set-associative caches and a LRU replacement policy. Skewed-associative caches with an hypothetic LRU replacement policy «provide» this high associativity but with a low number of cache banks. Unfortunately, LRU replacement policies can not be easily implemented in hardware on skewed-associative caches. We propose some new replacement heuristics for skewed-associative caches. Those heuristics exhibit slightly worse behavior than a full LRU replacement policy, but still allow a 2-way skewed-associative cache to outperform a 4-way LRU set-associative cache and a 4-way skewed-associative cache to outperform a 16-way LRU set-associative cache. Therefore skewed-associativity allows significant miss reduction on BTBs and L2 caches.
Document type :
Reports
Complete list of metadata

https://hal.inria.fr/inria-00073481
Contributor : Rapport de Recherche Inria <>
Submitted on : Wednesday, May 24, 2006 - 12:58:16 PM
Last modification on : Thursday, January 7, 2021 - 4:29:04 PM
Long-term archiving on: : Sunday, April 4, 2010 - 11:47:49 PM

Identifiers

  • HAL Id : inria-00073481, version 1

Citation

André Seznec. A New Case for Skewed-Associativity. [Research Report] RR-3208, INRIA. 1997. ⟨inria-00073481⟩

Share

Metrics

Record views

400

Files downloads

745