Energy-efficient cache partitioning for future CMPs

Authors:
Karthik T. Sundararajan;Timothy M. Jones;Nigel P. Topham
Affiliations:
University of Edinburgh, Edinburgh, United Kingdom;University of Cambridge, Cambridge, United Kingdom;University of Edinburgh, Edinburgh, United Kingdom
Venue:
Proceedings of the 21st international conference on Parallel architectures and compilation techniques
Year:
2012

Citing 6
Cited 0

Dynamic Partitioning of Shared Cache Memory

The Journal of Supercomputing
Utility-Based Cache Partitioning: A Low-Overhead, High-Performance, Runtime Mechanism to Partition Shared Caches

Proceedings of the 39th Annual IEEE/ACM International Symposium on Microarchitecture
PIPP: promotion/insertion pseudo-partitioning of multi-core shared caches

Proceedings of the 36th annual international symposium on Computer architecture
High performance cache replacement using re-reference interval prediction (RRIP)

Proceedings of the 37th annual international symposium on Computer architecture
The gem5 simulator

ACM SIGARCH Computer Architecture News
Benchmarking modern multiprocessors

Benchmarking modern multiprocessors

Quantified Score

Hi-index	0.00

Visualization

Abstract

The demand for high performance computing systems requires processor vendors to increase the number of cores per chip multiprocessor (CMP). However, as their number grows, the core-to-way ratio in the last level cache (LLC) increases, presenting problems to existing cache partitioning techniques which require more ways than cores. Further, effective energy management of the LLC becomes increasingly important due to its size. In this paper we propose an LLC energy-saving scheme for high-performance, many-core processors. It partitions the data within the cache into shared and private regions. Applications only access the ways containing the type of data that they require, realising dynamic energy savings. Any ways that are not within the shared or private regions can be turned off to save static energy.