DMCA
CloudCache: Expanding and Shrinking Private Caches
| Citations: | 10 - 0 self |
BibTeX
@MISC{Lee_cloudcache:expanding,
author = {Hyunjin Lee and Sangyeun Cho and Bruce R. Childers},
title = {CloudCache: Expanding and Shrinking Private Caches},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The number of cores in a single chip multiprocessor is expected to grow in coming years. Likewise, aggregate on-chip cache capacity is increasing fast and its effective utilization is becoming ever more important. Furthermore, available cores are expected to be underutilized due to the power wall and highly heterogeneous future workloads. This trend makes existing L2 cache management techniques less effective for two problems: increased capacity interference between working cores and longer L2 access latency. We propose a novel scalable cache management framework called CloudCache that creates dynamically expanding and shrinking L2 caches for working threads with fine-grained hardware monitoring and control. The key architectural components of CloudCache are L2 cache chaining, inter- and intra-bank cache partitioning, and a performance-optimized coherence protocol. Our extensive experimental evaluation demonstrates that CloudCache significantly improves performance of a wide range of workloads when all or a subset of cores are occupied. 1.
Keyphrases
private cache available core capacity interference aggregate on-chip cache capacity single chip multiprocessor effective utilization l2 access latency l2 cache chaining heterogeneous future workload novel scalable cache management framework l2 cache management technique power wall key architectural component coming year wide range performance-optimized coherence protocol fine-grained hardware monitoring intra-bank cache partitioning extensive experimental evaluation l2 cache
