The Coherence Predictor Cache: A Resource-Efficient and Accurate Coherence Prediction Infrastructure

Authors:
Jim Nilsson;Anders Landin;Per Stenström
Affiliations:
-;-;-
Venue:
IPDPS '03 Proceedings of the 17th International Symposium on Parallel and Distributed Processing
Year:
2003

Citing 0
Cited 8

RegionScout: Exploiting Coarse Grain Sharing in Snoop-Based Coherence

Proceedings of the 32nd annual international symposium on Computer Architecture
Aggressive snoop reduction for synchronized producer-consumer communication in energy-efficient embedded multi-processors

CODES+ISSS '07 Proceedings of the 5th IEEE/ACM international conference on Hardware/software codesign and system synthesis
Application-aware snoop filtering for low-power cache coherence in embedded multiprocessors

ACM Transactions on Design Automation of Electronic Systems (TODAES)
Using supplier locality in power-aware interconnects and caches in chip multiprocessors

Journal of Systems Architecture: the EUROMICRO Journal
Low-power snoop architecture for synchronized producer-consumer embedded multiprocessing

IEEE Transactions on Very Large Scale Integration (VLSI) Systems
An adaptive cache coherence protocol for chip multiprocessors

Proceedings of the Second International Forum on Next-Generation Multicore/Manycore Technologies
Predicting Coherence Communication by Tracking Synchronization Points at Run Time

MICRO-45 Proceedings of the 2012 45th Annual IEEE/ACM International Symposium on Microarchitecture
Bandwidth Adaptive Cache Coherence Optimizations for Chip Multiprocessors

International Journal of Parallel Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

Two-level coherence predictors have shown great promise to reduce coherence overhead in shared memory multiprocessors. However, to be accurate they require a memory overhead that on e.g. a 64-processor machine can be as high as 50%.Based on an application case study consisting of seven applications from SPLASH-2, a first observation made in this paper is that memory blocks subject to coherence activities usually constitute only a small fraction (around 10%) of the entire application footprint. Based on this, we contribute with a new class of resource-efficient coherence predictors that is organized as a cache attached to each memory controller. We show that such a Coherence Predictor Cache (CPC) can provide nearly as effective predictions as if a predictor is associated with every memory block, but needs only 2-7% as many predictors.