Modeling NoC traffic locality and energy consumption with rent's communication probability distribution

Authors:
George B.P. Bezerra;Stephanie Forrest;Melanie Forrest;Al Davis;Payman Zarkesh-Ha
Affiliations:
University of New Mexico, Albuquerque, NM, USA;University of New Mexico, Albuquerque, NM, USA;University of New Mexico, Albuquerque, NM, USA;University of Utah, Salt Lake City, UT, USA;University of New Mexico, Albuquerque, NM, USA
Venue:
Proceedings of the 12th ACM/IEEE international workshop on System level interconnect prediction
Year:
2010

Citing 11
Cited 2

The interpretation and application of Rent's rule

IEEE Transactions on Very Large Scale Integration (VLSI) Systems - Special issue on system-level interconnect prediction
Span: an energy-efficient coordination algorithm for topology maintenance in ad hoc wireless networks

Wireless Networks
The Raw Microprocessor: A Computational Fabric for Software Circuits and General-Purpose Programs

IEEE Micro
Principles and Practices of Interconnection Networks

Principles and Practices of Interconnection Networks
Mapping embedded systems onto NoCs: the traffic effect on dynamic energy estimation

SBCCI '05 Proceedings of the 18th annual symposium on Integrated circuits and system design
Energy-aware mapping for tile-based NoC architectures under performance constraints

ASP-DAC '03 Proceedings of the 2003 Asia and South Pacific Design Automation Conference
A Statistical Traffic Model for On-Chip Interconnection Networks

MASCOTS '06 Proceedings of the 14th IEEE International Symposium on Modeling, Analysis, and Simulation
Implications of Rent's Rule for NoC Design and Its Fault-Tolerance

NOCS '07 Proceedings of the First International Symposium on Networks-on-Chip
A 5-GHz Mesh Interconnect for a Teraflops Processor

IEEE Micro
Rent's rule and parallel programs: characterizing network traffic behavior

Proceedings of the 2008 international workshop on System level interconnect prediction
ORION 2.0: a fast and accurate NoC power and area model for early-stage design space exploration

Proceedings of the Conference on Design, Automation and Test in Europe

Hybrid network on chip (HNoC): local buses with a global mesh architecture

Proceedings of the 12th ACM/IEEE international workshop on System level interconnect prediction
Reducing energy and increasing performance with traffic optimization in many-core systems

Proceedings of the System Level Interconnect Prediction Workshop

Quantified Score

Hi-index	0.00

Visualization

Abstract

In systems on chip, the energy consumed by the Network on Chip (NoC) depends heavily on the network traffic pattern. The higher the communication locality, the lower the energy consumption will be. In this paper, we use the Communication Probability Distribution (CPD) to model communication locality and energy consumption in NoC. Firstly, based on recent results showing that communication patterns of many parallel applications follow Rent's rule, we propose a Rent's rule [6] traffic generator. In this method, the probability of communication between cores is derived directly from Rent's rule, which results in CPDs displaying high locality. Next, we provide a model for predicting NoC energy consumption based on the CPD. The model was tested on two NoC systems and several workloads, including Rent's rule traffic, and obtained accurate results when compared to simulations. The results also show that Rent's rule traffic has lower energy consumption than commonly used synthetic workloads, due to its higher communication locality. Finally, we exploit the tunability of our traffic generator to study applications with different locality, analyzing the impact of the Rent's exponent on energy consumption.