Exploring NoC Mapping Strategies: An Energy and Timing Aware Technique

TL;DR

This paper introduces a new model called CDCM that considers both communication dependence and computation for mapping applications on NoCs, leading to significant reductions in execution time and energy consumption.

Contribution

It proposes the CDCM model that simultaneously captures communication and computation aspects, improving NoC mapping strategies over previous models.

Findings

Estimated 40% reduction in execution time.

Estimated 20% reduction in energy consumption.

Applicable to current technology nodes.

Abstract

Complex applications implemented as Systems on Chip (SoCs) demand extensive use of system level modeling and validation. Their implementation gathers a large number of complex IP cores and advanced interconnection schemes, such as hierarchical bus architectures or networks on chip (NoCs). Modeling applications involves capturing its computation and communication characteristics. Previously proposed communication weighted models (CWM) consider only the application communication aspects. This work proposes a communication dependence and computation model (CDCM) that can simultaneously consider both aspects of an application. It presents a solution to the problem of mapping applications on regular NoCs while considering execution time and energy consumption. The use of CDCM is shown to provide estimated average reductions of 40% in execution time, and 20% in energy consumption, for current technologies.