Mapping and configuration methods for multi-use-case networks on chips

Abstract

To provide a scalable communication infrastructure for Systems on Chips (SoCs), Networks on Chips (NoCs), a communication centric design paradigm is needed. To be cost effective, SoCs are often programmable and integrate several different applications or use-cases on to the same chip. For the SoC platform to support the different use-cases, the NoC architecture should satisfy the performance constraints of each individual use-case. In this work we motivate the need to consider multiple use-cases during the NoC design process. We present a method to efficiently map the applications on to the NoC architecture, satisfying the design constraints of each individual use-case. We also present novel ways to dynamically reconfigure the network across the different use-cases and explore the possibility of integrating Dynamic Voltage and Frequency Scaling (DVS/DFS) techniques with the use-case centric NoC design methodology. We validate the performance of the design methodology on several SoC applications. The dynamic reconfiguration of the NoC integrated with DVS/DFS schemes results in large power savings for the resulting NoC systems.

A multi-objective adaptive immune algorithm for multi-application NoC mapping

“…The work of Murali et al [1] is the only previous work that belongs to the third category. Murali et al [1] proposes a heuristic capable of select the NoC configuration that satisfies the latency requirements of all the applications (just a single optimization objective).…”

“…Murali et al [1] proposes a heuristic capable of select the NoC configuration that satisfies the latency requirements of all the applications (just a single optimization objective).…”

“…According to the number of the optimization objectives and the number of application supported by the SoC, previous works can be divided into 3 categories: (1) Single objective and single application [7,8]; (2) Multiple objective and single application [4][5][6]; and (3) Single objective and multiple applications [1]. All works [1,[4][5][6][7][8] used an application characterization graph (APCG) that describes the communication requirements.…”

“…Furthermore, the mapping solution must satisfy all the system requirements consisting of multiple desired objectives that are frequently in contrast with each other [4]. To the best of our knowledge, only Murali et al [1] addresses the multi-application NoC mapping with the aim of minimizing communication delay by exploiting the possibility of splitting traffic among various paths. However, previous works show that mapping strategies that search for single performance index optimization may lead to unacceptable values for other performance indexes [4].…”

“…According to Murali et al [1], NoC mapping is one of the most critical parameters in NoC design. Previous works showed that an optimal mapping may enhance the NoC performance up to 60 % [2].…”