A component selection methodology for IP reuse in the design of power-aware SoCs based on requirements similarity

Abstract

To counter today's rising complexity in System-on-Chip (SoC) design intellectual property (IP) cores are reused. In libraries often many different pre-designed components are available and selecting suitable IP is difficult and laborious. Power consumption is a key constraint in mobile devices, where SoCs are often used. Therefore, it is important to consider power when selecting components for reuse in the current SoC design. This paper introduces our approach to support component search and selection. Initially, a repository and container for IP is presented. Onto our repository the novel component selection methodology is applied. It considers constraints and properties of IP. Then it performs a similarity analysis between system and component requirements. The result is a ranking of the best-suited components for reuse in the current system under design. To demonstrate our approach a case study is performed on a SoC. With our methodology ranking of components matching the system requirements and constraints is generated. Our work is part of the SIMBA1 project which focuses on simulation-based requirements testing of power-aware SoCs.