Algorithm Design Methodology for Embedded Architectures

Power efficiency is a critical constraint for embedded systems. To address this many technological innovations are being proposed by the community. However, leveraging such advances also requires algorithmic solutions to handle the potential for run-time errors due to near threshold computing. In this work we plan to develop algorithmic innovations and optimizations for power efficiency in the emerging landscape of embedding computing platforms. We also plan to develop resilient run-time systems and incorporate resiliency in algorithmic solutions. In this paper we briefly describe our design methodology employed in the TAPAS (Tunable Algorithms for PERFECT Architectures) project. The TAPAS project is funded under the DARPA PERFECT (Power Efficiency Revolution for Embedded Computing Technologies) program.