High-level modeling and synthesis for embedded FPGAs

  • Authors:
  • Xiaolin Chen;Shuai Li;Jochen Schleifer;Thomas Coenen;Anupam Chattopadhyay;Gerd Ascheid;Tobias G. Noll

  • Affiliations:
  • RWTH Aachen University, Germany;RWTH Aachen University, Germany;RWTH Aachen University, Germany;RWTH Aachen University, Germany;RWTH Aachen University, Germany;RWTH Aachen University, Germany;RWTH Aachen University, Germany

  • Venue:
  • Proceedings of the Conference on Design, Automation and Test in Europe
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

The fast evolving applications in modern digital signal processing have an increasing demand for components which have high computational power and energy efficiency without compromising the flexibility. Embedded FPGA, which is the customized FPGA with heterogeneous fine-grained application specific operations and routing resources, has shown significantly improved efficiency in terms of throughput, power dissipation and chip area for the target application domain. On the other hand, the complexity of such architecture makes it difficult to perform an efficient architecture exploration and application synthesis without tool support. In this work, we propose a framework for the design of embedded FPGA (eFPGA) architectures, which is extended from an existing framework for Coarse-Grained Reconfigurable Architectures (CGRAs). The framework is composed of a high-level modeling formalism for eFPGAs to explore the mapping space, and a retargetable application synthesis flow. To enable fast design space exploration, a force-directed placement algorithm is proposed. Finally, we demonstrate the efficacy of this framework with demanding application kernels.