Energy Efficient Design of Coarse-Grained Reconfigurable Architectures: Insights, Trends and Challenges
Authors:
- 5 December 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-11
Abstract
Coarse-Grained Reconfigurable Architectures (CGRAs) are promising solutions to achieve more performance with the end of Moore's law. Thanks to word-level programmability, they are more energy-efficient compared to FPGAs. Although ASICs can minimize energy, they suffer from high Non-Recurring Engineering (NRE) costs and inflexibility. CGRAs provide near ASIC energy efficiency and are deployed in the literature to accelerate low-power and high-performance applications. However, focusing on low-power CGRAs is crucial as a high volume of data should be processed on a resource-constrained device by the development of IoT and Machine Learning applications. This survey has reviewed and categorized CGRA architectures from processing elements, interconnect networks, and memory points of view and derived guidelines for energy-efficient CGRA design.Keywords
Funding Information
- DFG, German Research Foundation (287022738)
This publication has 75 references indexed in Scilit:
- Variable pipeline structure for Coarse Grained Reconfigurable Array CMA2016
- Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural NetworksIEEE Journal of Solid-State Circuits, 2016
- Energy-Efficient CNN Implementation on a Deeply Pipelined FPGA Cluster2016
- EyerissACM SIGARCH Computer Architecture News, 2016
- Compiling HPC Kernels for the REDEFINE CGRA2015
- Reconfigurable Computing ArchitecturesProceedings of the IEEE, 2015
- ULP-SRPACM Transactions on Reconfigurable Technology and Systems, 2014
- NeuroCGRA: A CGRA with support for neural networks2014
- Architectural Exploration of the ADRES Coarse-Grained Reconfigurable Array2007
- ADRES: An Architecture with Tightly Coupled VLIW Processor and Coarse-Grained Reconfigurable Matrix2003