A Survey of FPGA Optimization Methods for Data Center Energy Efficiency

Abstract

This article provides a survey of academic literature about field programmable gate array (FPGA) and their utilization for energy efficiency acceleration in data centers. The goal is to critically present the existing FPGA energy optimization techniques and discuss how they can be applied to such systems. To do so, the article explores current energy trends and their projection to the future with particular attention to the requirements set out by the European Code of Conduct for Data Center Energy Efficiency. The article then proposes a complete analysis of over ten years of research in energy optimization techniques, classifying them by purpose, method of application, and impacts on the sources of consumption. Finally, we conclude with the challenges and possible innovations we expect for this sector.

arXiv commentAccepted for publication in IEEE Transactions on Sustainable Computing

References in corpus (7)

• Shannon Information and Kolmogorov Complexity
• A Data-Center FPGA Acceleration Platform for Convolutional Neural Networks
• When HLS Meets FPGA HBM: Benchmarking and Bandwidth Optimization
• Thermodynamic Computing
• EVEREST: A design environment for extreme-scale big data analytics on heterogeneous platforms
• Multi-Tenant Cloud FPGA: A Survey on Security
• Iris: Automatic Generation of Efficient Data Layouts for High Bandwidth Utilization