Heterogeneous Computing for Edge AI
2019 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)(2019)
摘要
Current artificial intelligence (AI) with human-level accuracy has promising business values in many application fields. However, the price is high computation complexity and memory bandwidth. Therefore it is challenging to deploy AI onto edge devices where the power and hardware resource are limited. In this paper, the design challenges on Edge AI and solutions from Mediatek is introduced. Dedicated parallel AI processor is embedded to gain computation and power efficiency. Memory hierarchy is designed to share and reuse data locally without redundant DRAM accessing. A direct data link is implemented to pass the data between system peripherals and processors to further reduce DRAM bandwidth. The implementation result shows the SoC with all these techniques significantly outperforms other works according to ETHZ AI benchmark.
更多查看译文
关键词
Edge AI,edge devices,power efficiency,memory hierarchy,direct data link,DRAM bandwidth,ETHZ AI benchmark,artificial intelligence,parallel AI processor,heterogeneous computing,SoC,Mediatek
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络