可编辑门阵列FPGA在智慧云中的应用案例分析

Case Study of the Application of Field Programmable Gate Array FPGA in the Smart Skill

分析Amazon和Microsoft在Cloud中使用FPGA加速的实现方法。相比Google的TPU(ASIC)针对Deep Learning的设计,FPGA虽然在效率上有差距,但在灵活性方面有自己的优势。不管是在AWS和Azure中,FPGA可以更广泛用于不同的加速任务当中。如果能够配合更好的开发环境,形成完整的生态,相信未来它在云端会有更大的发展空间。

This paper analyzes the implementation of FPGA using Amazon and Microsoft in Cloud. Compared with Google＇s TPU （ASIC） for the design of Deep Learning, FPGA has a gap in efficiency, but has its own advantages in flexibility. In both AWS and Azure, FPGA can be used more widely in different acceleration tasks. If we can cooperate with the better development environment and form a complete ecology, it is believed that it will have more space for development in the future.