自适应光学实时控制可扩展平台(SPARC)第2部分:现场可编程门阵列(FPGA)的实现和性能
Scalable Platform for Adaptive optics Real-time Control (SPARC) Part 2: Field Programmable Gate Array (FPGA) implementation and performance
摘要:
大型望远镜上的下一代自适应光学(AO)系统将需要巨大的计算性能和存储带宽,这两者都是当今技术的挑战。这项工作的目的是创建一个面向未来的自适应光学平台上的FPGA架构,其规模与子孔径,每个子孔径和外部存储器的像素的数量。我们已经创建了一个可扩展的自适应光学平台与现成的FPGA开发板,它提供了一个AO重建时间只受外部存储器带宽的限制。与AO系统中的子孔径数目无关,FPGA使用相同的逻辑资源。本文面向对FPGA设计及其硬件接口感兴趣的嵌入式开发人员。本文的中心主题是展示如何在FPGA实现的不同层次的可扩展性。这项工作是论文第1部分的延续,该部分解释了用于测试平台的概念、目标、控制方案和验证方法。
英文摘要:
The next generation of Adaptive Optics (AO) systems on large telescopes will require immense computation performance and memory bandwidth, both of which are challenging with the technology available today. The objective of this work is to create a future-proof adaptive optics platform on an FPGA architecture, which scales with the number of subapertures, pixels per subaperture and external memory. We have created a scalable adaptive optics platform with an off-the-shelf FPGA development board, which provides an AO reconstruction time only limited by the external memory bandwidth. SPARC uses the same logic resources irrespective of the number of subapertures in the AO system. This paper is aimed at embedded developers who are interested in the FPGA design and the accompanying hardware interfaces. The central theme of this paper is to show how scalability is incorporated at different levels of the FPGA implementation. This work is a continuation of Part 1 of the paper which explains the concept, objectives, control scheme and method of validation used for testing the platform.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。