星载SAR成像与智能处理的单片多处理架构  

Single-chip multi-processing architecture for spaceborne SAR imaging and intelligent processing

作　　者：王时雨 张盛兵[1] 黄小平[1] 常立博 WANG Shiyu;ZHANG Shengbing;HUANG Xiaoping;CHANG Libo(School of Computer Science and Engineering,Northwestern Polytechnical University, Xi′an 710072, China)

机构地区：[1]西北工业大学计算机学院,陕西西安710072

出　　处：《西北工业大学学报》2021年第3期510-520,共11页Journal of Northwestern Polytechnical University

摘　　要：星载SAR图像智能处理系统需对成像和多种不同任务应用进行在轨实时处理,设计高效专用单芯片多处理器能够有效支持实时性和低功耗的要求,片上数据组织和访存结构是设计重点。分析了SAR成像CSA(chirp scaling)和神经网络VGG-112种典型模型,抽象出遥感图像智能处理过程的协同计算模型。设计了一种带状Tile化数据处理方案及专用多处理架构,提出了一种Tile划分及多Tile同步拼接策略,设计了处理单元之间数据缓存结构,极大降低片外访存带宽,支持多任务模型的并行流水执行。芯片采用28 nm工艺,整体功耗仅为1.83 W,吞吐率和能效分别达到9.89 TOPS和5.4 TOPS/W。该架构可提高在轨遥感智能处理平台的实时性,降低系统设计复杂度,根据算法模型的不同,可灵活适应差异化扩展。The satellite-borne SAR image intelligent processing system needs to process on-orbit real-time imaging and various tasks of applications,for which reason designing a dedicated high-efficient single-chip multi-processor is of prioritized necessity that can simultaneously satisfy requirements of real-time and low power consumption.Aiming at on-chip data organization and memory access structure,two typical models of SAR(synthetic aperture radar)imaging CSA(chirp scaling)and neural network VGG-11 are analyzed,and then a collaborative computing model for the intelligent processing on remote sensing is extracted.A strip Tile data processing scheme and a dedicated multi-processing architecture is not only proposed,but a data organization and a caching strategy of Tile space synchronization splicing is also presented.In addition,the designed data caching structure among the processing units greatly reduces off-chip access memory bandwidth while supporting parallel pipeline execution of multi-task model.The chip adopts 28 nm CMOS technology featuring with merely 1.83 W of the overall power consumption,whose throughput and energy efficiency reaches 9.89TOPS and 5.4 TOPS/W,respectively.The present architecture can improve real-time performance of the on-orbit remote sensing intelligent processing platform while reducing the complexity of system designing,which is highly adaptive to differentiated expansions according to different models of algorithm.

关 键 词：单片多处理器 领域专用 智能遥感 带状数据划分 数据填充 灵活扩展 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构]