声纳阵元域信号并行仿真系统设计  

The design for parallel computing simulation of waveforms in the front end of sonar

作　　者：王希敏[1] 蔡志明[1] 邱风[1] 许任洲[1] 

机构地区：[1]海军工程大学,武汉430033

出　　处：《声学技术》2009年第4期550-555,共6页Technical Acoustics

摘　　要：采用由多片DSP和工控机为核心组成的DSP并行处理系统,进行声纳阵元域信号仿真。为满足实时性与通用性的应用需求,探讨基于并行DSP系统的仿真系统的软硬件结合设计方法。根据仿真算法,设计仿真系统任务流水线并行模式;基于软件工程方法和设计模式,设计便于流水线阶段映射的DSP进程框架和适当粒度的任务封装;采用时延隐藏方式设计DSP间的数据通信。使用表明,这些设计既满足了实时性能的要求,又解决了并行多任务实时系统通常难以进行适应性维护和功能重配置的问题。A commercial off-the-shelf （COTS） parallel processing system, consisted of multi-DSPs and a control computer, is used as a hardware platform for the online simulation of waveforms in the front end of sonar. The simulation system should keep open and run in real time, so the design issues for the simulation software in the multi-DSPs platform are addressed. The task parallel mode of the simulation system is designed. The program framework of DSP process is defined as an active object based on the object-oriented for the pipeline stage being smartly mapped onto DSP. Latency-tolerance technology is used for the design of data communications between DSPs. Practices show that the constructed simulation system runs in real-time, and can be easily modified and reconfigured which are usually difficult for the multi-task parallel DSP system.

关 键 词：信息处理 并行计算 流水线并行模式 TIGERSHARC DSP 实时仿真 声纳信号 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]