共享存储可重构计算机软硬件通信的优化实现  

Optimized Software-Hardware Communications for Shared Memory Reconfigurable Computer

作　　者：荀长庆[1] 杨乾明[1] 伍楠[1] 文梅[1] 张春元[1] 

机构地区：[1]国防科学技术大学计算机学院,长沙410073

出　　处：《计算机研究与发展》2013年第8期1637-1646,共10页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(61033008);国家自然科学基金青年基金项目(60903041);高等学校博士学科点基金项目(20104307110002)

摘　　要：可重构硬件操作系统BORPH提供的硬件进程概念和以硬件为中心的执行模型可极大地提高可重构计算平台的易用性.BORPH-N为BORPH的扩展系统,主要的扩展是支持在共享存储可重构计算平台上的运行.BORPH-N为硬件进程提供基于共享存储、符合Unix语义的高性能进程间通信支持:共享存储和信号量.利用这两项服务,硬件进程可与系统中其他所有软件进程和硬件进程进行交互.可重构计算的重要目标是利用可重构逻辑对应用的耗时部分进行加速,所以软硬件交互机制的效率至关重要.通过类似远程调用这种简单方式来提供这两项服务,软硬件交互频繁,开销较大,性能难以满足需求.BORPH-N使用的优化策略基于独立执行的基本思路进行设计.实验结果表明,BORPH-N所需硬件开销较小,为硬件进程提供的共享存储和信号量的效率逼近硬件平台的峰值,可以满足实际应用的需求.Hardware processes and hardware centric execution model introduced by BORPH have improved the usability of reconfigurable computers significantly. BORPH-N is designed as an extended system oI BORPH. The main extension is that BORPH-N supports shared memory reconfigurable computers. And hardware processes can communicate with the rest of the system by shared memory and semaphore which are Unix semantic in BORPH-N. Accelerating the computing intensive parts of applications is one of the most important goals of reconfigurable computing. Thereby efficiency of software-hardware communications is very crucial. Supporting shared memory and semaphore through simple mechanisms such as remote system call, can definitely not meet the need of applications. Independent-execution-based optimizations are adopted by BORPH-N. Independent execution means the FPGA does some work locally without the help of the host. The efficiency will be enhanced a lot due to the elimination of data exchange between the host and FPGA. To reduce the workload, only the functions which are repeated frequently during the execution of applications will be completed by FPGA independently. BORPH-N focuses on two tasks： virtual memory access and atomic variable access. Experiment is setup on a PC with an ARRIA II GX FPGA board. The results show the hardware overhead of BORPH-N is low. The efficiency of shared memory and semaphore access is close to the peak performance of hardware platform.

关 键 词：可重构计算 软硬件协同 共享存储 进程间通信 硬件进程 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]