Design Automation for Memory Access Free Architecture

高层次设计方法在大系统LSI器件的设计中变得越来越重要。因此，基于C语言和其他高级语言的行为综合是实现大型设计所需生产力的关键，特别是对于存储密集型应用，存储器访问操作的自动识别、优化和综合是必不可少的。该方法与寄存器化相结合，可以在不考虑数据重用程度的情况下加速存储器访问（MA）.将该方法应用于语音识别、JPEG编码和粒子跟踪技术等领域的常用算法中，并对其有效性进行了评估.使用这些MA加速方法，MA的数量减少了20%以上，总体性能提高了10%以上.

High level design methodologies are becoming more and more important in the design of large system LSI devices. As a result, behavioral synthesis from C and other high level languages is key to achieving the productivity demanded by such large designs.For memory intensive applications in particular, the automatic identification, optimization and synthesis of memory access operations is essential.This research developed a method for automatically generating behavioral descriptions for memory access pipeline circuits. Combined with registerization, the approach can accelerate Memory Accesses (MA) irrespective of the degree of data reuse.The method is applied to well-known algorithms used in applications such as speech recognition, JPEG encoding and particle tracking technology, and its effectiveness evaluated.The number of MAs is reduced by over 20% and the overall performance improved by over 10% using these MA speed-up methods.