Analysis and approximation for bank selection instruction minimization on partitioned memory architecture

Author:

Li Minming1,Xue Chun Jason1,Liu Tiantian1,Zhao Yingchao1

Affiliation:

1. Department of Computer Science, City University of Hong Kong, Hong Kong, Hong Kong

Abstract

A large number of embedded systems include 8-bit microcontrollers for their energy efficiency and low cost. Multi-bank memory architecture is commonly applied in 8-bit microcontrollers to increase the size of memory without extending address buses. To switch among different memory banks, a special instruction, Bank Selection, is used. How to minimize the number of bank selection instructions inserted is important to reduce code size for embedded systems. In this paper, we consider how to insert the minimum number of bank selection instructions in a program to achieve feasibility. A program can be represented by a control flow graph (CFG). We prove that it is NP-Hard to insert the minimum number of bank selection instructions if all the variables are pre-assigned to memory banks. Therefore, we introduce a 2-approximation algorithm using a rounding method. When the CFG is a tree or the out-degree of each node in the CFG is at most two, we show that we can insert the bank selection instructions optimally in polynomial time. We then consider the case when there are some nodes that do not access any memory bank and design a dynamic programming method to compute the optimal insertion strategy when the CFG is a tree. Experimental result shows the proposed techniques can reduce bank selection instructions significantly on partitioned memory architecture.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design,Software

Reference21 articles.

1. Freescale. http://www.freescale.com. Freescale. http://www.freescale.com.

2. Semico. http://www.semico.com/. Semico. http://www.semico.com/.

3. Zilog. http://www.zilog.com. Zilog. http://www.zilog.com.

4. Exploiting dual data-memory banks in digital signal processors

5. Data and memory optimization techniques for embedded systems

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3