期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2017
卷号：6
期号：10
页码：19383
DOI：10.15680/IJIRSET.2017.0610011
出版社：S&S Publications
摘要：Memory plays a crucial role in designing embedded systems. Embedded systems are constrained by theavailable memory. A larger memory can accommodate more and large applications but increases cost, area, as well asenergy requirements. Code-compression techniques address this issue by reducing the code size of applicationprograms. It is a major challenge to develop an efficient code-compression technique that can generate substantialreduction in code size without affecting the overall system performance. We present an efficient code-compressiontechnique, which significantly improves the compression ratio. Two previously proposed algorithm are evaluated. Thefirst algorithm is dictionary-based method, provides a small separated dictionary is proposed to restrict the codewordlength of high-frequency instructions, and a novel dictionary selection algorithm is proposed to achieve moresatisfactory instruction selection, which in turn may reduce the average CR. The second algorithm is mixed-bit savingdictionary selection (MBSDS) the fully separated dictionary architecture is proposed to improve the performance of thedictionary-based decompression engine. This architecture has a better chance to parallel decompress instructions thanexisting single dictionary decoders Additionally, this paper offers a third algorithm namely, to combine the twopreviously proposed schemes along with run length encoding to compress the code.
