Code optimization for code compression

International Symposium on Code Generation and Optimization, 2003. CGO 2003. Pub Date : 2003-03-23 DOI:10.1109/CGO.2003.1191555

M. Drinic, D. Kirovski, Hoi Vo

{"title":"Code optimization for code compression","authors":"M. Drinic, D. Kirovski, Hoi Vo","doi":"10.1109/CGO.2003.1191555","DOIUrl":null,"url":null,"abstract":"With the emergence of software delivery platforms such as Microsoft's .NET, the reduced size of transmitted binaries has become a very important system parameter, strongly affecting system performance. We present two novel pre-processing steps for code compression that explore program binaries' syntax and semantics to achieve superior compression ratios. The first preprocessing step involves heuristic partitioning of a program binary into streams with high auto-correlation. The second preprocessing step uses code optimization via instruction rescheduling in order to improve prediction probabilities for a given compression engine. We have developed three heuristics for instruction rescheduling that explore tradeoffs of the solution quality versus algorithm run-time. The pre-processing steps are integrated with the generic paradigm of prediction by partial matching (PPM) which is the basis of our compression codec. The compression algorithm is implemented for x86 binaries and tested on several large Microsoft applications. Binaries compressed using our compression codec are 18-24% smaller than those compressed using the best available off-the-shelf compressor.","PeriodicalId":277590,"journal":{"name":"International Symposium on Code Generation and Optimization, 2003. CGO 2003.","volume":"25 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2003-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Symposium on Code Generation and Optimization, 2003. CGO 2003.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CGO.2003.1191555","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 11

Abstract

With the emergence of software delivery platforms such as Microsoft's .NET, the reduced size of transmitted binaries has become a very important system parameter, strongly affecting system performance. We present two novel pre-processing steps for code compression that explore program binaries' syntax and semantics to achieve superior compression ratios. The first preprocessing step involves heuristic partitioning of a program binary into streams with high auto-correlation. The second preprocessing step uses code optimization via instruction rescheduling in order to improve prediction probabilities for a given compression engine. We have developed three heuristics for instruction rescheduling that explore tradeoffs of the solution quality versus algorithm run-time. The pre-processing steps are integrated with the generic paradigm of prediction by partial matching (PPM) which is the basis of our compression codec. The compression algorithm is implemented for x86 binaries and tested on several large Microsoft applications. Binaries compressed using our compression codec are 18-24% smaller than those compressed using the best available off-the-shelf compressor.

查看原文本刊更多论文

代码压缩的代码优化

随着微软的。net等软件交付平台的出现，传输二进制文件的减小大小已经成为一个非常重要的系统参数，强烈影响系统性能。我们提出了两个新的代码压缩预处理步骤，探索程序二进制文件的语法和语义，以获得更高的压缩比。预处理的第一步涉及将程序二进制数据启发式划分为具有高自相关性的流。第二个预处理步骤通过指令重调度进行代码优化，以提高给定压缩引擎的预测概率。我们为指令重调度开发了三种启发式方法，探索了解决方案质量与算法运行时之间的权衡。预处理步骤与部分匹配(PPM)预测的通用范式相结合，这是我们的压缩编解码器的基础。该压缩算法是为x86二进制文件实现的，并在几个大型微软应用程序上进行了测试。使用我们的压缩编解码器压缩的二进制文件比使用最好的现成压缩器压缩的二进制文件小18-24%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Symposium on Code Generation and Optimization, 2003. CGO 2003.

自引率

0.00%

发文量