Lutz Schammer, Jan Runge, Paula Klimach, Goerschwin Fey
{"title":"Design Understanding: Identifying Instruction Pipelines in Hardware Designs","authors":"Lutz Schammer, Jan Runge, Paula Klimach, Goerschwin Fey","doi":"10.1109/mocast54814.2022.9837742","DOIUrl":null,"url":null,"abstract":"Automated tools help a designer to reduce the time and the effort required to understand details of an unfamiliar design. In this paper we show an approach using static analysis to identify instruction pipelines, which are key structures in processor hardware designs. We present two algorithms which identify pipeline structures. The first algorithm is based on a structural analysis using a graph representation of the design, while the second algorithm uses terms and phrases for pipelines as they are found in literature for a name-matching approach. The two algorithms successfully identified pipelines for e.g. Y86 and edge processor designs.","PeriodicalId":122414,"journal":{"name":"2022 11th International Conference on Modern Circuits and Systems Technologies (MOCAST)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 11th International Conference on Modern Circuits and Systems Technologies (MOCAST)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/mocast54814.2022.9837742","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Automated tools help a designer to reduce the time and the effort required to understand details of an unfamiliar design. In this paper we show an approach using static analysis to identify instruction pipelines, which are key structures in processor hardware designs. We present two algorithms which identify pipeline structures. The first algorithm is based on a structural analysis using a graph representation of the design, while the second algorithm uses terms and phrases for pipelines as they are found in literature for a name-matching approach. The two algorithms successfully identified pipelines for e.g. Y86 and edge processor designs.