B. Mei, S. Vernalde, D. Verkest, H. Man, R. Lauwereins
{"title":"DRESC: a retargetable compiler for coarse-grained reconfigurable architectures","authors":"B. Mei, S. Vernalde, D. Verkest, H. Man, R. Lauwereins","doi":"10.1109/FPT.2002.1188678","DOIUrl":null,"url":null,"abstract":"Coarse-grained reconfigurable architectures have become increasingly important in recent years. Automatic design or compiling tools are essential to their success. In this paper, we present a retargetable compiler for a family of coarse-grained reconfigurable architectures. Several key issues are addressed. Program analysis and transformation prepare dataflow for scheduling. Architecture abstraction generates an internal graph representation from a concrete architecture description. A modulo scheduling algorithm is key to exploit parallelism and achieve high performance. The experimental results show up to 28.7 instructions per cycle (IPC) over tested kernels.","PeriodicalId":355740,"journal":{"name":"2002 IEEE International Conference on Field-Programmable Technology, 2002. (FPT). Proceedings.","volume":"49 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"227","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2002 IEEE International Conference on Field-Programmable Technology, 2002. (FPT). Proceedings.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/FPT.2002.1188678","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 227
Abstract
Coarse-grained reconfigurable architectures have become increasingly important in recent years. Automatic design or compiling tools are essential to their success. In this paper, we present a retargetable compiler for a family of coarse-grained reconfigurable architectures. Several key issues are addressed. Program analysis and transformation prepare dataflow for scheduling. Architecture abstraction generates an internal graph representation from a concrete architecture description. A modulo scheduling algorithm is key to exploit parallelism and achieve high performance. The experimental results show up to 28.7 instructions per cycle (IPC) over tested kernels.