Peter Milder, F. Franchetti, J. Hoe, Markus Püschel
{"title":"Formal datapath representation and manipulation for implementing DSP transforms","authors":"Peter Milder, F. Franchetti, J. Hoe, Markus Püschel","doi":"10.1145/1391469.1391572","DOIUrl":null,"url":null,"abstract":"We present a domain-specific approach to representing datapaths for hardware implementations of linear signal transform algorithms. We extend the tensor structure for describing linear transform algorithms, adding the ability to explicitly characterize two important dimensions of datapath architecture. This representation allows both algorithm and datapath to be specified within a single formula and gives the designer the ability to easily consider a wide space of possible datapaths at a high level of abstraction. We have constructed a formula manipulation system based on this representation and have written a compiler that can translate a formula into a hardware implementation. This enables an automatic \"push button\" compilation flow that produces a register transfer level hardware description from high-level datapath directives and an algorithm (written as a formula). In our experimental results, we demonstrate that this approach yields efficient designs over a large tradeoff space.","PeriodicalId":412696,"journal":{"name":"2008 45th ACM/IEEE Design Automation Conference","volume":"30 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"54","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 45th ACM/IEEE Design Automation Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/1391469.1391572","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 54
Abstract
We present a domain-specific approach to representing datapaths for hardware implementations of linear signal transform algorithms. We extend the tensor structure for describing linear transform algorithms, adding the ability to explicitly characterize two important dimensions of datapath architecture. This representation allows both algorithm and datapath to be specified within a single formula and gives the designer the ability to easily consider a wide space of possible datapaths at a high level of abstraction. We have constructed a formula manipulation system based on this representation and have written a compiler that can translate a formula into a hardware implementation. This enables an automatic "push button" compilation flow that produces a register transfer level hardware description from high-level datapath directives and an algorithm (written as a formula). In our experimental results, we demonstrate that this approach yields efficient designs over a large tradeoff space.