Fanchao Wang, Hanbin Zhu, Pranjay Popli, Yao Xiao, P. Bogdan, Shahin Nazarian
{"title":"Accelerating Coverage Directed Test Generation for Functional Verification: A Neural Network-based Framework","authors":"Fanchao Wang, Hanbin Zhu, Pranjay Popli, Yao Xiao, P. Bogdan, Shahin Nazarian","doi":"10.1145/3194554.3194561","DOIUrl":null,"url":null,"abstract":"With increasing design complexity, the correlation between test transactions and functional properties becomes non-intuitive, hence impacting the reliability of test generation. This paper presents a modified coverage directed test generation based on an Artificial Neural Network (ANN). The ANN extracts features of test transactions and only those which are learned to be critical, will be sent to the design under verification. Furthermore, the priority of coverage groups is dynamically learned based on the previous test iterations. With ANN-based screening, low-coverage or redundant assertions will be filtered out, which helps accelerate the verification process. This allows our framework to learn from the results of the previous vectors and use that knowledge to select the following test vectors. Our experimental results confirm that our learning-based framework can improve the speed of existing function verification techniques by 24.5x and also also deliver assertion coverage improvement, ranging from 4.3x to 28.9x, compared to traditional coverage directed test generation, implemented in UVM.","PeriodicalId":215940,"journal":{"name":"Proceedings of the 2018 on Great Lakes Symposium on VLSI","volume":"187 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"20","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2018 on Great Lakes Symposium on VLSI","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3194554.3194561","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 20
Abstract
With increasing design complexity, the correlation between test transactions and functional properties becomes non-intuitive, hence impacting the reliability of test generation. This paper presents a modified coverage directed test generation based on an Artificial Neural Network (ANN). The ANN extracts features of test transactions and only those which are learned to be critical, will be sent to the design under verification. Furthermore, the priority of coverage groups is dynamically learned based on the previous test iterations. With ANN-based screening, low-coverage or redundant assertions will be filtered out, which helps accelerate the verification process. This allows our framework to learn from the results of the previous vectors and use that knowledge to select the following test vectors. Our experimental results confirm that our learning-based framework can improve the speed of existing function verification techniques by 24.5x and also also deliver assertion coverage improvement, ranging from 4.3x to 28.9x, compared to traditional coverage directed test generation, implemented in UVM.