{"title":"A software aided algorithm analysis","authors":"R. Trimananda, Y. Kuang","doi":"10.1109/IEECON.2014.6925865","DOIUrl":null,"url":null,"abstract":"System validation in the industry needs a lot of servers to generate test sets and run them on the validated processors or SoCs. With the requirement of a competitive time-to-market, this process has to happen speedily and, yet thoroughly to ensure a quality product. As the validation is automated using software, this implies that effective and efficient validation software is absolutely needed. This paper reports the basics that were revisited while our team was trying to improve the performance of our validation software. The analysis and improvement process was aided by functional-level algorithm analysis software called VTune™ that could precisely pinpoint the caveats in the source code. Revisiting the basics resulted in three key learnings on software improvements. A significant 16 percent performance improvement was achieved.","PeriodicalId":306512,"journal":{"name":"2014 International Electrical Engineering Congress (iEECON)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2014-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 International Electrical Engineering Congress (iEECON)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IEECON.2014.6925865","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
System validation in the industry needs a lot of servers to generate test sets and run them on the validated processors or SoCs. With the requirement of a competitive time-to-market, this process has to happen speedily and, yet thoroughly to ensure a quality product. As the validation is automated using software, this implies that effective and efficient validation software is absolutely needed. This paper reports the basics that were revisited while our team was trying to improve the performance of our validation software. The analysis and improvement process was aided by functional-level algorithm analysis software called VTune™ that could precisely pinpoint the caveats in the source code. Revisiting the basics resulted in three key learnings on software improvements. A significant 16 percent performance improvement was achieved.