{"title":"Analysis of matrix multiplication on high density Virtex-7 FPGA","authors":"Wilson Jose, Ana Rita Silva, H. Neto, M. Véstias","doi":"10.1109/FPL.2013.6645604","DOIUrl":null,"url":null,"abstract":"In this work, we have developed a theoretical model of matrix multiplication including a detailed model of external memory access. We have used the model to guide the design of a many core architecture. The architecture was modeled and simulated in SystemC and a small prototype was implemented in an FPGA board to determine the accuracy of the model. Finally, using the model, we determined the achievable performance in Virtex-7 FPGAs. The results indicate the correctness of the model and the performance of state-of-the-art FPGAs in the execution of matrix-multiplication.","PeriodicalId":200435,"journal":{"name":"2013 23rd International Conference on Field programmable Logic and Applications","volume":"60 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 23rd International Conference on Field programmable Logic and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/FPL.2013.6645604","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 9
Abstract
In this work, we have developed a theoretical model of matrix multiplication including a detailed model of external memory access. We have used the model to guide the design of a many core architecture. The architecture was modeled and simulated in SystemC and a small prototype was implemented in an FPGA board to determine the accuracy of the model. Finally, using the model, we determined the achievable performance in Virtex-7 FPGAs. The results indicate the correctness of the model and the performance of state-of-the-art FPGAs in the execution of matrix-multiplication.