{"title":"An Area-Efficient Multiple-Valued Reconfigurable VLSI Architecture Using an X-Net","authors":"Xu Bai, M. Kameyama","doi":"10.1109/ISMVL.2013.13","DOIUrl":null,"url":null,"abstract":"An X-net is employed for simplifying interconnections and switch blocks of a multiple-valued reconfigurable VLSI (MV-RVLSI). One cell composed of a logic block and a switch block is connected to four adjacent \"X\" intersections by four one-bit switches. A multiple-valued X-net data transfer scheme is proposed to improve the utilization of the X-net, where two binary data can be transferred from two adjacent cells to one common adjacent cell simultaneously at each \"X\" intersection. To evaluate the MV-RVLSIs, a sum-of-absolute-differences operation is mapped onto a previous MV-RVLSI using an 8 nearest-neighbor mesh network (8-NNM) and the MV-RVLSI using the X-net, respectively. The area of the MV-RVLSI based on the multiple-valued X-net data transfer scheme is reduced to 73% and 84%, respectively, in comparison with those of the MVRVLSI using the 8-NNM and the MV-RVLSI based on a binary X-net data transfer scheme.","PeriodicalId":124947,"journal":{"name":"2013 IEEE 43rd International Symposium on Multiple-Valued Logic","volume":"41 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE 43rd International Symposium on Multiple-Valued Logic","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISMVL.2013.13","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
An X-net is employed for simplifying interconnections and switch blocks of a multiple-valued reconfigurable VLSI (MV-RVLSI). One cell composed of a logic block and a switch block is connected to four adjacent "X" intersections by four one-bit switches. A multiple-valued X-net data transfer scheme is proposed to improve the utilization of the X-net, where two binary data can be transferred from two adjacent cells to one common adjacent cell simultaneously at each "X" intersection. To evaluate the MV-RVLSIs, a sum-of-absolute-differences operation is mapped onto a previous MV-RVLSI using an 8 nearest-neighbor mesh network (8-NNM) and the MV-RVLSI using the X-net, respectively. The area of the MV-RVLSI based on the multiple-valued X-net data transfer scheme is reduced to 73% and 84%, respectively, in comparison with those of the MVRVLSI using the 8-NNM and the MV-RVLSI based on a binary X-net data transfer scheme.