{"title":"从平面规划的角度来看,片上系统的高效电压隔离","authors":"P. Ghosh, Arunabha Sen","doi":"10.1109/DATE.2010.5457124","DOIUrl":null,"url":null,"abstract":"Power consumption can be significantly reduced in Systems-on-Chip (SoC) by scaling down the voltage levels of the Processing Elements (PEs). The power efficiency of this Voltage Islanding technique comes at the cost of energy and area overhead due to the level shifters between voltage islands. Moreover, from the physical design perspective it is not desirable to have an excessive number of voltage islands on the chip. Considering voltage islanding at an early phase of design as during floorplanning of the PEs can address various of these issues. In this paper, we propose a new cost function for the floorplanning objective different from the traditional floorplanning objective. The new cost function not only includes the overall area requirement, but also incorporates the overall power consumption and the design constraint imposed on the maximum number of voltage islands. We propose a greedy heuristic based on the proposed cost function for the floorplanning of the PEs with several voltage islands. Experimental results using benchmark data study the effect of several parameters on the outcome of the heuristic. It is evident from the results that power consumption can be significantly reduced using our algorithm without significant area overhead. The area obtained from the heuristic is also compared with the optimal, and found to be within 4% of the optimal on average, when area minimization is given the priority.","PeriodicalId":432902,"journal":{"name":"2010 Design, Automation & Test in Europe Conference & Exhibition (DATE 2010)","volume":"405 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Power efficient voltage islanding for Systems-on-chip from a floorplanning perspective\",\"authors\":\"P. Ghosh, Arunabha Sen\",\"doi\":\"10.1109/DATE.2010.5457124\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Power consumption can be significantly reduced in Systems-on-Chip (SoC) by scaling down the voltage levels of the Processing Elements (PEs). The power efficiency of this Voltage Islanding technique comes at the cost of energy and area overhead due to the level shifters between voltage islands. Moreover, from the physical design perspective it is not desirable to have an excessive number of voltage islands on the chip. Considering voltage islanding at an early phase of design as during floorplanning of the PEs can address various of these issues. In this paper, we propose a new cost function for the floorplanning objective different from the traditional floorplanning objective. The new cost function not only includes the overall area requirement, but also incorporates the overall power consumption and the design constraint imposed on the maximum number of voltage islands. We propose a greedy heuristic based on the proposed cost function for the floorplanning of the PEs with several voltage islands. Experimental results using benchmark data study the effect of several parameters on the outcome of the heuristic. It is evident from the results that power consumption can be significantly reduced using our algorithm without significant area overhead. The area obtained from the heuristic is also compared with the optimal, and found to be within 4% of the optimal on average, when area minimization is given the priority.\",\"PeriodicalId\":432902,\"journal\":{\"name\":\"2010 Design, Automation & Test in Europe Conference & Exhibition (DATE 2010)\",\"volume\":\"405 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2010-03-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2010 Design, Automation & Test in Europe Conference & Exhibition (DATE 2010)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/DATE.2010.5457124\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 Design, Automation & Test in Europe Conference & Exhibition (DATE 2010)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DATE.2010.5457124","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Power efficient voltage islanding for Systems-on-chip from a floorplanning perspective
Power consumption can be significantly reduced in Systems-on-Chip (SoC) by scaling down the voltage levels of the Processing Elements (PEs). The power efficiency of this Voltage Islanding technique comes at the cost of energy and area overhead due to the level shifters between voltage islands. Moreover, from the physical design perspective it is not desirable to have an excessive number of voltage islands on the chip. Considering voltage islanding at an early phase of design as during floorplanning of the PEs can address various of these issues. In this paper, we propose a new cost function for the floorplanning objective different from the traditional floorplanning objective. The new cost function not only includes the overall area requirement, but also incorporates the overall power consumption and the design constraint imposed on the maximum number of voltage islands. We propose a greedy heuristic based on the proposed cost function for the floorplanning of the PEs with several voltage islands. Experimental results using benchmark data study the effect of several parameters on the outcome of the heuristic. It is evident from the results that power consumption can be significantly reduced using our algorithm without significant area overhead. The area obtained from the heuristic is also compared with the optimal, and found to be within 4% of the optimal on average, when area minimization is given the priority.