{"title":"在多核智能手机上实现更好的CPU电源管理","authors":"Yifan Zhang, Xudong Wang, Xuanzhe Liu, Yunxin Liu, Linda Zhuang, Feng Zhao","doi":"10.1145/2525526.2525849","DOIUrl":null,"url":null,"abstract":"Although multicore smartphones have become increasingly mainstream, it is unclear whether and how smartphone applications can utilize multicore CPUs to improve performance. In this paper we study the performance of mobile applications using multicore CPUs, in terms of power and computation cost. Using Web browsing as an example, our preliminary measurement results show that even large applications like Web browsers with multi-threading acceleration cannot fully utilize the multicore CPUs. Furthermore, we find that the existing CPU power models on smartphones are ill-suited for modern multicore CPUs. We develop a new CPU power model with a high accuracy, 95.6% on average. Our work helps to better understand the performance of multicore smartphones and paves the way towards better CPU power management on multicore smartphones.","PeriodicalId":112226,"journal":{"name":"Power-Aware Computer Systems","volume":"145 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"37","resultStr":"{\"title\":\"Towards better CPU power management on multicore smartphones\",\"authors\":\"Yifan Zhang, Xudong Wang, Xuanzhe Liu, Yunxin Liu, Linda Zhuang, Feng Zhao\",\"doi\":\"10.1145/2525526.2525849\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Although multicore smartphones have become increasingly mainstream, it is unclear whether and how smartphone applications can utilize multicore CPUs to improve performance. In this paper we study the performance of mobile applications using multicore CPUs, in terms of power and computation cost. Using Web browsing as an example, our preliminary measurement results show that even large applications like Web browsers with multi-threading acceleration cannot fully utilize the multicore CPUs. Furthermore, we find that the existing CPU power models on smartphones are ill-suited for modern multicore CPUs. We develop a new CPU power model with a high accuracy, 95.6% on average. Our work helps to better understand the performance of multicore smartphones and paves the way towards better CPU power management on multicore smartphones.\",\"PeriodicalId\":112226,\"journal\":{\"name\":\"Power-Aware Computer Systems\",\"volume\":\"145 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-11-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"37\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Power-Aware Computer Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/2525526.2525849\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Power-Aware Computer Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2525526.2525849","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Towards better CPU power management on multicore smartphones
Although multicore smartphones have become increasingly mainstream, it is unclear whether and how smartphone applications can utilize multicore CPUs to improve performance. In this paper we study the performance of mobile applications using multicore CPUs, in terms of power and computation cost. Using Web browsing as an example, our preliminary measurement results show that even large applications like Web browsers with multi-threading acceleration cannot fully utilize the multicore CPUs. Furthermore, we find that the existing CPU power models on smartphones are ill-suited for modern multicore CPUs. We develop a new CPU power model with a high accuracy, 95.6% on average. Our work helps to better understand the performance of multicore smartphones and paves the way towards better CPU power management on multicore smartphones.