完整後設資料紀錄
DC 欄位語言
dc.contributor.authorLiou, De-Yinen_US
dc.contributor.authorChen, Chien-Chihen_US
dc.contributor.authorChen, Tien-Fuen_US
dc.contributor.authorLin, Tay-Jyien_US
dc.date.accessioned2019-06-03T01:09:16Z-
dc.date.available2019-06-03T01:09:16Z-
dc.date.issued2017-01-01en_US
dc.identifier.isbn978-1-5386-0501-1en_US
dc.identifier.issn2378-8232en_US
dc.identifier.urihttp://hdl.handle.net/11536/152016-
dc.description.abstractWith the number and variety of IoT devices increasing, a large amount of data have to be moved to the cloud, resulting into unpredictable latency from limitation of network bandwidth. R language, the most popular analytic tool, has a serious bottleneck, memory garbage collection, which will become even worse problem at the edge systems with limited memory resources. Processing a large amount of dynamic objects and high percentage of LLC misses with significantmiss penalty are the two key issues in the R execution environment. In this paper, we propose a Partially Parallel Garbage Collection to improve the waiting time during garbage collection; and a centralized memory allocation mechanism to reduce miss penalty that is caused by the high percentage of LLC misses. Our optimizations can bring benefits to those machine learning algorithms that spend most of time in R for processing large data list at the edge systems.en_US
dc.language.isoen_USen_US
dc.subjectData analyticsen_US
dc.subjectBig data at edgeen_US
dc.subjectR languageen_US
dc.titleAccelerating R Data Analytics in IoT Edge Systems by Memory Optimizationen_US
dc.typeProceedings Paperen_US
dc.identifier.journal2017 11TH IEEE INTERNATIONAL CONFERENCE ON APPLICATION OF INFORMATION AND COMMUNICATION TECHNOLOGIES (AICT 2017)en_US
dc.citation.spage18en_US
dc.citation.epage22en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000467077400024en_US
dc.citation.woscount0en_US
顯示於類別:會議論文