カネミツ　ヒデヒロ   Hidehiro Kanemitsu   金光　永煥    所属   コンピュータサイエンス学部 コンピュータサイエンス学科    職種   専任講師
言語種別	英語
発行・発表の年月	2018/03
形態種別	国際会議論文
査読	査読あり
標題	On the Optimal Number of Computational Resources in MapReduce
執筆形態	共著
掲載誌名	Proc. of 2018 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP 2018)
掲載区分	国外
出版社・発行元	RISP
巻・号・頁	pp.311-314
著者・共著者	Hidehiro Kanemitsu and Masaki Hanada
概要	Data parallel processing such as MapReduce is becomingmore and more attractive due to its simple and effectiveparadigm for large amount of data analysis. Conventionalapplications on MapReduce have been executed at the manuallyconfigured status, e.g., the number of map/reduce slots,the size of data chunk, and so on. However, there is no guaranteethat such status is optimal for minimizing the responsetime. In this paper, we study how to derive the number ofmap/reduce slots, as well as the size of data chunk by mathematicalanalysis.