{"updated":"2025-01-21T09:06:03.218664+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00107296","sets":["1164:1579:7406:7755"]},"path":["7755"],"owner":"11","recid":"107296","title":["Performance Analysis of MapReduce Implementations for High Performance Homology Search (Unrefereed Workshop Manuscript)"],"pubdate":{"attribute_name":"公開日","attribute_value":"2014-12-02"},"_buckets":{"deposit":"dfcdae0f-06ca-4961-b8d9-2043d59224a7"},"_deposit":{"id":"107296","pid":{"type":"depid","value":"107296","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"Performance Analysis of MapReduce Implementations for High Performance Homology Search (Unrefereed Workshop Manuscript)","author_link":["16514","16506","16508","16507","16509","16510","16515","16511","16513","16512"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Performance Analysis of MapReduce Implementations for High Performance Homology Search (Unrefereed Workshop Manuscript)"},{"subitem_title":"Performance Analysis of MapReduce Implementations for High Performance Homology Search (Unrefereed Workshop Manuscript)","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"性能評価","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2014-12-02","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Tokyo Institute of Technology"},{"subitem_text_value":"Tokyo Institute of Technology／JST CREST"},{"subitem_text_value":"Tokyo Institute of Technology"},{"subitem_text_value":"Tokyo Institute of Technology／JST CREST"},{"subitem_text_value":"Tokyo Institute of Technology／JST CREST"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Tokyo Institute of Technology / JST CREST","subitem_text_language":"en"},{"subitem_text_value":"Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Tokyo Institute of Technology / JST CREST","subitem_text_language":"en"},{"subitem_text_value":"Tokyo Institute of Technology / JST CREST","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/107296/files/IPSJ-ARC14213029.pdf"},"date":[{"dateType":"Available","dateValue":"2016-12-02"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-ARC14213029.pdf","filesize":[{"value":"1.0 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"16"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"57cc3d28-5f2d-45b5-bd17-2e16bb7c6fc0","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2014 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Chaojie, Zhang"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Koichi, Shirahata"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shuji, Suzuki"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yutaka, Akiyama"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Satoshi, Matsuoka"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Chaojie, Zhang","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Koichi, Shirahata","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shuji, Suzuki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yutaka, Akiyama","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Satoshi, Matsuoka","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10096105","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Homology search to be used in emerging bioinformatics problems such as metagenomics is of increasing importance and challenge as its application area grows more broadly while the computational complexity is increasing, thus requiring massive parallel data processing. Earlier work by some of the authors have devised novel algorithms such as GHOSTX, but the master-worker parallelization to enumerate and schedule for data processing was done with a privately developed, MPI-based master-worker framework called GHOST-MP. An alternative is to utilize the now-popular big data software substrates, such as MapReduce with abundant associated software tool-chains, but it is not clear whether the massive resource required by metagenomic homology search would not overwhelm its known limitations. By converting the GHOST-MP master-worker data processing pipeline to accommodate MapReduce, and benchmarking them on a variety of high-performance MapReduce incarnations including Hadoop and Spark, we attempt to characterize the appropriateness of MapReduce as a generic framework for metagenomics that embody extremely resource consuming requirements for both compute and data.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Homology search to be used in emerging bioinformatics problems such as metagenomics is of increasing importance and challenge as its application area grows more broadly while the computational complexity is increasing, thus requiring massive parallel data processing. Earlier work by some of the authors have devised novel algorithms such as GHOSTX, but the master-worker parallelization to enumerate and schedule for data processing was done with a privately developed, MPI-based master-worker framework called GHOST-MP. An alternative is to utilize the now-popular big data software substrates, such as MapReduce with abundant associated software tool-chains, but it is not clear whether the massive resource required by metagenomic homology search would not overwhelm its known limitations. By converting the GHOST-MP master-worker data processing pipeline to accommodate MapReduce, and benchmarking them on a variety of high-performance MapReduce incarnations including Hadoop and Spark, we attempt to characterize the appropriateness of MapReduce as a generic framework for metagenomics that embody extremely resource consuming requirements for both compute and data.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","bibliographic_titles":[{"bibliographic_title":"研究報告計算機アーキテクチャ（ARC）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2014-12-02","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"29","bibliographicVolumeNumber":"2014-ARC-213"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-18T23:50:30.124342+00:00","id":107296,"links":{}}