{"created":"2025-01-18T22:56:49.697870+00:00","updated":"2025-01-22T19:08:59.048586+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00026123","sets":["1164:1867:1921:1923"]},"path":["1923"],"owner":"1","recid":"26123","title":["ユーザ・カーネル間の協調スケジューリング"],"pubdate":{"attribute_name":"公開日","attribute_value":"1995-08-22"},"_buckets":{"deposit":"6a716b5f-a4c4-474f-9d6f-cb5dd57d4c85"},"_deposit":{"id":"26123","pid":{"type":"depid","value":"26123","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"ユーザ・カーネル間の協調スケジューリング","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ユーザ・カーネル間の協調スケジューリング"},{"subitem_title":"Cooperative Scheduling between User and Kernel","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"1995-08-22","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"日本電気（株）C&C研究所"},{"subitem_text_value":"日本電気（株）C&C研究所"},{"subitem_text_value":"日本電気（株）C&C研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"C&C Laboratory, NEC corporation","subitem_text_language":"en"},{"subitem_text_value":"C&C Laboratory, NEC corporation","subitem_text_language":"en"},{"subitem_text_value":"C&C Laboratory, NEC corporation","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/26123/files/IPSJ-OS95070012.pdf"},"date":[{"dateType":"Available","dateValue":"1997-08-22"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-OS95070012.pdf","filesize":[{"value":"648.2 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"11"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"25bab0b7-eba0-4493-a3be-ff931aff2008","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 1995 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"相場, 雄一"},{"creatorName":"青木, 久幸"},{"creatorName":"中崎, 良成"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yuichi, Aiba","creatorNameLang":"en"},{"creatorName":"Hisayuki, Aoki","creatorNameLang":"en"},{"creatorName":"Ryousei, Nakazaki","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10444176","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":"並列機の普及に伴い、多数の並列プログラムが一度に動作できる並列OSが一般的となった。ユーザはプログラムを並列処理させるため、並列実行できる単位（タスク）を切り出す。並列OSでは、各CPUへ割り当てる処理単位（スレッド）をカーネルが用意し、ライブラリ層のスケジューラによりタスクがスレッドに割り当てられて並列処理される。しかし、カーネルとライブラリのスケジューリングが矛盾する場面が見られ、思わぬ性能低下を引き起こすことがある。そこで、性能低下の起こる場合を調べ、協調したスケジューリングを実現する方式を考察した。また、協調スケジューリングの機能をSX?3のOSに実装し、実機によって効果が測定できたのでこれを報告する。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"As multiprocessor computers are getting popular, parallel OS's are generally used on which many parallel programs can run at a time. To parallelize a program, a user devides it into tasks which can be processed in parallel. Being a parallel 0S, the kernel provides threads as CPU allocation units and tasks allocated onto the threads by a library scheduler. But, scheduling conflicts sometimes occurred between kernel and library, therefore unexpected low performance was derived. Then, we studied such a case and designed cooperative scheduling. Besides, we implemented it in SX-3 OS, and report performance data derived by evaluation on a real machine.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"96","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告システムソフトウェアとオペレーティング・システム（OS）"}],"bibliographicPageStart":"89","bibliographicIssueDates":{"bibliographicIssueDate":"1995-08-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"79(1995-OS-070)","bibliographicVolumeNumber":"1995"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"id":26123,"links":{}}