{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00074405","sets":["6164:6165:6426:6428"]},"path":["6428"],"owner":"11","recid":"74405","title":["最適なロールバック・ポイントを選択するトランザクショナル・メモリ"],"pubdate":{"attribute_name":"公開日","attribute_value":"2011-05-18"},"_buckets":{"deposit":"f4f11019-28b4-471a-8601-90af1c7af833"},"_deposit":{"id":"74405","pid":{"type":"depid","value":"74405","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"最適なロールバック・ポイントを選択するトランザクショナル・メモリ","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"最適なロールバック・ポイントを選択するトランザクショナル・メモリ"},{"subitem_title":"Transactional Memory Selecting the Optimal Rollback Point","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"メモリアーキテクチャ","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2011-05-18","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学大学院情報理工学系研究科／現在，株式会社日立製作所"},{"subitem_text_value":"名古屋大学大学院工学研究科"},{"subitem_text_value":"東京大学大学院情報理工学系研究科"},{"subitem_text_value":"東京大学大学院情報理工学系研究科"}]},"item_18_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information Science and Technology, The University of Tokyo / Presently with Hitachi, Ltd.","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, The University of Tokyo","subitem_text_language":"en"}]},"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/74405/files/IPSJ-SACSIS2011067.pdf"},"date":[{"dateType":"Available","dateValue":"2013-05-18"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SACSIS2011067.pdf","filesize":[{"value":"990.3 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"330","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"330","billingrole":"16"},{"tax":["include_tax"],"price":"330","billingrole":"11"},{"tax":["include_tax"],"price":"330","billingrole":"14"},{"tax":["include_tax"],"price":"330","billingrole":"15"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"cbf05179-61c4-4de0-8815-a00a574a32a1","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2011 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"伊藤, 悠二"},{"creatorName":"塩谷, 亮太"},{"creatorName":"五島, 正裕"},{"creatorName":"坂井, 修一"}],"nameIdentifiers":[{}]}]},"item_18_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yuji, Ito","creatorNameLang":"en"},{"creatorName":"Ryota, Shioya","creatorNameLang":"en"},{"creatorName":"Masahiro, Goshima","creatorNameLang":"en"},{"creatorName":"Shuichi, Sakai","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"並列プログラミングにおいてロックを用いない同期機構として，トランザクショナル・メモリが提案されている．トランザクションは不可分に実行されているかのように投機実行される．もし他スレッドのアクセスと競合した場合，トランザクションをロールバックし，初めから再実行する．長いトランザクションでは，ロールバックが大きなペナルティとなる．トランザクションの途中に戻る部分ロールバックを行うことでペナルティを削減できる．しかし，既存手法では，常に最適なロールバック・ポイントを選択するとは限らない．本稿では，過去に競合した命令直前で無効化しないチェックポイントを取り，ログによって最適なロールバック・ポイントを選択する手法を提案する．本手法の評価では，部分ロールバックしない場合の最大 6.9 倍の性能向上を達成できた．","subitem_description_type":"Other"}]},"item_18_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Transactional Memory is proposed for programmability and performance. A transaction is executed speculatively as if it was executed atomically. When conflicts occur, the system does a rollback and restarts the transaction. When a long transaction does a rollback, the penalty is large. Therefore, partial rollback into a transaction were proposed. However, these proposals can't always do a rollback to the optimal rollback point. In this paper, we propose transactional memory selecting the optimal rollback point. Checkpoints are taken on the past conflict instructions and are not invalidated. The optimal rollback point is selected by the log. The evaluation of the scheme which selects the optimal rollback point showed up to a 6.9 times speedup.","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"331","bibliographic_titles":[{"bibliographic_title":"先進的計算基盤システムシンポジウム論文集"}],"bibliographicPageStart":"324","bibliographicIssueDates":{"bibliographicIssueDate":"2011-05-18","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2011"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"id":74405,"updated":"2025-01-21T21:36:44.656283+00:00","links":{},"created":"2025-01-18T23:31:57.304085+00:00"}