{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00158260","sets":["1164:1579:8444:8624"]},"path":["8624"],"owner":"11","recid":"158260","title":["フロントエンド実行方式における高エネルギー効率なメモリ・レベル並列性の利用"],"pubdate":{"attribute_name":"公開日","attribute_value":"2016-03-17"},"_buckets":{"deposit":"6178d9a0-b0e7-4b62-9bbc-a2f9e88a7e66"},"_deposit":{"id":"158260","pid":{"type":"depid","value":"158260","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"フロントエンド実行方式における高エネルギー効率なメモリ・レベル並列性の利用","author_link":["302056","302055","302054"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"フロントエンド実行方式における高エネルギー効率なメモリ・レベル並列性の利用"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"マイクロアーキテクチャ","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2016-03-17","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"名古屋大学大学院工学研究科"},{"subitem_text_value":"名古屋大学大学院工学研究科"},{"subitem_text_value":"名古屋大学大学院工学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Engineering, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, Nagoya University","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/158260/files/IPSJ-ARC16219012.pdf","label":"IPSJ-ARC16219012.pdf"},"date":[{"dateType":"Available","dateValue":"2018-03-17"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-ARC16219012.pdf","filesize":[{"value":"453.0 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":"16"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"da04df12-377f-47b0-a256-c15b755d9721","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2016 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"出岡, 宏二郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"塩谷, 亮太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"安藤, 秀樹"}],"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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8574","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"プロセッサとメモリ間の速度差は非常に大きく，コンピュータの性能を大きく制限している．この問題を解決する方法の一つとしてメモリ・レベル並列性 （MLP: memory-level parallelism） の利用がある．本研究では高いエネルギー効率で MLP を利用する手法としてフロントエンド実行方式を拡張した continual front-end execution を提案する．フロントエンド実行方式は通常のアウト・オブ・オーダ・スーパスカラ・プロセッサのバックエンドに加え，フロントエンドにインオーダに命令を実行する実行系を持つ．フロントエンドの実行系で命令をインオーダに実行することにより，バックエンドへの命令ディスパッチをフィルタし，エネルギー効率を上げる．提案手法は，プロセッサのバックエンドが最終レベル・キャッシュ・ミスによってストールしている間，フロントエンドのみで命令実行を継続するものである．フロントエンドで命令実行を継続することにより，プログラム上で後続する LLC ミスを起こす命令を多数実行する．この継続した実行はフロントエンドでインオーダに行われる．このため，従来の MLP を利用して多数の LLC ミスを起こす命令を実行するアーキテクチャと比べると，少ない消費エネルギーで MLP を利用することができる．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告システム・アーキテクチャ（ARC）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2016-03-17","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"12","bibliographicVolumeNumber":"2016-ARC-219"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"id":158260,"updated":"2025-01-20T13:03:12.507741+00:00","links":{},"created":"2025-01-19T00:31:58.726644+00:00"}