{"id":222512,"updated":"2025-01-19T13:43:11.366711+00:00","links":{},"created":"2025-01-19T01:22:27.865110+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00222512","sets":["6164:6805:6807:11063"]},"path":["11063"],"owner":"44499","recid":"222512","title":["OpenACCによる共役勾配法カーネルコードの並列化と実行性能評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-01-19"},"_buckets":{"deposit":"331b28f0-e943-4338-89e0-30d40e4bb252"},"_deposit":{"id":"222512","pid":{"type":"depid","value":"222512","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"OpenACCによる共役勾配法カーネルコードの並列化と実行性能評価","author_link":["583923","583919","583920","583922","583921","583918"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"OpenACCによる共役勾配法カーネルコードの並列化と実行性能評価"},{"subitem_title":"Parallelization and Evaluation of Conjugate Gradient Method's kernel code using OpenACC","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"C++，OpenACC，OpenMP，CUDA，共役勾配法，JSS2","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2018-01-19","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":"宇宙航空研究開発機構"},{"subitem_text_value":"宇宙航空研究開発機構"},{"subitem_text_value":"宇宙航空研究開発機構"}]},"item_18_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Japan Aerospace Exploration Agency","subitem_text_language":"en"},{"subitem_text_value":"Japan Aerospace Exploration Agency","subitem_text_language":"en"},{"subitem_text_value":"Japan Aerospace Exploration Agency","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/222512/files/IPSJ-WPRO2018025.pdf","label":"IPSJ-WPRO2018025.pdf"},"date":[{"dateType":"Available","dateValue":"2018-01-19"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-WPRO2018025.pdf","filesize":[{"value":"434.6 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"2fb696bc-447f-4c28-9315-e8dcada89290","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2018 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"川口, 優樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"宮島, 敬明"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"藤田, 直行"}],"nameIdentifiers":[{}]}]},"item_18_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yuki, Kawaguchi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takaaki, Miyajima","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Naoyuki, Fujita","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":"近年，HPC 分野では様々な並列計算機が登場しており，効率的にプログラムの並列化をする手法が検討されている．特に GPU の利用には専用開発環境 CUDA を用いる必要があるため開発の敷居が高いとされていたが，ディレクティブを記述するだけで GPU が利用可能となる OpenACC が登場した．しかしながら，OpenACC は発展途上の手法であり CUDA での実装や他の並列計算機との比較研究が少ない．本研究の目的は，連立一次方程式ソルバーの1つである共役勾配法のカーネルコードを OpenACC を用いて並列化した際の実行性能を各環境で評価することである．評価には共役勾配法のカーネルコードに対して OpenACC, OpenMP, CUDA を適用し, Xeon (Skylake), GPU (P100), FX100 環境を用いて実行性能の比較を行う. 結果，FX100 に対し OpenACC を用いた P100 の実行性能は3.6倍以上の高速化を達成した. ","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"195","bibliographic_titles":[{"bibliographic_title":"第59回プログラミング・シンポジウム予稿集"}],"bibliographicPageStart":"185","bibliographicIssueDates":{"bibliographicIssueDate":"2018-01-19","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2018"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}