{"created":"2025-01-19T01:28:46.370661+00:00","updated":"2025-01-19T11:30:59.662926+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00229549","sets":["6504:11436:11437"]},"path":["11437"],"owner":"44499","recid":"229549","title":["複数のGPU向けプログラミングモデルを用いた倍々精度疎行列ベクトル積の特性分析"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-16"},"_buckets":{"deposit":"0418f250-ffc6-43d4-8805-ef9704494ae9"},"_deposit":{"id":"229549","pid":{"type":"depid","value":"229549","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"複数のGPU向けプログラミングモデルを用いた倍々精度疎行列ベクトル積の特性分析","author_link":["617439","617442","617441","617438","617440"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"複数のGPU向けプログラミングモデルを用いた倍々精度疎行列ベクトル積の特性分析"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"コンピュータシステム","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2023-02-16","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"工学院大"},{"subitem_text_value":"工学院大"},{"subitem_text_value":"工学院大"},{"subitem_text_value":"工学院大"},{"subitem_text_value":"工学院大"}]},"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/229549/files/IPSJ-Z85-1J-07.pdf","label":"IPSJ-Z85-1J-07.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-17"}],"format":"application/pdf","filename":"IPSJ-Z85-1J-07.pdf","filesize":[{"value":"1.6 MB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"630418ad-2b98-4372-bc96-ef76d6be013f","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"寺田, 洋人"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"慈道, 亮人"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"大崎, 健太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"藤井, 昭宏"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"田中, 輝雄"}],"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_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"倍々精度演算（DD演算）は，ソフトウェアによる２つの倍精度変数を組み合わせた4倍精度相当の演算である．倍々精度演算は倍精度演算と比べ10倍から20倍の計算量を要するため，計算時間が増加する．また，疎行列ベクトル積（SpMV）はGPUによる高速化が有効である． 本研究では，ディレクティブベースのGPU向けプログラミングモデルOpenMP OffloadingとOpenACCにおいて，自動で設定される並列化の粒度が最適かどうかを調べた．比較のためにCUDAも調べた．その結果，計測する環境あるいは問題行列により，最適な粒度の位置が変化することを確認した","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"34","bibliographic_titles":[{"bibliographic_title":"第85回全国大会講演論文集"}],"bibliographicPageStart":"33","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":229549,"links":{}}