{"created":"2025-01-19T01:40:18.129393+00:00","updated":"2025-01-19T08:50:02.234534+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00237589","sets":["1164:2240:11467:11704"]},"path":["11704"],"owner":"44499","recid":"237589","title":["C++ Sender/Receiver非同期実行モデルで実装されたRed-Black SOR法のGPU上での評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-08-01"},"_buckets":{"deposit":"07e90d18-9717-47e1-8718-ad9fc640ba3c"},"_deposit":{"id":"237589","pid":{"type":"depid","value":"237589","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"C++ Sender/Receiver非同期実行モデルで実装されたRed-Black SOR法のGPU上での評価","author_link":["650631","650630"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"C++ Sender/Receiver非同期実行モデルで実装されたRed-Black SOR法のGPU上での評価"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"並列計算","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-08-01","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"大阪公立大学"},{"subitem_text_value":"大阪公立大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Osaka Metropolitan University","subitem_text_language":"en"},{"subitem_text_value":"Osaka Metropolitan 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/237589/files/IPSJ-HPC24195028.pdf","label":"IPSJ-HPC24195028.pdf"},"date":[{"dateType":"Available","dateValue":"2026-08-01"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-HPC24195028.pdf","filesize":[{"value":"430.3 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":"14"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"d2f4b215-c48f-4a26-b5ea-5a481d582966","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"田道, 竜大"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"藤本, 典幸"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10463942","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":"2188-8841","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"C++17 で導入された，Standard Template Library（STL）の拡張を用いた並列プログラミングモデル Standard Parallelism では，既存の逐次 STL コードを軽微な修正で並列化可能であるが，非同期並列処理は記述できなかった．現在策定中の C++26 で導入される見通しの Sender/Receiver モデルでは非同期並列処理が記述できる．連立一次方程式を解く反復法の一つの SOR 法を並列化する手法として Red-Black SOR 法がある．本研究では，2 次元定常熱伝導方程式を Red-Black SOR 法で解く問題を例にとり，その Sender/Receiver 実装を提案し，Sender/Receiver モデルで非同期並列実装した Red-Black SOR 法と，Standard Parallelism あるいは OpenMP を用いて同期並列実装した Red-Black SOR 法の性能を GPU 及びマルチコア CPU 上で比較する．問題サイズ 2,048×2,048 のとき，物理16 コア・論理 32 コアの AMD Ryzen 9 7950X CPU 上で実行した OpenMP 実装版と比較して，NVIDIA RTX4090 GPU 上で実行した Sender/Receiver 実装版は単精度（FP32）で約 29 倍，倍精度（FP64）で約 16 倍の高速化ができた．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"10","bibliographic_titles":[{"bibliographic_title":"研究報告ハイパフォーマンスコンピューティング（HPC）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-08-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"28","bibliographicVolumeNumber":"2024-HPC-195"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":237589,"links":{}}