{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00241688","sets":["1164:1579:11464:11813"]},"path":["11813"],"owner":"44499","recid":"241688","title":["Effects of Process/Thread Allocation for Optimization of Communication-Computation Overlapping in Parallel Multigrid Methods"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-12-09"},"_buckets":{"deposit":"3e5336ea-053e-4714-bae6-d50918eb0155"},"_deposit":{"id":"241688","pid":{"type":"depid","value":"241688","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Effects of Process/Thread Allocation for Optimization of Communication-Computation Overlapping in Parallel Multigrid Methods","author_link":["665808","665809"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Effects of Process/Thread Allocation for Optimization of Communication-Computation Overlapping in Parallel Multigrid Methods"},{"subitem_title":"Effects of Process/Thread Allocation for Optimization of Communication-Computation Overlapping in Parallel Multigrid Methods","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"アーキテクチャ","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-12-09","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Information Technology Center, The University of Tokyo／RIKEN, Center for Computational Science (R-CCS)"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Information Technology Center, The University of Tokyo / RIKEN, Center for Computational Science (R-CCS)","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/241688/files/IPSJ-ARC24259023.pdf","label":"IPSJ-ARC24259023.pdf"},"date":[{"dateType":"Available","dateValue":"2026-12-09"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-ARC24259023.pdf","filesize":[{"value":"544.6 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":"acd832fc-c4da-4d61-900b-60f68b818810","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":"Kengo, Nakajima"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kengo, Nakajima","creatorNameLang":"en"}],"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":"Preconditioned iterative methods based on the Krylov subspace technique are widely employed in various scientific and technical computing. When utilizing large-scale parallel computing systems, the communication overhead tends to increase with the growth in the number of nodes, making its reduction a crucial challenge. In parallel FEM/FVM, halo communication and computation overlapping (CC-Overlapping) are commonly employed, often in conjunction with the dynamic loop scheduling feature of OpenMP. In the previous work, the author proposes a method to apply CC-Overlapping to the forward and backward substitutions of the IC(0) smoother of the parallel Conjugate Gradient method preconditioned by Multigrid (MGCG). Using up to 4,096 nodes on Wisteria/BDEC-01 (Odyssey) with A64FX, performance improvement of approximately 40+% was achieved compared to the original implementation. In the present work, effects of process/thread allocation within a compute node in OpenMP/MPI Hybrid parallel programming model has been conducted for optimization of CC-Overlapping.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Preconditioned iterative methods based on the Krylov subspace technique are widely employed in various scientific and technical computing. When utilizing large-scale parallel computing systems, the communication overhead tends to increase with the growth in the number of nodes, making its reduction a crucial challenge. In parallel FEM/FVM, halo communication and computation overlapping (CC-Overlapping) are commonly employed, often in conjunction with the dynamic loop scheduling feature of OpenMP. In the previous work, the author proposes a method to apply CC-Overlapping to the forward and backward substitutions of the IC(0) smoother of the parallel Conjugate Gradient method preconditioned by Multigrid (MGCG). Using up to 4,096 nodes on Wisteria/BDEC-01 (Odyssey) with A64FX, performance improvement of approximately 40+% was achieved compared to the original implementation. In the present work, effects of process/thread allocation within a compute node in OpenMP/MPI Hybrid parallel programming model has been conducted for optimization of CC-Overlapping.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"10","bibliographic_titles":[{"bibliographic_title":"研究報告システム・アーキテクチャ（ARC）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-12-09","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"23","bibliographicVolumeNumber":"2024-ARC-259"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":241688,"updated":"2025-01-19T07:34:45.526437+00:00","links":{},"created":"2025-01-19T01:46:26.427061+00:00"}