{"updated":"2025-01-22T22:51:19.077232+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00018312","sets":["934:1119:1131:1133"]},"path":["1133"],"owner":"1","recid":"18312","title":["CPUとGPUを用いた並列GEMM演算の提案と実装"],"pubdate":{"attribute_name":"公開日","attribute_value":"2006-09-15"},"_buckets":{"deposit":"7c6bac59-a762-4f4f-9f80-e3c34daa6860"},"_deposit":{"id":"18312","pid":{"type":"depid","value":"18312","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"CPUとGPUを用いた並列GEMM演算の提案と実装","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"CPUとGPUを用いた並列GEMM演算の提案と実装"},{"subitem_title":"Proposal and Implementation of Parallel GEMM Routine Using CPU and GPU","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"数値計算","subitem_subject_scheme":"Other"}]},"item_type_id":"3","publish_date":"2006-09-15","item_3_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"電気通信大学大学院情報システム学研究科"},{"subitem_text_value":"電気通信大学大学院情報システム学研究科 / 現在，東京工業大学大学院情報理工学研究科"},{"subitem_text_value":"電気通信大学大学院情報システム学研究科"},{"subitem_text_value":" 電気通信大学大学院情報システム学研究科"}]},"item_3_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information Systems, The University of Electro-Communications","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Systems, The University of Electro-Communications / Presently with Graduate School of Information Science and Engineering, Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Systems, The University of Electro-Communications","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Systems, The University of Electro-Communications","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/18312/files/IPSJ-TACS4712028.pdf"},"date":[{"dateType":"Available","dateValue":"2008-09-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-TACS4712028.pdf","filesize":[{"value":"1.9 MB"}],"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":"11"},{"tax":["include_tax"],"price":"0","billingrole":"14"},{"tax":["include_tax"],"price":"0","billingrole":"15"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"faac2a28-e4a0-4a61-af7e-552a7f707cb9","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2006 by the Information Processing Society of Japan"}]},"item_3_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"大島, 聡史"},{"creatorName":"吉瀬, 謙二"},{"creatorName":"片桐, 孝洋"},{"creatorName":"弓場, 敏嗣"}],"nameIdentifiers":[{}]}]},"item_3_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Satoshi, Ohshima","creatorNameLang":"en"},{"creatorName":"Kenji, Kise","creatorNameLang":"en"},{"creatorName":"Takahiro, Katagiri","creatorNameLang":"en"},{"creatorName":"Toshitsugu, Yuba","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_3_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11833852","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_3_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7829","subitem_source_identifier_type":"ISSN"}]},"item_3_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"画像処理用のハードウェアであるGPU（Graphics Processing Unit）の性能向上にともない，GPUの演算能力を様々な分野で活用する研究がさかんである．我々はGPUを用いた新しい計算方式として，CPUとGPUの並列処理による数値計算方式を提案してきた．本稿では既存の数値計算ライブラリに対して計算方式を適用し，性能チューニングのための検討およびベンチマークプログラムを用いた性能評価を行った．計算方式をBLASのGEMMに適用して並列GEMMを作成し，これを用いてHPLベンチマークを実行したところ，Pentium43.0GHz単体での実行と比べて最大で1.45倍の性能を達成した．GPUによる演算が単精度であるためHPLの高速化としては問題があるものの，計算方式が現実的なアプリケーションに適用できる可能性を示すことができた．","subitem_description_type":"Other"}]},"item_3_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"GPUs for numerical computations are becoming an attractive research topics. We have proposed a new computation method of GPU, which utilizes parallel processing based on CPU and GPU. In this paper, we apply this method to existing numerical computation library. We examine a performance tuning method and execute performance experiments using a benchmark program. We also apply the method to the GEMM routine of BLAS and execute the HPL benchmark. As a result, the performance can be improved to 1. 45 times by our method, compared with a CPU only environment using Pentium 43.0GHz. There is a precision problem depending on GPU’s arithmatic precision, but we show such a potentiality that our method can be applied to various applications.","subitem_description_type":"Other"}]},"item_3_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"328","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌コンピューティングシステム（ACS）"}],"bibliographicPageStart":"317","bibliographicIssueDates":{"bibliographicIssueDate":"2006-09-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"SIG12(ACS15)","bibliographicVolumeNumber":"47"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"created":"2025-01-18T22:51:04.804623+00:00","id":18312,"links":{}}