{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00227113","sets":["1164:2240:11176:11310"]},"path":["11310"],"owner":"44499","recid":"227113","title":["Comparison of Parallel STL with C/C++ GPU Programming Models"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-07-27"},"_buckets":{"deposit":"2b1b4494-710a-4bd5-a088-43c9cb1a280e"},"_deposit":{"id":"227113","pid":{"type":"depid","value":"227113","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Comparison of Parallel STL with C/C++ GPU Programming Models","author_link":["604543","604537","604541","604542","604540","604538","604539","604544"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Comparison of Parallel STL with C/C++ GPU Programming Models"},{"subitem_title":"Comparison of Parallel STL with C/C++ GPU Programming Models","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"アクセラレータ","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-07-27","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Department of Mechanical and Aerospace Engineering, School of Engineering, Tohoku University"},{"subitem_text_value":"Cyberscience Center, Tohoku University／Graduate School of Information Sciences, Tohoku University"},{"subitem_text_value":"Cyberscience Center, Tohoku University"},{"subitem_text_value":"Cyberscience Center, Tohoku University／Graduate School of Information Sciences, Tohoku University"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Mechanical and Aerospace Engineering, School of Engineering, Tohoku University","subitem_text_language":"en"},{"subitem_text_value":"Cyberscience Center, Tohoku University / Graduate School of Information Sciences, Tohoku University","subitem_text_language":"en"},{"subitem_text_value":"Cyberscience Center, Tohoku University","subitem_text_language":"en"},{"subitem_text_value":"Cyberscience Center, Tohoku University / Graduate School of Information Sciences, Tohoku University","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/227113/files/IPSJ-HPC23190002.pdf","label":"IPSJ-HPC23190002.pdf"},"date":[{"dateType":"Available","dateValue":"2025-07-27"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-HPC23190002.pdf","filesize":[{"value":"934.0 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":"bfb2c4dd-30ff-4901-910e-ad629eb232ec","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Joanna, Imada"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Keichi, Takahashi"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yoichi, Shimomura"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroyuki, Takizawa"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Joanna, Imada","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Keichi, Takahashi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yoichi, Shimomura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroyuki, Takizawa","creatorNameLang":"en"}],"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":"The C++ 17 standard introduced a set of parallel algorithms, referred to as Parallel STL, that is designed to be programmer-friendly and portable across CPU and GPU. Several studies compared the performance between GPU programming models including Parallel STL. However, the reasons behind the performance differences are not well discussed yet. This study thus investigates what causes the performance differences among GPU programming models: CUDA, Kokkos, OpenACC, OpenMP, and Parallel STL. Three benchmarks are selected to compare the models: BabelStream, Himeno benchmark, and CloverLeaf. In BabelStream, Parallel STL achieves similar performance to other models. In the Himeno benchmark, it achieves 12% higher performance than CUDA for the large problem size. However, for the largest problem size, it performs 23% worse than CUDA. Profiling reveals that Parallel STL has a low cache hit ratio compared to other models in the larger problem sizes.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"The C++ 17 standard introduced a set of parallel algorithms, referred to as Parallel STL, that is designed to be programmer-friendly and portable across CPU and GPU. Several studies compared the performance between GPU programming models including Parallel STL. However, the reasons behind the performance differences are not well discussed yet. This study thus investigates what causes the performance differences among GPU programming models: CUDA, Kokkos, OpenACC, OpenMP, and Parallel STL. Three benchmarks are selected to compare the models: BabelStream, Himeno benchmark, and CloverLeaf. In BabelStream, Parallel STL achieves similar performance to other models. In the Himeno benchmark, it achieves 12% higher performance than CUDA for the large problem size. However, for the largest problem size, it performs 23% worse than CUDA. Profiling reveals that Parallel STL has a low cache hit ratio compared to other models in the larger problem sizes.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","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":"2023-07-27","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"2023-HPC-190"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":227113,"updated":"2025-01-19T12:16:22.841265+00:00","links":{},"created":"2025-01-19T01:26:25.645337+00:00"}