{"updated":"2025-01-20T03:08:12.647340+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00184907","sets":["934:935:8954:9278"]},"path":["9278"],"owner":"11","recid":"184907","title":["Identification and Elimination of the Overhead of Accelerate with a Super-resolution Application"],"pubdate":{"attribute_name":"公開日","attribute_value":"2017-12-12"},"_buckets":{"deposit":"dd134398-2110-4ce5-a112-f14882d3c5b2"},"_deposit":{"id":"184907","pid":{"type":"depid","value":"184907","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"Identification and Elimination of the Overhead of Accelerate with a Super-resolution Application","author_link":["409681","409677","409680","409675","409682","409678","409676","409679"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Identification and Elimination of the Overhead of Accelerate with a Super-resolution Application"},{"subitem_title":"Identification and Elimination of the Overhead of Accelerate with a Super-resolution Application","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[通常論文] GPGPU, Accelerate","subitem_subject_scheme":"Other"}]},"item_type_id":"3","publish_date":"2017-12-12","item_3_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"School of Computing, Tokyo Institute of Technology"},{"subitem_text_value":"School of Computing, Tokyo Institute of Technology"},{"subitem_text_value":"Graduate School of Engineering, Kochi University of Technology"},{"subitem_text_value":"School of Information, Kochi University of Technology"}]},"item_3_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"School of Computing, Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"School of Computing, Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, Kochi University of Technology","subitem_text_language":"en"},{"subitem_text_value":"School of Information, Kochi University of Technology","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/184907/files/IPSJ-TPRO1006002.pdf","label":"IPSJ-TPRO1006002.pdf"},"date":[{"dateType":"Available","dateValue":"2019-12-12"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-TPRO1006002.pdf","filesize":[{"value":"572.3 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"15"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"93a372ed-4a6f-4bd2-8172-1245a2f5ea7d","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2017 by the Information Processing Society of Japan"}]},"item_3_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Izumi, Asakura"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hidehiko, Masuhara"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takuya, Matsumoto"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kiminori, Matsuzaki"}],"nameIdentifiers":[{}]}]},"item_3_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Izumi, Asakura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hidehiko, Masuhara","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takuya, Matsumoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kiminori, Matsuzaki","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_3_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11464814","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":"1882-7802","subitem_source_identifier_type":"ISSN"}]},"item_3_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"This paper supplements the evaluation of libraries for parallel computing in Haskell by Matsumoto and Matsuzaki. The previous work implemented an image processing program by using two different libraries and compared expressiveness and parallel execution performance. In particular, it found that a parallel execution of the Accelerate program on a GPU is slower than the execution of the handwritten CUDA-C program by a factor of more than 70. We analyzed the execution of the Accelerate program and identified that the major sources of the overhead are in the process of the syntax tree before execution of a GPU kernel. Since the program realizes repeated execution by constructing a large syntax tree whose size is proportional to the number of repetitions, we rewrote this part by using a while-construct, which significantly reduces the overhead as it runs half as fast as the CUDA-C program. We also discuss language design alternatives for avoiding this type of overhead.\n------------------------------\nThis is a preprint of an article intended for publication Journal of\nInformation Processing(JIP). This preprint should not be cited. This\narticle should be cited as: Journal of Information Processing Vol.26(2018) (online)\n------------------------------","subitem_description_type":"Other"}]},"item_3_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper supplements the evaluation of libraries for parallel computing in Haskell by Matsumoto and Matsuzaki. The previous work implemented an image processing program by using two different libraries and compared expressiveness and parallel execution performance. In particular, it found that a parallel execution of the Accelerate program on a GPU is slower than the execution of the handwritten CUDA-C program by a factor of more than 70. We analyzed the execution of the Accelerate program and identified that the major sources of the overhead are in the process of the syntax tree before execution of a GPU kernel. Since the program realizes repeated execution by constructing a large syntax tree whose size is proportional to the number of repetitions, we rewrote this part by using a while-construct, which significantly reduces the overhead as it runs half as fast as the CUDA-C program. We also discuss language design alternatives for avoiding this type of overhead.\n------------------------------\nThis is a preprint of an article intended for publication Journal of\nInformation Processing(JIP). This preprint should not be cited. This\narticle should be cited as: Journal of Information Processing Vol.26(2018) (online)\n------------------------------","subitem_description_type":"Other"}]},"item_3_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌プログラミング（PRO）"}],"bibliographicIssueDates":{"bibliographicIssueDate":"2017-12-12","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"6","bibliographicVolumeNumber":"10"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-19T00:52:11.052149+00:00","id":184907,"links":{}}