{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00149682","sets":["1164:2240:8543:8544"]},"path":["8544"],"owner":"11","recid":"149682","title":["OSCARコンパイラを用いた医用画像3Dノイズリダクションの自動マルチグレイン並列処理"],"pubdate":{"attribute_name":"公開日","attribute_value":"2016-02-23"},"_buckets":{"deposit":"030867e3-6cdd-4ab9-a2d9-b1eba14c5d49"},"_deposit":{"id":"149682","pid":{"type":"depid","value":"149682","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"OSCARコンパイラを用いた医用画像3Dノイズリダクションの自動マルチグレイン並列処理","author_link":["248289","248291","248292","248293","248288","248290","248286","248287"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"OSCARコンパイラを用いた医用画像3Dノイズリダクションの自動マルチグレイン並列処理"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"可視化/画像処理","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2016-02-23","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"早稲田大学"},{"subitem_text_value":"早稲田大学"},{"subitem_text_value":"早稲田大学"},{"subitem_text_value":"早稲田大学"},{"subitem_text_value":"早稲田大学"},{"subitem_text_value":"オリンパス株式会社"},{"subitem_text_value":"オリンパス株式会社"},{"subitem_text_value":"早稲田大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Olympus Corporation","subitem_text_language":"en"},{"subitem_text_value":"Olympus Corporation","subitem_text_language":"en"},{"subitem_text_value":"Waseda 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/149682/files/IPSJ-HPC16153011.pdf","label":"IPSJ-HPC16153011.pdf"},"date":[{"dateType":"Available","dateValue":"2018-02-23"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-HPC16153011.pdf","filesize":[{"value":"1.1 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":"14"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"39f907fc-9e72-4b6b-84c0-ff56e20ea12b","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2016 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"柴崎, 大侑"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"桑島, 昂平"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"奥村, 万里子"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"見神, 広紀"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"木村, 啓二"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"門下, 康平"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中野, 恵一"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"笠原, 博徳"}],"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":"医用画像 3 次元ノイズリダクション （3DNR） は，動画像データ内の連続するフレームを時間軸方向に分析し，動画像データに含まれるノイズ成分を検出・除去するデジタルノイズ除去手法の一種である．従来ではリアルタイム制約を守るために，3DNR 処理はハードウェアで実装されることが多かったが，近年では生産性，柔軟性の観点からソフトウェア実装が注目されてきており，ソフトウェア実装の最大の課題である実行時間の改善が求められている．また，現在のマルチコアプロセッサの普及に伴い，プログラム並列化による高速処理が有効になっている．プログラムのループ並列化は最も一般的な並列化手法として知られているが，3DNR プログラムはメニーコア実行に十分なループ並列性を持たないため，ループ並列化のみの適用では十分な性能向上は得られない．以上の背景から，本稿では 3DNR プログラムから更なる並列性を利用するための，色処理別ループ分割を用いた階層的並列化手法を提案する．3DNR プログラムに提案手法を適用することで，プログラム全域の並列性を階層的に利用したマルチグレイン並列処理を実現できる．提案手法を適用し，POWER7 ベースの 128コアSMP サーバ Hitachi SR16000 上で性能評価を行った結果，3DNR プログラムの根幹処理である動き補償及びコントラストマップ取得において，128 コア使用時に 99.86 倍の性能向上，ベクトル平滑化及び巡回 NR において，128 コア使用時に 79.64 倍の性能向上を得ることが出来た．","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":"2016-02-23","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"11","bibliographicVolumeNumber":"2016-HPC-153"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"id":149682,"updated":"2025-01-20T16:43:26.845600+00:00","links":{},"created":"2025-01-19T00:24:31.958701+00:00"}