{"_buckets": {"deposit": "ae8ebdf1-e094-40b2-b771-082e90f52cc2"}, "_deposit": {"id": "8569", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "8569"}, "status": "published"}, "_oai": {"id": "oai:nagoya.repo.nii.ac.jp:00008569"}, "item_10_alternative_title_19": {"attribute_name": "\u305d\u306e\u4ed6\u306e\u8a00\u8a9e\u306e\u30bf\u30a4\u30c8\u30eb", "attribute_value_mlt": [{"subitem_alternative_title": "Convolution Calculation for Access Pattern Analysis in Nested Loops"}]}, "item_10_biblio_info_6": {"attribute_name": "\u66f8\u8a8c\u60c5\u5831", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2002-09", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "87", "bibliographicPageStart": "77", "bibliographicVolumeNumber": "43", "bibliographic_titles": [{"bibliographic_title": "\u60c5\u5831\u51e6\u7406\u5b66\u4f1a\u8ad6\u6587\u8a8c"}]}]}, "item_10_description_4": {"attribute_name": "\u6284\u9332", "attribute_value_mlt": [{"subitem_description": "\u30eb\u30fc\u30d7\u6587\u306e\u4e26\u5217\u5b9f\u884c\u306b\u306f,\u30eb\u30fc\u30d7\u6587\u4e2d\u3067\u914d\u5217\u30c7\u30fc\u30bf\u304c\u3069\u306e\u3088\u3046\u306b\u64cd\u4f5c\u3055\u308c\u308b\u304b\u306e\u89e3\u6790\u304c\u91cd\u8981\u3067\u3042\u308b.\u73fe\u5728\u307e\u3067\u306b\u3082,\u30eb\u30fc\u30d7\u6587\u5168\u4f53\u306e\u5b9f\u884c\u306b\u304a\u3051\u308b\u914d\u5217\u30c7\u30fc\u30bf\u306e\u64cd\u4f5c\u9818\u57df\u3092\u89e3\u6790\u3059\u308b\u624b\u6cd5\u304c\u591a\u304f\u63d0\u6848\u3055\u308c\u3066\u304d\u305f.\u3057\u304b\u3057,\u3053\u308c\u3089\u306e\u624b\u6cd5\u3067\u306f\u64cd\u4f5c\u3059\u308b\u9818\u57df\u3092\u89e3\u6790\u3067\u304d\u308b\u304c,\u9818\u57df\u4e2d\u306e\u914d\u5217\u8981\u7d20\u306e\u64cd\u4f5c\u9806\u5e8f\u306a\u3069\u3092\u89e3\u6790\u3059\u308b\u3053\u3068\u306f\u3067\u304d\u306a\u3044.\u6211\u3005\u306f,\u30eb\u30fc\u30d7\u6587\u4e2d\u306e\u914d\u5217\u64cd\u4f5c\u306e\u9806\u5e8f\u3092\u8868\u73fe\u53ef\u80fd\u306a\u30a2\u30af\u30bb\u30b9\u30fb\u30d1\u30bf\u30fc\u30f3\u8868\u73fe\u3092\u63d0\u6848\u3057\u3066\u3044\u308b.\u30a2\u30af\u30bb\u30b9\u30fb\u30d1\u30bf\u30fc\u30f3\u306f\u30eb\u30fc\u30d7\u6587\u5168\u4f53\u306e\u5b9f\u884c\u3067\u64cd\u4f5c\u3055\u308c\u308b\u914d\u5217\u30c7\u30fc\u30bf\u306e\u64cd\u4f5c\u9818\u57df\u3060\u3051\u3067\u306a\u304f,\u30eb\u30fc\u30d7\u6587\u306e\u5b9f\u884c\u306b\u3068\u3082\u306a\u3044\u64cd\u4f5c\u9818\u57df\u304c\u3069\u306e\u3088\u3046\u306b\u5909\u5f62,\u79fb\u52d5\u3059\u308b\u304b\u3092\u8868\u73fe\u53ef\u80fd\u3068\u3057\u3066\u3044\u308b.\u672c\u7a3f\u3067\u306f,\u30a2\u30af\u30bb\u30b9\u30fb\u30d1\u30bf\u30fc\u30f3\u89e3\u6790\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306b\u3064\u3044\u3066\u8ff0\u3079\u308b.\u30cd\u30b9\u30c8\u3057\u305f\u30eb\u30fc\u30d7\u6587\u306b\u304a\u3044\u3066\u30a2\u30af\u30bb\u30b9\u30fb\u30d1\u30bf\u30fc\u30f3\u3092\u89e3\u6790\u3059\u308b\u305f\u3081\u306e\u7573\u8fbc\u307f\u6f14\u7b97\u3092\u5b9a\u7fa9\u3059\u308b.2\u3064\u306e\u30a2\u30af\u30bb\u30b9\u30fb\u30d1\u30bf\u30fc\u30f3\u304c\u7573\u8fbc\u307f\u53ef\u80fd\u3067\u3042\u308b\u6761\u4ef6\u3092\u793a\u3057,\u7573\u8fbc\u307f\u306b\u3088\u3063\u3066\u5f97\u3089\u308c\u308b\u30a2\u30af\u30bb\u30b9.\u30d1\u30bf\u30fc\u30f3\u306e\u8a08\u7b97\u65b9\u6cd5\u306b\u3064\u3044\u3066\u8ff0\u3079\u308b.\u7573\u8fbc\u307f\u6f14\u7b97\u3092\u5b9a\u7fa9\u3059\u308b\u3053\u3068\u3067,\u30cd\u30b9\u30c8\u3057\u305f\u30eb\u30fc\u30d7\u6587\u306b\u5bfe\u3059\u308b\u30a2\u30af\u30bb\u30b9\u30fb\u30d1\u30bf\u30fc\u30f3\u306e\u89e3\u6790\u304c\u53ef\u80fd\u3068\u306a\u308a,\u30eb\u30fc\u30d7\u6587\u306e\u6f38\u9032\u51e6\u7406\u3092\u9069\u7528\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u308b. For loop parallel processing, it is very important to analyze array manipulations in loops. Until today, many analysis methods have been proposed, in which the access region of array data in the whole loop execution is calculated. However, these methods can achieve only the access region analysis but do not take the access order of array elements into account. We have already proposed an access pattern representation in order to describe the access order of array manipulations in loops. With the access pattern representation, the movement and transformation of access region of array data according to value change of a loop variable can be analyzed correctly. In this paper, we propose an algorithm for calculating the access patterns. In order to calculate access patterns correctly in nested loops, a convolution calculation is introduced. We show conditions for application of the convolution calculation to two access patterns, and algorithm for calculating combined access patterns for nested loops. By introduction of the convolution calculation, we can apply the incremental parallel processing to nested loops appropriately.", "subitem_description_type": "Abstract"}]}, "item_10_identifier_60": {"attribute_name": "URI", "attribute_value_mlt": [{"subitem_identifier_type": "HDL", "subitem_identifier_uri": "http://hdl.handle.net/2237/10317"}]}, "item_10_publisher_32": {"attribute_name": "\u51fa\u7248\u8005", "attribute_value_mlt": [{"subitem_publisher": "\u60c5\u5831\u51e6\u7406\u5b66\u4f1a"}]}, "item_10_rights_12": {"attribute_name": "\u6a29\u5229", "attribute_value_mlt": [{"subitem_rights": "\u3053\u3053\u306b\u63b2\u8f09\u3057\u305f\u8457\u4f5c\u7269\u306e\u5229\u7528\u306b\u95a2\u3059\u308b\u6ce8\u610f \u672c\u8457\u4f5c\u7269\u306e\u8457\u4f5c\u6a29\u306f\uff08\u793e\uff09\u60c5\u5831\u51e6\u7406\u5b66\u4f1a\u306b\u5e30\u5c5e\u3057\u307e\u3059\u3002\u672c\u8457\u4f5c\u7269\u306f\u8457\u4f5c\u6a29\u8005\u3067\u3042\u308b\u60c5\u5831\u51e6\u7406\u5b66\u4f1a\u306e\u8a31\u53ef\u306e\u3082\u3068\u306b\u63b2\u8f09\u3059\u308b\u3082\u306e\u3067\u3059\u3002\u3054\u5229\u7528\u306b\u5f53\u305f\u3063\u3066\u306f\u300c\u8457\u4f5c\u6a29\u6cd5\u300d\u306a\u3089\u3073\u306b\u300c\u60c5\u5831\u51e6\u7406\u5b66\u4f1a\u502b\u7406\u7db1\u9818\u300d\u306b\u5f93\u3046\u3053\u3068\u3092\u304a\u9858\u3044\u3044\u305f\u3057\u307e\u3059\u3002 Notice for the use of this material The copyright of this material is retained by the Information Processing Society of Japan (IPSJ). This material is published on this web site with the agreement of the author (s) and the IPSJ. Please be complied with Copyright Law of Japan and the Code of Ethics of the IPSJ if any users wish to reproduce, make derivative work, distribute or make available to the public any part or whole thereof. All Rights Reserved, Copyright (C) Information Processing Society of Japan. Comments are welcome. Mail to address: \u3000editj\u003cat\u003eipsj.or.jp, please."}]}, "item_10_select_15": {"attribute_name": "\u8457\u8005\u7248\u30d5\u30e9\u30b0", "attribute_value_mlt": [{"subitem_select_item": "publisher"}]}, "item_10_source_id_7": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "03875806", "subitem_source_identifier_type": "ISSN"}]}, "item_10_text_14": {"attribute_name": "\u30d5\u30a9\u30fc\u30de\u30c3\u30c8", "attribute_value_mlt": [{"subitem_text_value": "application/pdf"}]}, "item_creator": {"attribute_name": "\u8457\u8005", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "\u671d\u5009, \u5b8f\u4e00"}], "nameIdentifiers": [{"nameIdentifier": "24123", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "ASAKURA, KOICHI"}], "nameIdentifiers": [{"nameIdentifier": "24124", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "\u6e21\u9089, \u8c4a\u82f1"}], "nameIdentifiers": [{"nameIdentifier": "24125", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "WATANABE, TOYOHIDE"}], "nameIdentifiers": [{"nameIdentifier": "24126", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "\u30d5\u30a1\u30a4\u30eb\u60c5\u5831", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2018-02-19"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "43-s6.pdf", "filesize": [{"value": "1.0 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 1000000.0, "url": {"label": "43-s6.pdf", "url": "https://nagoya.repo.nii.ac.jp/record/8569/files/43-s6.pdf"}, "version_id": "df59fe3c-9744-43b3-96c9-28915907cf66"}]}, "item_language": {"attribute_name": "\u8a00\u8a9e", "attribute_value_mlt": [{"subitem_language": "jpn"}]}, "item_resource_type": {"attribute_name": "\u8cc7\u6e90\u30bf\u30a4\u30d7", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "\u30eb\u30fc\u30d7\u6587\u30a2\u30af\u30bb\u30b9\u30fb\u30d1\u30bf\u30fc\u30f3\u89e3\u6790\u306b\u304a\u3051\u308b\u7573\u8fbc\u307f\u6f14\u7b97", "item_titles": {"attribute_name": "\u30bf\u30a4\u30c8\u30eb", "attribute_value_mlt": [{"subitem_title": "\u30eb\u30fc\u30d7\u6587\u30a2\u30af\u30bb\u30b9\u30fb\u30d1\u30bf\u30fc\u30f3\u89e3\u6790\u306b\u304a\u3051\u308b\u7573\u8fbc\u307f\u6f14\u7b97"}]}, "item_type_id": "10", "owner": "1", "path": ["320/321/322"], "permalink_uri": "http://hdl.handle.net/2237/10317", "pubdate": {"attribute_name": "\u516c\u958b\u65e5", "attribute_value": "2008-08-04"}, "publish_date": "2008-08-04", "publish_status": "0", "recid": "8569", "relation": {}, "relation_version_is_last": true, "title": ["\u30eb\u30fc\u30d7\u6587\u30a2\u30af\u30bb\u30b9\u30fb\u30d1\u30bf\u30fc\u30f3\u89e3\u6790\u306b\u304a\u3051\u308b\u7573\u8fbc\u307f\u6f14\u7b97"], "weko_shared_id": 3}