{"id":10522,"date":"2013-09-13T23:41:34","date_gmt":"2013-09-13T20:41:34","guid":{"rendered":"http:\/\/hgpu.org\/?p=10522"},"modified":"2013-09-13T23:41:34","modified_gmt":"2013-09-13T20:41:34","slug":"an-interface-for-halo-exchange-pattern","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=10522","title":{"rendered":"An Interface for Halo Exchange Pattern"},"content":{"rendered":"<p>Halo exchange patterns are very common in scientific computing, since the solution of PDEs often requires communication between neighbor points. Although this is a common pattern, implementations are often made by programmers from scratch, with an accompanying feeling of &quot;reinventing the wheel&quot;. In this paper we describe GCL, a C++ generic library that implements a flexible and still efficient interface to specify halo-exchange\/haloupdate operations for regular grids. GCL allows to specify data layout, processor mapping, value types, and other parameters at compile time, while other parameters are specified at run-time. GCL is also GPU enabled and we show that, somewhat surprisingly, GPU-to-GPU communication can be faster than the traditional CPUto-CPU communication, making accelerated platforms more appealing for large scale computations.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Halo exchange patterns are very common in scientific computing, since the solution of PDEs often requires communication between neighbor points. Although this is a common pattern, implementations are often made by programmers from scratch, with an accompanying feeling of &quot;reinventing the wheel&quot;. In this paper we describe GCL, a C++ generic library that implements a [&hellip;]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11,89,3],"tags":[1782,14,20,550,551,1390,1241],"class_list":["post-10522","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-paper","tag-computer-science","tag-cuda","tag-nvidia","tag-partial-differential-equations","tag-pdes","tag-tesla-k20","tag-tesla-m2090"],"views":2370,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/10522","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/users\/351"}],"replies":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=10522"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/10522\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=10522"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=10522"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=10522"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}