{"id":8243,"date":"2012-09-21T14:05:05","date_gmt":"2012-09-21T11:05:05","guid":{"rendered":"http:\/\/hgpu.org\/?p=8243"},"modified":"2012-09-21T14:05:05","modified_gmt":"2012-09-21T11:05:05","slug":"autotuning-wavefront-abstractions-for-heterogeneous-architectures","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=8243","title":{"rendered":"Autotuning Wavefront Abstractions for Heterogeneous Architectures"},"content":{"rendered":"<p>We present our autotuned heterogeneous parallel programming abstraction for the wavefront pattern. An exhaustive search of the tuning space indicates that correct setting of tuning factors can average 37x speedup over a sequential baseline. Our best automated machine learning based heuristic obtains 92% of this ideal speedup, averaged across our full range of wavefront examples.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We present our autotuned heterogeneous parallel programming abstraction for the wavefront pattern. An exhaustive search of the tuning space indicates that correct setting of tuning factors can average 37x speedup over a sequential baseline. Our best automated machine learning based heuristic obtains 92% of this ideal speedup, averaged across our full range of wavefront examples.<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"open","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":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11,90,3],"tags":[7,1307,1782,452,1025,20,379,974,1793],"class_list":["post-8243","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-opencl","category-paper","tag-ati","tag-ati-radeon-hd-7970","tag-computer-science","tag-heterogeneous-systems","tag-machine-learning","tag-nvidia","tag-nvidia-geforce-gtx-480","tag-nvidia-geforce-gtx-580","tag-opencl"],"views":2055,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/8243","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=8243"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/8243\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=8243"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=8243"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=8243"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}