{"id":2666,"date":"2013-11-01T13:15:00","date_gmt":"2013-11-01T12:15:00","guid":{"rendered":"https:\/\/forschungsnetzwerk-chim.de\/?post_type=publikationen&#038;p=2666"},"modified":"2024-01-26T13:27:43","modified_gmt":"2024-01-26T12:27:43","slug":"efficient-co-processor-utilization-in-database-query-processing","status":"publish","type":"publikationen","link":"https:\/\/forschungsnetzwerk-chim.de\/en\/publications\/efficient-co-processor-utilization-in-database-query-processing\/","title":{"rendered":"Efficient co-processor utilization in database query processing"},"content":{"rendered":"\n<p id=\"sp0070\">Specialized processing units such as GPUs or FPGAs provide great opportunities to speed up database operations by exploiting\u00a0<a href=\"https:\/\/www.sciencedirect.com\/topics\/computer-science\/parallelism\">parallelism<\/a>\u00a0and relieving the\u00a0<a href=\"https:\/\/www.sciencedirect.com\/topics\/computer-science\/central-processing-unit\">CPU<\/a>. However, distributing a workload on suitable (co-)processors is a challenging task, because of the heterogeneous nature of a hybrid processor\/co-processor system. In this paper, we present a framework that automatically learns and adapts execution models for arbitrary algorithms on any (co-)processor. Our physical optimizer uses the execution models to distribute a workload of database operators on available (co-)processing devices. We demonstrate its applicability for two common use cases in modern database systems. Additionally, we contribute an overview of GPU-co-processing approaches, an in-depth discussion of our framework&#8217;s operator model, the required steps for deploying our framework in practice and the support of complex operators requiring multi-dimensional learning strategies.<\/p>\n\n<ul class=\"wp-block-list\" id=\"issue-navigation\">\n<li><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p><b>Publication:<\/b> 2013<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"_acf_changed":false},"beteiligte":[],"class_list":["post-2666","publikationen","type-publikationen","status-publish","hentry","publikationen_category-software-en"],"acf":[],"_links":{"self":[{"href":"https:\/\/forschungsnetzwerk-chim.de\/en\/wp-json\/wp\/v2\/publikationen\/2666","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/forschungsnetzwerk-chim.de\/en\/wp-json\/wp\/v2\/publikationen"}],"about":[{"href":"https:\/\/forschungsnetzwerk-chim.de\/en\/wp-json\/wp\/v2\/types\/publikationen"}],"wp:attachment":[{"href":"https:\/\/forschungsnetzwerk-chim.de\/en\/wp-json\/wp\/v2\/media?parent=2666"}],"wp:term":[{"taxonomy":"beteiligte","embeddable":true,"href":"https:\/\/forschungsnetzwerk-chim.de\/en\/wp-json\/wp\/v2\/beteiligte?post=2666"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}