{"id":6505,"date":"2011-12-07T11:50:47","date_gmt":"2011-12-07T09:50:47","guid":{"rendered":"http:\/\/hgpu.org\/?p=6505"},"modified":"2012-06-14T23:46:53","modified_gmt":"2012-06-14T20:46:53","slug":"efficient-two-level-preconditionined-conjugate-gradient-method-on-the-gpu","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=6505","title":{"rendered":"Efficient Two-Level Preconditionined Conjugate Gradient Method on the GPU"},"content":{"rendered":"<p>We present an implementation of Two-Level Preconditioned Conjugate Gradient Method for the GPU. We investigate a Truncated Neumann Series based preconditioner in combination with deflation and compare it with Block Incomplete Cholesky schemes. This combination exhibits fine-grain parallelism and hence we gain considerably in execution time. It&#8217;s numerical performance is also comparable to the Block Incomplete Cholesky approach. Our method provides a speedup of up to 16 times for a system of one million unknowns when compared to an optimized implementation on the CPU.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We present an implementation of Two-Level Preconditioned Conjugate Gradient Method for the GPU. We investigate a Truncated Neumann Series based preconditioner in combination with deflation and compare it with Block Incomplete Cholesky schemes. This combination exhibits fine-grain parallelism and hence we gain considerably in execution time. It&#8217;s numerical performance is also comparable to the Block [&hellip;]<\/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":[36,89,157,3],"tags":[1787,580,14,1796,20,1006],"class_list":["post-6505","post","type-post","status-publish","format-standard","hentry","category-algorithms","category-nvidia-cuda","category-mathematics","category-paper","tag-algorithms","tag-conjugate-gradient-solver","tag-cuda","tag-mathematics","tag-nvidia","tag-tesla-c2070"],"views":2261,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/6505","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=6505"}],"version-history":[{"count":1,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/6505\/revisions"}],"predecessor-version":[{"id":7744,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/6505\/revisions\/7744"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6505"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6505"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6505"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}