{"id":1682,"date":"2010-11-27T13:30:16","date_gmt":"2010-11-27T13:30:16","guid":{"rendered":"http:\/\/hgpu.org\/?p=1682"},"modified":"2010-11-27T13:30:16","modified_gmt":"2010-11-27T13:30:16","slug":"a-massively-parallel-adaptive-fast-multipole-method-on-heterogeneous-architectures","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=1682","title":{"rendered":"A massively parallel adaptive fast-multipole method on heterogeneous architectures"},"content":{"rendered":"<p>We present new scalable algorithms and a new implementation of our kernel-independent fast multipole method (Ying et al. ACM\/IEEE SC &#8217;03), in which we employ both distributed memory parallelism (via MPI) and shared memory\/streaming parallelism (via GPU acceleration) to rapidly evaluate two-body non-oscillatory potentials. On traditional CPU-only systems, our implementation scales well up to 30 billion unknowns on 65K cores (AMD\/CRAY-based Kraken system at NSF\/NICS) for highly non-uniform point distributions. On GPU-enabled systems, we achieve 30x speedup for problems of up to 256 million points on 256 GPUs (Lincoln at NSF\/NCSA) over a comparable CPU-only based implementations.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We present new scalable algorithms and a new implementation of our kernel-independent fast multipole method (Ying et al. ACM\/IEEE SC &#8217;03), in which we employ both distributed memory parallelism (via MPI) and shared memory\/streaming parallelism (via GPU acceleration) to rapidly evaluate two-body non-oscillatory potentials. On traditional CPU-only systems, our implementation scales well up to 30 [&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":[11,89,3],"tags":[1782,14,723,106,242,258,20,70,244],"class_list":["post-1682","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-paper","tag-computer-science","tag-cuda","tag-fast-multipole-method","tag-gpu-cluster","tag-mpi","tag-n-body-simulation","tag-nvidia","tag-programming-techniques","tag-tesla-s1070"],"views":2128,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/1682","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=1682"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/1682\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1682"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1682"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1682"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}