{"id":5919,"date":"2011-10-16T16:12:25","date_gmt":"2011-10-16T13:12:25","guid":{"rendered":"http:\/\/hgpu.org\/?p=5919"},"modified":"2011-10-16T16:12:25","modified_gmt":"2011-10-16T13:12:25","slug":"asynchronous-communication-for-finite-difference-simulations-on-gpu-clusters-using-cuda-and-mpi","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=5919","title":{"rendered":"Asynchronous Communication for Finite-Difference Simulations on GPU Clusters using CUDA and MPI"},"content":{"rendered":"<p>Graphical processing Units (GPUs) are finding widespread use as accelerators in computer clusters. It is not yet trivial to program applications that use multiple GPU-enabled cluster nodes efficiently. A key aspect of this is managing effective communication between GPU memory on separate devices on separate nodes. We develop an algorithmic framework for Finite-Difference numerical simulations that would normally require highly synchronous data-parallelism so they can effectively use loosely coupled GPU-enabled cluster nodes. We employ asynchronous communications and appropriate memory overlay of computations and communications to hide latency.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Graphical processing Units (GPUs) are finding widespread use as accelerators in computer clusters. It is not yet trivial to program applications that use multiple GPU-enabled cluster nodes efficiently. A key aspect of this is managing effective communication between GPU memory on separate devices on separate nodes. We develop an algorithmic framework for Finite-Difference numerical simulations [&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":[36,11,89,3],"tags":[1787,1782,14,106,242,285,20,953,379],"class_list":["post-5919","post","type-post","status-publish","format-standard","hentry","category-algorithms","category-computer-science","category-nvidia-cuda","category-paper","tag-algorithms","tag-computer-science","tag-cuda","tag-gpu-cluster","tag-mpi","tag-numerical-simulation","tag-nvidia","tag-nvidia-geforce-gtx-470","tag-nvidia-geforce-gtx-480"],"views":1953,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/5919","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=5919"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/5919\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5919"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5919"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5919"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}