Large-scale electromagnetic field simulations using the FDTD (finite-difference time-domain) method require the use of GPU (graphics processing unit) clusters. However, the communication overhead caused by slow interconnections becomes a major performance bottleneck. In this paper, as a way to remove the bottleneck, we propose the "kernel-split method" and the "host-buffer method" which overlap computation and communication for the FDTD simulation on the GPU cluster. The host-buffer method in particular enables overlapping without any modifications to the update-kernels that are already in use. We also present theoretical formulas to predict the overlap threshold and the total throughput for each method. By using our overlap methods with 6 GPU nodes, we demonstrate that the total performance of 3D FDTD reaches 92% of a six-fold increase, which is the upper limit that would be reached if there were no communication overhead.<\/p>\n","protected":false},"excerpt":{"rendered":"
Large-scale electromagnetic field simulations using the FDTD (finite-difference time-domain) method require the use of GPU (graphics processing unit) clusters. However, the communication overhead caused by slow interconnections becomes a major performance bottleneck. In this paper, as a way to remove the bottleneck, we propose the "kernel-split method" and the "host-buffer method" which overlap computation and […]<\/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":[1782,323,322,106,20,1793,1226],"class_list":["post-8250","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-opencl","category-paper","tag-computer-science","tag-fdtd","tag-finite-difference-time-domain","tag-gpu-cluster","tag-nvidia","tag-opencl","tag-tesla-c2075"],"views":2763,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/8250","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=8250"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/8250\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=8250"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=8250"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=8250"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}