A simulator for microfluidic systems, based on lattice Boltzmann method (LBM) was developed for running on a Graphics Processing Unit (GPU) cluster. It was written on CUDA C language, implementing single component single phase fluids, and includes periodic, velocity, bounce-back and pressure boundary conditions. The program was run on a cluster with four node, where each node contains one quad-core CPU with 12 GB DDR3 2000 MHz memory, and four 512 cores NVIDIA GeForce GTX580, 1.5 GB GDDR5 GPUs. A simple on-line visualization program is used to follow-up the simulations, such that "on-the-flight" adjustments of the simulation parameters may be made. Our results show that interactive simulation on GPU accelerated the tuning of operational parameters of a microfluidic oscillator on the order of one tenth the time needed by an offline simulation on GPU. Given that a single GPU runs the simulator at least 30 faster than a CPU, the interactive simulator on a cluster of GPUs extends this advantage to problems on the order of tens of millions of lattice units.<\/p>\n","protected":false},"excerpt":{"rendered":"
A simulator for microfluidic systems, based on lattice Boltzmann method (LBM) was developed for running on a Graphics Processing Unit (GPU) cluster. It was written on CUDA C language, implementing single component single phase fluids, and includes periodic, velocity, bounce-back and pressure boundary conditions. The program was run on a cluster with four node, where […]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"closed","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":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[89,104,3],"tags":[14,1795,106,108,20,974,134],"class_list":["post-11270","post","type-post","status-publish","format-standard","hentry","category-nvidia-cuda","category-fluid-dynamics","category-paper","tag-cuda","tag-fluid-dynamics","tag-gpu-cluster","tag-lattice-boltzmann-model","tag-nvidia","tag-nvidia-geforce-gtx-580","tag-visualization"],"views":2527,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/11270","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=11270"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/11270\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=11270"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=11270"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=11270"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}