{"id":11952,"date":"2014-04-27T10:12:02","date_gmt":"2014-04-27T07:12:02","guid":{"rendered":"http:\/\/hgpu.org\/?p=11952"},"modified":"2014-04-27T10:12:02","modified_gmt":"2014-04-27T07:12:02","slug":"on-the-use-of-remote-gpus-and-low-power-processors-for-the-acceleration-of-scientific-applications","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=11952","title":{"rendered":"On the Use of Remote GPUs and Low-Power Processors for the Acceleration of Scientific Applications"},"content":{"rendered":"<p>Many current high-performance clusters include one or more GPUs per node in order to dramatically reduce application execution time, but the utilization of these accelerators is usually far below 100%. In this context, remote GPU virtualization can help to reduce acquisition costs as well as the overall energy consumption. In this paper, we investigate the potential overhead and bottlenecks of several &quot;heterogeneous&quot; scenarios consisting of client GPU-less nodes running CUDA applications and remote GPU-equipped server nodes providing access to NVIDIA hardware accelerators. The experimental evaluation is performed using three general-purpose multicore processors (Intel Xeon, Intel Atom and ARM Cortex A9), two graphics accelerators (NVIDIA GeForce GTX480 and NVIDIA Quadro M1000), and two relevant scientific applications (CUDASW++ and LAMMPS) arising in bioinformatics and molecular dynamics simulations.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Many current high-performance clusters include one or more GPUs per node in order to dramatically reduce application execution time, but the utilization of these accelerators is usually far below 100%. In this context, remote GPU virtualization can help to reduce acquisition costs as well as the overall energy consumption. In this paper, we investigate the [&hellip;]<\/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":[11,89,3],"tags":[123,1782,14,344,452,112,20,379,167],"class_list":["post-11952","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-paper","tag-bioinformatics","tag-computer-science","tag-cuda","tag-energy-efficient-computing","tag-heterogeneous-systems","tag-molecular-dynamics","tag-nvidia","tag-nvidia-geforce-gtx-480","tag-virtualization"],"views":2653,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/11952","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=11952"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/11952\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=11952"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=11952"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=11952"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}