{"id":17289,"date":"2017-06-10T11:41:47","date_gmt":"2017-06-10T08:41:47","guid":{"rendered":"https:\/\/hgpu.org\/?p=17289"},"modified":"2017-06-10T11:41:47","modified_gmt":"2017-06-10T08:41:47","slug":"crane-fast-and-migratable-gpu-passthrough-for-opencl-applications","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=17289","title":{"rendered":"Crane &#8211; Fast and Migratable GPU Passthrough for OpenCL applications"},"content":{"rendered":"<p>General purpose GPU (GPGPU) computing in virtualized environments leverages PCI passthrough to achieve GPU performance comparable to bare-metal execution. However, GPU passthrough prevents service administrators from performing virtual machine migration between physical hosts. Crane is a new technique for virtualizing OpenCL-based GPGPU computing that achieves within 5.25% of passthrough GPU performance while supporting VM migration. Crane interposes a virtualization-aware OpenCL library that makes it possible to reclaim and subsequently reassign physical GPUs to a VM without terminating the guest or its applications. Crane also enables continued GPU operation while the VM is undergoing live migration by transparently switching between GPU passthrough operation and API remoting.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>General purpose GPU (GPGPU) computing in virtualized environments leverages PCI passthrough to achieve GPU performance comparable to bare-metal execution. However, GPU passthrough prevents service administrators from performing virtual machine migration between physical hosts. Crane is a new technique for virtualizing OpenCL-based GPGPU computing that achieves within 5.25% of passthrough GPU performance while supporting VM migration. [&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":[11,90,3],"tags":[1782,20,1959,1793,167],"class_list":["post-17289","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-opencl","category-paper","tag-computer-science","tag-nvidia","tag-nvidia-grid-k1","tag-opencl","tag-virtualization"],"views":2203,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/17289","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=17289"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/17289\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=17289"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=17289"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=17289"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}