{"id":5757,"date":"2011-10-02T00:30:37","date_gmt":"2011-10-01T21:30:37","guid":{"rendered":"http:\/\/hgpu.org\/?p=5757"},"modified":"2011-10-02T00:30:37","modified_gmt":"2011-10-01T21:30:37","slug":"ptask-operating-system-abstractions-to-manage-gpus-as-compute-devices","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=5757","title":{"rendered":"PTask: Operating System Abstractions To Manage GPUs as Compute Devices"},"content":{"rendered":"<p>We propose a new set of OS abstractions to support GPUs and other accelerator devices as first class computing resources. These new abstractions, collectively called the PTask API, support a data flow programming model. Because a PTask graph consists of OS-managed objects, the kernel has sufficient visibility and control to provide system-wide guarantees like fairness and performance isolation, and can streamline data movement in ways that are impossible under current GPU programming models. Our experience developing the PTask API, along with a gestural interface on Windows 7 and a FUSE-based encrypted file system on Linux show that the PTask API can provide important systemwide guarantees where there were previously none, and can enable significant performance improvements, for example gaining a 5x improvement in maximum throughput for the gestural interface.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We propose a new set of OS abstractions to support GPUs and other accelerator devices as first class computing resources. These new abstractions, collectively called the PTask API, support a data flow programming model. Because a PTask graph consists of OS-managed objects, the kernel has sufficient visibility and control to provide system-wide guarantees like fairness [&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":[11,89,90,3],"tags":[1782,14,114,20,1175,953,974,1793,852,67,70],"class_list":["post-5757","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-opencl","category-paper","tag-computer-science","tag-cuda","tag-hlsl","tag-nvidia","tag-nvidia-geforce-gt-230","tag-nvidia-geforce-gtx-470","tag-nvidia-geforce-gtx-580","tag-opencl","tag-operating-systems","tag-performance","tag-programming-techniques"],"views":2620,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/5757","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=5757"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/5757\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5757"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5757"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5757"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}