{"id":15277,"date":"2016-01-14T01:32:45","date_gmt":"2016-01-13T23:32:45","guid":{"rendered":"http:\/\/hgpu.org\/?p=15277"},"modified":"2016-01-14T01:32:45","modified_gmt":"2016-01-13T23:32:45","slug":"a-case-for-work-stealing-on-fpgas-with-opencl-atomics","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=15277","title":{"rendered":"A Case for Work-stealing on FPGAs with OpenCL Atomics"},"content":{"rendered":"<p>We provide a case study of work-stealing, a popular method for run-time load balancing, on FPGAs. Following the Cederman-Tsigas implementation for GPUs, we synchronize workitems not with locks, mutexes or critical sections, but instead with the atomic operations provided by Altera&#8217;s OpenCL SDK. We evaluate work-stealing for FPGAs by synthesizing a K-means clustering algorithm on an Altera P385 D5 board, both with work-stealing and with a statically-partitioned load. When block RAM utilization is maximized in both cases, we find that work-stealing leads to a 1.5x speedup. This demonstrates that the ability to do load balancing at run-time can outweigh the drawback of using &quot;expensive&quot; atomics on FPGAs. We hope that our case study will stimulate further research into the high-level synthesis of fine-grained, lock-free, concurrent programs.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We provide a case study of work-stealing, a popular method for run-time load balancing, on FPGAs. Following the Cederman-Tsigas implementation for GPUs, we synchronize workitems not with locks, mutexes or critical sections, but instead with the atomic operations provided by Altera&#8217;s OpenCL SDK. We evaluate work-stealing for FPGAs by synthesizing a K-means clustering algorithm on [&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":[36,11,90,3],"tags":[1787,468,1782,377,1793],"class_list":["post-15277","post","type-post","status-publish","format-standard","hentry","category-algorithms","category-computer-science","category-opencl","category-paper","tag-algorithms","tag-clustering","tag-computer-science","tag-fpga","tag-opencl"],"views":4142,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/15277","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=15277"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/15277\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=15277"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=15277"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=15277"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}