{"id":3149,"date":"2011-03-09T14:58:55","date_gmt":"2011-03-09T14:58:55","guid":{"rendered":"http:\/\/hgpu.org\/?p=3149"},"modified":"2011-04-11T19:37:11","modified_gmt":"2011-04-11T19:37:11","slug":"benchmarking-gpu-and-cpu-codes-for-heisenberg-spin-glass-overrelaxation","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=3149","title":{"rendered":"Benchmarking GPU and CPU codes for Heisenberg spin glass overrelaxation"},"content":{"rendered":"<p>We present a set of possible implementations for Graphics Processing Units (GPU) of the Overrelaxation technique applied to the 3D Heisenberg spin glass model. The results show that a carefully tuned code can achieve more than 100 GFlops\/sec. of sustained performance and update a single spin in about 0.6 nanoseconds. A multi-hit technique that exploits the GPU shared memory further reduces this time. Such results are compared with those obtained by means of a highly-tuned vector-parallel code on latest generation multi-core CPUs.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We present a set of possible implementations for Graphics Processing Units (GPU) of the Overrelaxation technique applied to the 3D Heisenberg spin glass model. The results show that a carefully tuned code can achieve more than 100 GFlops\/sec. of sustained performance and update a single spin in about 0.6 nanoseconds. A multi-hit technique that exploits [&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":[89,3,12],"tags":[196,14,20,379,176,1783,198,199,378],"class_list":["post-3149","post","type-post","status-publish","format-standard","hentry","category-nvidia-cuda","category-paper","category-physics","tag-condensed-matter","tag-cuda","tag-nvidia","tag-nvidia-geforce-gtx-480","tag-package","tag-physics","tag-spin-systems","tag-tesla-c1060","tag-tesla-c2050"],"views":2205,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/3149","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=3149"}],"version-history":[{"count":2,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/3149\/revisions"}],"predecessor-version":[{"id":3552,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/3149\/revisions\/3552"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3149"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3149"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3149"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}