{"id":9491,"date":"2013-05-30T23:29:48","date_gmt":"2013-05-30T20:29:48","guid":{"rendered":"http:\/\/hgpu.org\/?p=9491"},"modified":"2013-05-30T23:29:48","modified_gmt":"2013-05-30T20:29:48","slug":"performance-tradeoff-spectrum-of-integer-and-floating-point-applications","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=9491","title":{"rendered":"Performance Tradeoff Spectrum of Integer and Floating Point Applications"},"content":{"rendered":"<p>Floating point precision and performance and the ratio of floating point units to integer processing elements on a graphics processing unit accelerator all continue to present complex tradeoffs for optimising core utilisation on modern devices. We investigate various hybrid CPU and GPU combinations using a range of different GPU models occupying different points in this tradeoff space. We analyse some performance data for a range of numerical simulation kernels and discuss their use as benchmark problems for characterising such devices.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Floating point precision and performance and the ratio of floating point units to integer processing elements on a graphics processing unit accelerator all continue to present complex tradeoffs for optimising core utilisation on modern devices. We investigate various hybrid CPU and GPU combinations using a range of different GPU models occupying different points in this [&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":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11,89,3],"tags":[451,1782,14,20,379,974,1092,1306,67,378,1006],"class_list":["post-9491","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-paper","tag-benchmarking","tag-computer-science","tag-cuda","tag-nvidia","tag-nvidia-geforce-gtx-480","tag-nvidia-geforce-gtx-580","tag-nvidia-geforce-gtx-590","tag-nvidia-geforce-gtx-680","tag-performance","tag-tesla-c2050","tag-tesla-c2070"],"views":2744,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/9491","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=9491"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/9491\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=9491"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=9491"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=9491"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}