{"id":16934,"date":"2017-01-23T23:37:38","date_gmt":"2017-01-23T21:37:38","guid":{"rendered":"http:\/\/hgpu.org\/?p=16934"},"modified":"2017-01-23T23:37:38","modified_gmt":"2017-01-23T21:37:38","slug":"gpgpu-performance-estimation-with-core-and-memory-frequency-scaling","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=16934","title":{"rendered":"GPGPU Performance Estimation with Core and Memory Frequency Scaling"},"content":{"rendered":"<p>Graphics Processing Units (GPUs) support dynamic voltage and frequency scaling (DVFS) in order to balance computational performance and energy consumption. However, there still lacks simple and accurate performance estimation of a given GPU kernel under different frequency settings on real hardware, which is important to decide best frequency configuration for energy saving. This paper reveals a fine-grained model to estimate the execution time of GPU kernels with both core and memory frequency scaling. Over a 2.5x range of both core and memory frequencies among 12 GPU kernels, our model achieves accurate results (within 3.5%) on real hardware. Compared with the cycle-level simulators, our model only needs some simple micro-benchmark to extract a set of hardware parameters and performance counters of the kernels to produce this high accuracy.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Graphics Processing Units (GPUs) support dynamic voltage and frequency scaling (DVFS) in order to balance computational performance and energy consumption. However, there still lacks simple and accurate performance estimation of a given GPU kernel under different frequency settings on real hardware, which is important to decide best frequency configuration for energy saving. This paper reveals [&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":[11,89,32,3],"tags":[1782,14,1785,20,1650,67],"class_list":["post-16934","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-hardware","category-paper","tag-computer-science","tag-cuda","tag-hardware","tag-nvidia","tag-nvidia-geforce-gtx-980","tag-performance"],"views":4287,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/16934","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=16934"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/16934\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=16934"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=16934"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=16934"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}