{"id":27600,"date":"2022-12-11T16:45:36","date_gmt":"2022-12-11T14:45:36","guid":{"rendered":"https:\/\/hgpu.org\/?p=27600"},"modified":"2022-12-11T16:45:36","modified_gmt":"2022-12-11T14:45:36","slug":"assessing-application-efficiency-and-performance-portability-in-single-source-programming-for-heterogeneous-parallel-systems","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=27600","title":{"rendered":"Assessing Application Efficiency and Performance Portability in Single-Source Programming for Heterogeneous Parallel Systems"},"content":{"rendered":"<p>We analyze the performance portability of the skeleton-based, single-source multi-backend high-level programming framework SkePU across multiple different CPU\u2013GPU heterogeneous systems. Thereby, we provide a systematic application efficiency characterization of SkePU-generated code in comparison to equivalent hand-written code in more low-level parallel programming models such as OpenMP and CUDA. For this purpose, we contribute ports of the STREAM benchmark suite and of a part of the NAS Parallel Benchmark suite to SkePU. We show that for STREAM and the EP benchmark, SkePU regularly scores efficiency values above 80% and in particular for CPU systems, SkePU can outperform hand-written code.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We analyze the performance portability of the skeleton-based, single-source multi-backend high-level programming framework SkePU across multiple different CPU\u2013GPU heterogeneous systems. Thereby, we provide a systematic application efficiency characterization of SkePU-generated code in comparison to equivalent hand-written code in more low-level parallel programming models such as OpenMP and CUDA. For this purpose, we contribute ports of [&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":[11,89,90,3],"tags":[451,1782,14,452,20,1793,252,176,1586,1390],"class_list":["post-27600","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-opencl","category-paper","tag-benchmarking","tag-computer-science","tag-cuda","tag-heterogeneous-systems","tag-nvidia","tag-opencl","tag-openmp","tag-package","tag-performance-portability","tag-tesla-k20"],"views":1327,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/27600","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=27600"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/27600\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=27600"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=27600"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=27600"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}