{"id":28156,"date":"2023-04-16T19:55:33","date_gmt":"2023-04-16T16:55:33","guid":{"rendered":"https:\/\/hgpu.org\/?p=28156"},"modified":"2023-04-16T19:55:33","modified_gmt":"2023-04-16T16:55:33","slug":"understanding-performance-portability-of-bioinformatics-applications-in-sycl-on-an-nvidia-gpu","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=28156","title":{"rendered":"Understanding Performance Portability of Bioinformatics Applications in SYCL on an NVIDIA GPU"},"content":{"rendered":"<p>Our goal is to have a better understanding of performance portability of SYCL kernels on a GPU. Toward this goal, we migrate representative kernels in bioinformatics applications from CUDA to SYCL, evaluate their performance on an NVIDIA GPU, and explain the performance gaps through performance profiling and analyses. We hope that the findings provide valuable feedback to the development of the SYCL ecosystem.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Our goal is to have a better understanding of performance portability of SYCL kernels on a GPU. Toward this goal, we migrate representative kernels in bioinformatics applications from CUDA to SYCL, evaluate their performance on an NVIDIA GPU, and explain the performance gaps through performance profiling and analyses. We hope that the findings provide valuable [&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":[11,89,3],"tags":[451,123,1782,14,452,20,176,1586,1845,1963],"class_list":["post-28156","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-paper","tag-benchmarking","tag-bioinformatics","tag-computer-science","tag-cuda","tag-heterogeneous-systems","tag-nvidia","tag-package","tag-performance-portability","tag-sycl","tag-tesla-v100"],"views":1258,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/28156","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=28156"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/28156\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=28156"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=28156"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=28156"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}