The expanding hardware diversity in high performance computing adds enormous complexity to scientific software development. Developers who aim to write maintainable software have two options: 1) To use a so-called data locality abstraction that handles portability internally, thereby, performance-productivity becomes a trade off. Such abstractions usually come in the form of libraries, domain-specific languages, and run-time systems. 2) To use generic programming where performance, productivity and portability are subject to software design. In the direction of the second, this work describes a design approach that allows the integration of low-level and verbose programming tools into high-level generic algorithms based on template meta-programming in C++. This enables the development of performance-portable applications targeting host-device computer architectures, such as CPUs and GPUs. With a suitable design in place, the extensibility of generic algorithms to new hardware becomes a well defined procedure that can be developed in isolation from other parts of the code. That allows scientific software to be maintainable and efficient in a period of diversifying hardware in HPC. As proof of concept, a finite-difference modelling algorithm for the acoustic wave equation is developed and benchmarked using roofline model analysis on Intel Xeon Gold 6248 CPU, Nvidia Tesla V100 GPU, and AMD MI100 GPU.<\/p>\n","protected":false},"excerpt":{"rendered":"
The expanding hardware diversity in high performance computing adds enormous complexity to scientific software development. Developers who aim to write maintainable software have two options: 1) To use a so-called data locality abstraction that handles portability internally, thereby, performance-productivity becomes a trade off. Such abstractions usually come in the form of libraries, domain-specific languages, and […]<\/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":[2087,7,451,1782,14,2063,1682,20,252,176,67,1586,1300,1963],"class_list":["post-28739","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-paper","tag-amd-radeon-instinct-mi100","tag-ati","tag-benchmarking","tag-computer-science","tag-cuda","tag-hip","tag-hpc","tag-nvidia","tag-openmp","tag-package","tag-performance","tag-performance-portability","tag-portability","tag-tesla-v100"],"views":1319,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/28739","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=28739"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/28739\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=28739"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=28739"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=28739"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}