Session programming is a programming model based on the theory of session types, a typing system for pi-calculus. Session types is developed to model structured interaction between processes and correctly typed process will have the property of communication safety. Session Java (SJ) is a full implementation of session types in Java. In this project, we aim to introduce the session programming model to Axel, a heterogeneous cluster with both FPGAs and GPUs as hardware accelerators to design communication safe parallel algorithms. We give an implementation of a parallel algorithm, n-body simulation, on the Axel cluster, using SJ and FPGAs. We also give a translation of our SJ n-body simulation into C to get a higher performance. We find good performance improvements in both implementations, without compromising safety property of our program. Finally, we present a formalisation of two new multichannel SJ primitives for parallel programming. We use the formalisation to prove the correctness of our n-body implementation and generalise the proof to a ring topology used by parallel algorithms in SJ.<\/p>\n","protected":false},"excerpt":{"rendered":"
Session programming is a programming model based on the theory of session types, a typing system for pi-calculus. Session types is developed to model structured interaction between processes and correctly typed process will have the property of communication safety. Session Java (SJ) is a full implementation of session types in Java. In this project, we […]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"open","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":[36,11,89,3],"tags":[1787,1782,14,377,452,946,258,20,176,67,1803,390],"class_list":["post-5863","post","type-post","status-publish","format-standard","hentry","category-algorithms","category-computer-science","category-nvidia-cuda","category-paper","tag-algorithms","tag-computer-science","tag-cuda","tag-fpga","tag-heterogeneous-systems","tag-java","tag-n-body-simulation","tag-nvidia","tag-package","tag-performance","tag-tesla","tag-thesis"],"views":2030,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/5863","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=5863"}],"version-history":[{"count":1,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/5863\/revisions"}],"predecessor-version":[{"id":13557,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/5863\/revisions\/13557"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5863"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5863"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5863"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}