{"id":22409,"date":"2020-08-02T16:04:05","date_gmt":"2020-08-02T13:04:05","guid":{"rendered":"https:\/\/hgpu.org\/?p=22409"},"modified":"2020-08-02T16:04:05","modified_gmt":"2020-08-02T13:04:05","slug":"optimizing-block-sparse-matrix-multiplications-on-cuda-with-tvm","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=22409","title":{"rendered":"Optimizing Block-Sparse Matrix Multiplications on CUDA with TVM"},"content":{"rendered":"<p>We implemented and optimized matrix multiplications between dense and block-sparse matrices on CUDA. We leveraged TVM, a deep learning compiler, to explore the schedule space of the operation and generate efficient CUDA code. With the automatic parameter tuning in TVM, our cross-thread reduction based implementation achieved competitive or better performance compared with other state-of-the-art frameworks.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We implemented and optimized matrix multiplications between dense and block-sparse matrices on CUDA. We leveraged TVM, a deep learning compiler, to explore the schedule space of the operation and generate efficient CUDA code. With the automatic parameter tuning in TVM, our cross-thread reduction based implementation achieved competitive or better performance compared with other state-of-the-art frameworks.<\/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":[1782,14,1673,1025,324,20,176,421,2064],"class_list":["post-22409","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-paper","tag-computer-science","tag-cuda","tag-deep-learning","tag-machine-learning","tag-matrix-multiplication","tag-nvidia","tag-package","tag-sparse-matrix","tag-tesla-t4"],"views":2530,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/22409","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=22409"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/22409\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=22409"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=22409"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=22409"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}