{"id":29222,"date":"2024-05-26T19:27:34","date_gmt":"2024-05-26T16:27:34","guid":{"rendered":"https:\/\/hgpu.org\/?p=29222"},"modified":"2024-05-26T19:27:34","modified_gmt":"2024-05-26T16:27:34","slug":"enabling-full-speed-random-access-to-the-entire-memory-on-the-a100-gpu","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=29222","title":{"rendered":"Enabling full-speed random access to the entire memory on the A100 GPU"},"content":{"rendered":"<p>We describe some features of the A100 memory architecture. In particular, we give a technique to reverse-engineer some hardware layout information. Using this information, we show how to avoid TLB issues to obtain full-speed random HBM access to the entire memory, as long as we constrain any particular thread to a reduced access window of less than 64GB.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We describe some features of the A100 memory architecture. In particular, we give a technique to reverse-engineer some hardware layout information. Using this information, we show how to avoid TLB issues to obtain full-speed random HBM access to the entire memory, as long as we constrain any particular thread to a reduced access window 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":[11,3],"tags":[1782,20,2066,67,193],"class_list":["post-29222","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-paper","tag-computer-science","tag-nvidia","tag-nvidia-a100","tag-performance","tag-ptx"],"views":1583,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/29222","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=29222"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/29222\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=29222"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=29222"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=29222"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}