{"id":1397,"date":"2010-11-10T10:56:49","date_gmt":"2010-11-10T10:56:49","guid":{"rendered":"http:\/\/hgpu.org\/?p=1397"},"modified":"2010-11-10T10:56:49","modified_gmt":"2010-11-10T10:56:49","slug":"faster-radix-sort-via-virtual-memory-and-write-combining","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=1397","title":{"rendered":"Faster Radix Sort via Virtual Memory and Write-Combining"},"content":{"rendered":"<p>Sorting algorithms are the deciding factor for the performance of common operations such as removal of duplicates or database sort-merge joins. This work focuses on 32-bit integer keys, optionally paired with a 32-bit value. We present a fast radix sorting algorithm that builds upon a microarchitecture-aware variant of counting sort. Taking advantage of virtual memory and making use of write-combining yields a per-pass throughput corresponding to at least 88 % of the system&#8217;s peak memory bandwidth. Our implementation outperforms Intel&#8217;s recently published radix sort by a factor of 1.5. It also compares favorably to the reported performance of an algorithm for Fermi GPUs when data-transfer overhead is included. These results indicate that scalar, bandwidth-sensitive sorting algorithms remain competitive on current architectures. Various other memory-intensive applications can benefit from the techniques described herein.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Sorting algorithms are the deciding factor for the performance of common operations such as removal of duplicates or database sort-merge joins. This work focuses on 32-bit integer keys, optionally paired with a 32-bit value. We present a fast radix sorting algorithm that builds upon a microarchitecture-aware variant of counting sort. Taking advantage of virtual memory [&hellip;]<\/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":[36,11,3],"tags":[1787,1782,94,20,379,9],"class_list":["post-1397","post","type-post","status-publish","format-standard","hentry","category-algorithms","category-computer-science","category-paper","tag-algorithms","tag-computer-science","tag-data-structures-and-algorithms","tag-nvidia","tag-nvidia-geforce-gtx-480","tag-sorting"],"views":2614,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/1397","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=1397"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/1397\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1397"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1397"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1397"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}