[ https://issues.apache.org/jira/browse/ARROW-10899?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17360162#comment-17360162 ]
Kirill Lykov edited comment on ARROW-10899 at 6/9/21, 3:39 PM: --------------------------------------------------------------- Well, it looks like it is called "wolf sort" (https://github.com/scandum/wolfsort). I compared the implementation of Igor with Travis lsd and stable sort on uniformly distributed uint64_t from the range 0..1e9, see !uniform_1B_wolf.png! I don't know if his implementation is good/bad. I just took it and made it a bit more typed to be compiled by C++ compiler, see https://github.com/KirillLykov/int-sort-bmk/blob/wolfSortCheck/ branch if really interested was (Author: klykov): Well, it looks like it is called "wolf sort" (https://github.com/scandum/wolfsort). I compared the implementation of Igor with Travis lsd and stable sort, see !uniform_1B_wolf.png! I don't know if his implementation is good/bad. I just took it and made it a bit more typed to be compiled by C++ compiler, see https://github.com/KirillLykov/int-sort-bmk/blob/wolfSortCheck/ branch if really interested > [C++] Investigate radix sort for integer arrays > ----------------------------------------------- > > Key: ARROW-10899 > URL: https://issues.apache.org/jira/browse/ARROW-10899 > Project: Apache Arrow > Issue Type: Wish > Components: C++ > Reporter: Antoine Pitrou > Priority: Major > Attachments: Screen Shot 2021-02-09 at 17.48.13.png, Screen Shot > 2021-02-10 at 10.58.23.png, all_random_wholeRange.png, > all_random_wholeRange.png, all_random_wholeRange.png, differentdistrib.png, > uniform_1B_wolf.png > > > For integer arrays with a non-tiny range of values, we currently use a stable > sort. It may be faster to use a radix sort instead. -- This message was sent by Atlassian Jira (v8.3.4#803005)