[dragontamer]

This article has a great overview, but it is dense and uses a lot of unique terminlology: https://moderngpu.github.io/join.html

In many ways, this paper is easier to read instead: http://www.csee.usf.edu/~tuy/pub/SSDBM17.pdf

But I'm pretty sure the "moderngpu" version of merge-join is more optimal.