Topologically aware load balancing (TALB) was originally intended to address the needs of a few high performance scientific computing researchers in the 80s who had access to “massively parallel” machines (between 8 and 1024 processors at the time). Now, with top of the line supercomputers having upwards of 1.5 million nodes and desktop computers quickly gaining cores by the dozens, TALB has become relevant to a much wider range of applications and users. In this talk I will present a brief history of the field, the three main classes of algorithms used, and some of the challenges facing the field. Lastly I will present some of my ongoing research.