Found the CMU grad! I think this is very different from a splay tree, though. Open-address tables take advantage of the cache by removing linked lists from the data structure, which is why I think they tend to have good real-world performance.

Splay trees, on the other hand, can only really be implemented using pointers and a linked structure (splaying a tree that's been implemented with an array sounds absolutely miserable). They don't have good cache usage, which is why they generally perform poorly outside of big-O notation.