Similarity search with tensor core units

Tensor Core Units (TCUs) are hardware accelerators developed for deep neural networks, which efficiently support the multiplication of two dense $$sqrt{m} imes sqrt{m}$$ matrices, where m is a given hardware parameter. In this paper, we show that TCUs can speed up similarity search problems as well. We propose algorithms for the Johnson-Lindenstrauss dimensionality reduction and for similarity join that, by leveraging TCUs, achieve a $$arOmega (sqrt{m})$$ speedup up with respect to traditional approaches.