Matrix Multiplication 10x+ Speedup

Researchers at MIT’s Computer Science & Artificial Intelligence Lab (CSAIL) have open-sourced Multiply-ADDitioN-lESS (MADDNESS), an algorithm that speeds up machine learning using approximate matrix multiplication (AMM). MADDNESS requires zero multiply-add operations and runs 10x faster than other approximate methods and 100x faster than exact multiplication.

3 Likes

The first author was gracious enough to answer questions about and detail the (many, many) caveats of their approach on HN. AIUI, this is not going to be a drop-in replacement for BLAS or anything anytime soon.

2 Likes