This is integer multiplication, not matrix multiplication. The OpenAI dump also has a matrix multiplication improvement though.
In either case, no practical algorithm is expected to come from it, because the asymptotic gain isn't realized for practical input sizes--sometimes called a "galactic algorithm". But it's theoretically very interesting for breaking through a conjectured barrier.
In either case, no practical algorithm is expected to come from it, because the asymptotic gain isn't realized for practical input sizes--sometimes called a "galactic algorithm". But it's theoretically very interesting for breaking through a conjectured barrier.