Fawzi explained the novelty of AlphaTensor, and how it is able to improve over time despite no knowledge on existing algorithms at the start. The algorithm is able to re-discover older matrix ...

Those algorithms run up to 20% faster than existing matrix multiplication methods, according to the Alphabet unit.

AI engineers develop an algorithm that will replace floating-point multiplication with integer addition to make AI processing more efficient.

DeepMind breaks 50-year math record using AI; new record falls a week later AlphaTensor discovers better algorithms for matrix math, inspiring another improvement from afar.

By transforming operands into a Montgomery domain, these algorithms enable efficient modular multiplication and exponentiation, which are crucial for public-key cryptosystems.

Karatsuba’s divide-and-conquer multiplication algorithm takes advantage of this saving. Consider a multiplication algorithm that parallels the way multiplication of complex numbers works.

The multiplication algorithm can be nutted out by looking at the arithmetic/logic unit, or ALU. However, it’s also important to understand the role that microcode plays, too.