Less is Moore

© iStock.

On a guest post on IEEE Spectrum, three MIT scientists plead for more efficient code as a way of saving Moore’s Law. For decades, our ability to miniaturize components led to us doubling the number of transistors on a silicon chip every two years or so, but we’re now reaching the limits of miniaturization, and so computing performance is stagnating. What to do? Essentially, the authors say that we should be reaching for more efficient, economical and elegant code. It would seem that processor performance has supported complacency in software development, which has translated into low code efficiency and speed. As Moore’s Law becomes obsolete, if we want to make headway in the universe of artificial intelligence and robotics, we’re going to have to slim down our coding.

⇨ IEEE Spectrum, Charles E. Leiserson, Tao B. Schardl, Neil C. Thompson, “Can software performance engineering save us from the end of Moore’s law?.”