March 14th, 2013 by
By Andy The
Way back in 1965 in an article for the journal Electronics, Gordon Moore predicted that transistors on an integrated circuit would double every year. Moore, the co-founder and Chairman Emeritus of Intel, later revised his prediction to a doubling every 18 months. While Moore’s Law has held true for nearly five decades, there a lot of discussion today about it coming to an end.
Intel has hit the MHz ceiling and moved to multicore devices to scale performance. Recently they announced the vertical transistor to increase density, but many argue this is only buying time and that eventually physics will prevail. We are quickly approaching process nodes will fall to the laws quantum mechanics.
Adam Sneed of the New America Foundation, posted an excellent article on theoretical physicist Michio Kaku’s compelling argument that Moore’s Law will end in 10 years. “We’re reaching the physical limits of silicon technology, and at a certain point computing power won’t improve at the rate we’ve come to expect,” he predicts.
Is he right? What will be the consequences if he is? Or, is he wrong, and there be another breakthrough like molecular computing to carry Moore’s Law into the next millennium?