« How is the Real America Doing? | Main | Is FinTech Forcing Banking to a Tipping Point? »

April 05, 2016


Gordon Haff

>As in evolution, innovations in special-purpose chips and architectures will be increasingly important as Moore’s Law fades away.

I agree Irving. When I was an analyst I saw all these specialized architectures largely fail basically because why bother when Moore's Law would get you there in a year or two anyway? I'm not sure the implications of losing the CMOS scaling lever are as widely appreciated as they should be. (The former head of DARPA microelectronics peg them at about about a 3500X improvement over the past couple of decades; you don't lose a lever like that and just go on with business as usual.)

Pasquale Di Cesare

Turning to biology, as Irving points out, is an inspiration and a guide. Prior to possibly going to quantum computing, as at the end we live in a quantum reality, the bio-inspired system architectures are trending today. “memcomputing” (classical) approaches apparently truly overcome the von Neumann’s bottleneck architecture (CPU-memory) and computing, as our brain does, were memory is located. As Irving rightly point out, specialized architectures and chips will be increasingly important and I think this will ensure a bright future to the industry. E.g. see IBM’s TrueNorth, the developments in the frame of the European Human Brain Project’s Neuromorphic platform or the Nvidia’s P100.

The comments to this entry are closed.