The Future of CPUs

profdlp

If you'd like to read a thoughtful article which attempts to forecast what we'll all be running in our computers a few years from now, here is a nice read.

[img]http://www.short-media.com/images/newsimages/2006/October/Alpha Die.jpg[/img]

It’s very easy to make accurate predictions about the future of technology. Stuff will get smaller, faster, and cheaper. This has been true for centuries and is unlikely to change—at least until we start running out of oil. Making interesting and accurate predictions is somewhat more difficult.

One trick employed by many futurists is to predict as many things as possible, and then remind people of the correct predictions when they happen, while brushing the less accurate predictions under the carpet. This approach works, to an extent, but isn’t much fun.

One good technique in the computing world is to look at what’s happening in the mainframe and supercomputer communities and predict that the same sorts of things will happen in the personal computer arena.

Chances are that whatever the future holds, it will be full of surprises.

Hat Tip: drasnor

Source: InformIT

Leonardo

Good article, thanks. :thumbup

mirage

I am wondering what would be the place of Transmeta's code morphing technology in the future. It was a very neat idea, imho, will it be forgotten? Combined with the multiple cores and virtualization capabilities, CPUs (especially multiple cores) can be simultaneously morphed into multiple instruction sets for different purposes.

drasnor

mirage wrote:

I am wondering what would be the place of Transmeta's code morphing technology in the future. It was a very neat idea, imho, will it be forgotten? Combined with the multiple cores and virtualization capabilities, CPUs (especially multiple cores) can be simultaneously morphed into multiple instruction sets for different purposes.

I think code morphing would be neat if the overhead was about a quarter of what it is now and if it made its way into some embedded chips. I can see an engineering MCU with code morphing being a hit as a kind of combined in-circuit simulator and hardware debugger capable of pretending to be any kind of MCU you want.

As for general purpose machines, I can't imagine anyone being interested in running code morphing when they can have the real thing, faster, and for less money. There aren't any OSes worth mentioning that won't run natively on x86 so the only people that would want code morphing are strange folk that want to run Windows on their {insert favorite non-x86 enterprise or supercomputer arch here}. Given the nature of these machines and the fact that these people are already running BSD, SCO, Solaris, or Linux; Windows and MacOS seem like odd choices. I mean, the only person I know that would use it is Geeky because he refuses to learn any of the above.

-drasnor