Re: Teraflops consumer chips by 2006

From: James Rogers (jamesr@best.com)
Date: Tue Mar 13 2001 - 00:44:31 MST


On 3/12/01 8:22 PM, "Dale Johnstone" <DaleJohnstone@email.com> wrote:
> I'm not sure how useful a graphics processor would be for general AI
> work, but I suspect it's possible to implement some kind of neural
> style processing with judicious use of texture compositing hardware in
> combination with the z-buffer (or stencil buffer).

In any case, it is largely irrelevant, as memory size/speed is far more of a
limitation on general AI than instructions per second (not strictly true if
you are trying to map biological models onto silicon, but I don't consider
that to be efficient anyway). So I don't see this chip as any substantial
breakthrough as far as AI is concerned.

> Ben: Have you thought about compressing your data before paging to/from
> disk? And why use Java anyway? Nice language to work with, but it blows
> goats in the memory use department... :)

Perhaps because minor linear improvements in memory speed and availability
don't justify the programming effort when the need is for exponentially
larger memory? No point in wasting the effort; one might as well wait for
the hardware to catch up because you'll get there about the same time for
almost the same amount of money.

-James Rogers
 jamesr@best.com



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:36 MDT