End of Moore's law?

[Jerry Feldman]

On 07/11/2010 09:36 AM, Stephen Adler wrote:
> The CPU I have in my motherboard on my desktop right now is the followi=
ng...
>
> model name    : Intel(R) Core(TM)2 Quad  CPU   Q9550  @ 2.83GHz
>
> it boasts 5665.81 Bogomips. I bought this CPU 2 years ago. As of today,=
=20
> I have no need to upgrade, or rather, I don't know what I could get in =

> the same price range (~$300) which would make it worth my time to go=20
> through the hassle of ripping out my CPU and putting a new one in. I=20
> could get a Q9550S with 12Megs of cache (instead of 8), but would my=20
> windows pop up any faster? Maybe my virtual PC's would boot up more=20
> quickly, but by how much? Would the i7 really boost my performance by a=
=20
> factor of 2?
>
> Personally, as a desktop user, I feel that Moore's law is in decline.=20
> We're stuck at 3GHz and I don't see how multi threading is going to=20
> change my desktop experience.
>
> High Performance Computing is another thing of course, but I don't run =
a=20
> data center on my desktop... :(
>  =20
Essentially desktop computer users don't really need more than a couple
of cores. It is essentially a computer that one user is using at a time.
In server space, the issues are much different.

But, Moore's law was really referring to chips and not computers.

--=20
Jerry Feldman <gaf-mNDKBlG2WHs at public.gmane.org>
Boston Linux and Unix
PGP key id: 537C5846
PGP Key fingerprint: 3D1B 8377 A3C0 A5F2 ECBB  CA3B 4607 4319 537C 5846