Does Moore's Law still apply???

[gowens]

I understand that myriad factors influence the "computing power" of microchips, but certainly the one that seems universally referred to when measuring CPU performance is MHz. It would seem that Intel has been dramatically slower in the past year in a half, since the release of the 2 GHz, of pushing the MHz envelope at the same pace we've grown acustomed to. It will be two years since I bought by 2 GHz (which wasn't the fastest at the time, it was either 2.2 or 2.4) and they'll *only* be at 3.8 by Q1 of '04??? Any thoughts?

 

[slvr_phoenix]

My thought: <A HREF="http://www.webopedia.com/TERM/M/Moores_Law.html" target="_new">Moore's Law</A> states that the number of transistors that can be fit into the same amount of space will increase, not that processor speed will increase.

Further it isn't even technically a 'law'. It's just an observation based on the past and the current trend. Like any observation it changes when that which is being observed changes. Moore's Law has already changed once. There's no reason that it can't/won't change again should things slow down (or speed up).

As for the actual concern of CPU speed, the MHz hasn't changed all that much, but the number of instructions executed per second has. And even if <i>that</i> slows down eventually, who really cares? That'll just make people's investments in PCs worth more.

<font color=blue>If you look <font color=purple>The Devil</font color=purple><font color=red>®</font color=red> straight in the eye and only see yourself then you must be standing in front of a mirror.</font color=blue>

 

[pIII_Man]

also remember that intel has increased the bus speed to 2x the speed of what your cpu is rated (i am assuming you have a 400mhz bus cpu) this dramatically increases the performance of the p4's archetecture


Proud owner of DOS 3.3

 

[FallOutBoyTonto]

Moore's Law slowed down before, I'm thinking it'll slow down again in the near future. I'm not entirely sure but when Intel was a baby, they double the amount of transistors every 12 months, then it slowed to every 18 months. Who knows, it may end up being every 24 months.

<A HREF="http://www.anandtech.com/mysystemrig.html?id=24106" target="_new">My System Rig</A>
<A HREF="http://service.futuremark.com/compare?2k3=535386" target="_new">3DMark03</A>

 

[Crashman]

Intel doesn't have the pressure they used to that would force them to push the envelope. AMD has been lagging, so Intel has been taking it easy. All these problems you hear about with Intel switching to 90nm, would have probably come up months earlier had there been some sort of race going on.

<font color=blue>Only a place as big as the internet could be home to a hero as big as Crashman!</font color=blue>
<font color=red>Only a place as big as the internet could be home to an ego as large as Crashman's!</font color=red>

 

[RRAMJET]

I'd be guessing that both makers are going to slow down in the ghz department with the arrival of 64bit to the home pc. Amd have been going down this route for a while now, and if AMD can get a 2ghz to perform on par with intels top cpus which are running at around 3ghz i'm sure intel will be doing somthing similar sooner or later.

If he doesn't die, he'll get help!!!

 

[HardWareBoss]

Like the race to 1000 Mhz.