Intel first to demonstrate working 45nm chip's..

[AMDrulZ]

http://www.tgdaily.com/2006/01/25/intel_announces_45nm_sram/

sorry if its a repost...

 

[AkumaX]

just a question: was Intel the first to have 65nm? and 90nm?

because man, that 90nm tech called Prescott sure turned heads

 

[AMDrulZ]

i think they were the first to 90nm and yes they are the first to get 65nm... but AMD's 90nm still consume's less power than intel's 65nm chip's... and as it looks now AMD's 65nm may consume less power than intels 45nm chips also...

 

[dmens]

Uh... prescott is the microprocessor, not the process. But to answer your question, yes and yes.

but AMD's 90nm still consume's less power than intel's 65nm chip's

Yeah, yonah is really burning a hole in my pants... cedarmill power is a design issue, not a process issue.

and as it looks now AMD's 65nm may consume less power than intels 45nm chips also..

How so?

 

[BrownTown]

From what I've read about Intel's process for the 45nm node it sounds like its gonna be very different than their last few revisions. They claim its the most revolutionary process since the 1960's. Anyways, whether or not it works could really make or break Intel in 2008.

 

[themusgrat]

I hope it does well, so maybe we'll have a choice of brands for a change. In any case, if AMD would stop A64s and do all Opteron 1xx for desktop, they would kill Intel.

 

[AMDrulZ]

Because of AMD and IBM announcement of a 40%increase of transistor performance from there new strained silicon process... it is different than AMD and Intel?s Current strained silicon processes... but even if it only improves performance by 20% it will still make AMD's 65nm tech to consume less power than Intel?s 45nm tech while improving the chip performance..

 

[TSS]

they would kill themselves too yields would be wayyyy too low.

 

[dmens]

OK, here's some advice.... don't listen to PR FUD, since it has very little relevance to engineering reality.

 

[TuxDave]

Originally posted by: AMDrulZ
Because of AMD and IBM announcement of a 40%increase of transistor performance from there new strained silicon process... it is different than AMD and Intel?s Current strained silicon processes... but even if it only improves performance by 20% it will still make AMD's 65nm tech to consume less power than Intel?s 45nm tech while improving the chip performance..

I think we had this debate earlier on the quote "40%" performance increase. The issue at hand was what was the baseline for comparison.

"resulting in a 40 percent increase in transistor performance compared to similar chips produced without stress technology".

So it's not a direct comparison to Intel's transistors. In fact I would like to know who they are comparing themselves with since transistor performance from outside companies is confidential information.

 

[Accord99]

Originally posted by: AMDrulZ
Because of AMD and IBM announcement of a 40%increase of transistor performance from there new strained silicon process... it is different than AMD and Intel?s Current strained silicon processes... but even if it only improves performance by 20% it will still make AMD's 65nm tech to consume less power than Intel?s 45nm tech while improving the chip performance..

Let's see if their 65nm process is able to match the 90nm Dothan's low power consumption first.

 

[AMDrulZ]

Dothan consumes less power because of a better design not a better process technology... Dothan is way way better than the Pentium 4... and AMD's turion Is very close to Dothan when it comes to power consumption.. And isn't AMD supposed to improve there power now tech this year??? So I think AMD will have just as low power consumption as Intel 45nm tech or maybe even a little better...

 

[BrownTown]

i find it unlikely that AMDs 65nm will have better power consumption then Intels 45nm. But then again they aren't really suppowed to compete against each other, AMD claims they will ahve their 45nm process out at the same time as Intel, so if they can deliver then we won't have to worry about 65nm vs 45nm.

 

[AMDrulZ]

that maybe the case i hope that AMD get's to 45nm tech when intel does also... but you have to look at some facts here... AMD's 90nm tech still comsumes less power than intel's 65nm tech.. im not 100% on this but i think it would take a 130nm AMD cpu to consume as much power as a P4 does at 65nm... that's kind of crazy if its true.. i will look into that just for the heck of it...

 

[dmens]

AMD's 90nm tech still comsumes less power than intel's 65nm tech

Um.... no?

 

[AMDrulZ]

Um Yes

http://www.xbitlabs.com/articles/cpu/display/athlon64-fx60_3.html

 

[liebremx]

Originally posted by: AMDrulZ
that maybe the case i hope that AMD get's to 45nm tech when intel does also... but you have to look at some facts here... AMD's 90nm tech still comsumes less power than intel's 65nm tech.. im not 100% on this but i think it would take a 130nm AMD cpu to consume as much power as a P4 does at 65nm... that's kind of crazy if its true.. i will look into that just for the heck of it...

You shouldn't use different products to compare processes. Instead use transistor characteristics (which I doubt are available for the 45nm process) or use the same product implemented in different processes (i.e. Prescott <-> Cedar Mill).
The reduction in gate length translates in lower power consumption and faster switching. You You can choose to have the lowest power consumption (slowest switching) or the fastest swicthing (highest power consumption). Guess how Prescott transistors are tuned?

 

[dmens]

Yeah, what liebremx said... like what I've been saying.

 

[AMDrulZ]

I know that but if you compare the power consumption or the chips AMD produces and The Chip's Intel Produces AMD seem to get more out of there process technology than Intel does. And an AMD dual core built using 90nm still has Lower power consumption then the new Intel duel core that is built using 65nm tech. The idea of the 130nm AMD chip vs. the Intel 65nm chip I admit I was a little overly exocentric on my part. so maybe when AMD does get to 65nm there chips will still draw less power than intels 45nm..

 

[dmens]

Again, process comparisons are totally meaningless if you baseline it with different designs. For example, I can make yonah draw 3-4x more power than in commercial operation by messing with some debug features. Going by your reasoning, I can take yonah-in-debug and claim 65nm sucks ass compared to dothan at 90nm.... but that comparison is obviously garbage.

 

[BrownTown]

Of course Intels Processors consume more power, they work at alot higher clockspeed, and have more transistors. In order to get a comparison that is even clsoe to fair you have to underclock the Intel processor to the same clockspeed.

 

[dexvx]

Dont you just love people who have no idea what they're talking about spew random crap?

For people who think AMD > Intel when it comes to power consumption to process technology ratio (which is a totally absurd ratio):

TDP's:
Banias, 130 nm: 29W
Northwood, 130nm: ~90W
Clawhammer, 130nm: ~80W

Dothan, 90nm: 27W
Prescott, 90nm: ~100W
San Diego, 90nm: ~60W

Yonah (DC), 65nm: ~30W
Pressler (DC), 65nm: ~130W
Toledo (DC), 90nm: ~110W

 

[PetNorth]

Intel TDP and AMD TDP is measured differently. Intel = tipical power consumption; AMD = max power consumption.

BTW, you forgot here

Dothan, 90nm: 27W
Prescott, 90nm: ~100W
San Diego, 90nm: ~60W

To mention

Turion, 90nm: ~25-35W

 

[dmens]

Originally posted by: PetNorth
Intel TDP and AMD TDP is measured differently. Intel = tipical power consumption; AMD = max power consumption.

No, TDP is defined as max power and both companies observe that definition.

 

[PetNorth]

not really