Slashdot Mirror
Intel To Produce 65-Nanometer Chips In 2005
Ridgelift writes "In keeping with Moore's Law, Intel will begin mass-producing chips using 65-nanometer process technology in 2005, according to a ZDNet article (additional coverage at EE Times and The Inquirer). Intel recently produced a Static Random Access Memory (SRAM) cell at 0.57 square microns, in comparison to 90-nanometer process measuring 1 square micron. "You can get a 40 to 50 percent increase in clock speed with no further improvements" says Intel director Mark Bohr."
What a beautifully telling Intel quote that is, "You can get a 40 to 50 percent increase in clock speed with no further improvements". Just keep ramping it up boys.
Forget thrust, drag, lift and weight. Airplanes fly because of money.
Bohr? I wonder if he really knows where the manufacturing plans are or where they're going.
First Falcon-1 to orbit, then Falcon-9. Then I can die a happy man.
Well, more like "keeping Moore's Law a self-fulfilling prediction for yet another generation of processors". ;)
In Soviet Rush, today's Tom Sawyer gets high on you.
The gate length--the distance electrons travel to get from the source to the drain on a transistor and thereby flip the transistor on--drops from 50 nanometers to 35 nanometers in 65-nanometer chips.
For all those lazy or out of condition electrons out there, they only have to travel 35 nanometers now to get some work done.
Do not try to read the dupe, thats impossible. Instead, only try to realize the truth
What truth?
There is no dupe
This smells like a another smear piece by Intel to me, kinda like paper launching the P4 Emergency Edition on AMD's rollout day for the Athlon 64.
Boo. Hiss.
"You can get a 40 to 50 percent increase in clock speed with no further improvements" says Intel director Mark Bohr."
:-)
Yeah, I get those "40 to 50 percent increase" emails all the time...I've been deleting them as fast as they come in.
Ohhhhhh...wait.... He said CLOCK, not COCK
nevermind
TDz.
So does this mean, with 60nm tech, the die can be four times as large with an increase of 500% power? If we're moving from 90nm to 60nm, in the same die size that effectively puts us at a 30% efficiency increase. Times four (heck, just add more layers if you need more circuits!)...well, I'm hoping this means we see 20Ghz chips in time for Longhorn's launch. Watch it crash in 1/5 of the time!!
Damon,
http://actionPlant.com
That was a gauntlet to the face and no mistake. AMD have just announced a new Fab in Dresden, remember, at 90nm....
Simon.
Physicists get Hadrons!
But, you'll also be incuring greated magnetic field interference. Heck, the thing will also generate more heat as driving current through smaller traces creates more "friction;" the chip might break itself simply under thermal load.
Just because you can make it smaller, doesn't mean it'll function properly. There's a theoretical limit to how small traces can go before the interference makes signaling impossible.
I can't wait to see how many processors get "down-binned" once they ramp up production with this tech. 8/
Diplomacy is the art of saying, "Nice doggie!" until you can find a rock.
If they were really thinking ahead, they should have tried for 64 nanometers. Then, when the chip size halves every few years according to Moore's law, it can stay a whole number of nanometers for a few more years yet.
I've always wondered why it's called Moore's Law. After all, it's not something which is mathematically provable. You'd figure computer scientists and systems engineers would be a bit more rigorous and call it Moore's Theorem, Moore's Axiom, or Moore's Postulate (I'm not sure what the best terminology is for this kind of conjecture). Granted, it has been approximately held, but there's no underlying reason why processor speed couldn't increase by an order of magnitude in a few months given the right implementation.
Want to improve your Karma? Instead of "Post Anonymously", try the "Post Humously" option.
50%, hmm.
doesn't Moore's law require 100% increase every 18 months? Yeah I know Moore's law isn't really about speed, but still.
Will code a sig generator for food
On an individual-gate basis, smaller gates use less power, since there's less capacitance at the gate to charge or discharge. Of course, smaller gates mean more components in a given area, which increases power consumption.
These two effects should just about cancel out, since gate capacitance increases with the square of the feature size, and the number of gates drops at the same rate.
Which leaves you with the other effects (including leakage), which are all worse with smaller gates. So, a maximum-size part will have a higher power consumption on a smaller process, but if you took an existing design (like a Pentium 4) and rebuilt it on a smaller process, you should get a lower power consumption (and smaller/cheaper die size).
-Mark
With a large enough heatsink, I could put a few slices of bread between the fins. Not only will this new CPU toast your data, but your breakfast too.
Life is not for the lazy.
It's called Moore's Law because the guy at CompUSA would get funny looks if he said Moore's Theorem. Often times you must dumb down your speech and use improper or vague terms to be understood.
Sad and true, a winning combination!
"And now let's repeat the Non-Conformist's Oath! I promise to be different! I promise to be unique! I promise not to repeat things other people say!" -- Steve Martin
"Leakage, the unintentional dissipation of electricity, among other phenomena, can also inadvertently raise memory consumption." I would have to disagree, unless they're watching Johnny Mnemonic.
Wouldn't Moore's Law have failed by now without AMD competing for market share?
http://jesus.everdense.com/
From all I have read the new AMD fab, like most any other will start out at a given process size, likely 90nm in this case, but will be ramped down so to speak. Do you really think they are buying near a billion dollars worth of equipment that isn't in any way upgradeable? Do you think Intel builds entirely new fabs for each new process and just takes the wrecking ball to the old ones?
Also given that intel still isn't shipping any quantity or anything at 90nm I take the 65nm claims with a grain* of salt.
*the process size of said grain may vary
It's called Moore's Law because the guy at CompUSA would get funny looks if he said Moore's Theorem.
The guy at CompUSA does not know of Moore's Law.
For the most part, clock speed != performance.
Yes it goes to a large part of it within the same processor family, but it doesn't scale at 1:1.
Slashdot still doesnâ(TM)t support Unicode after it was added to the HTML standard in 1997.
Status Quo not to change!
I bloody well hope not, I've forked out 35 to see them next week.
"You can make a 80% to 100% price increase without any further improvements."
paintball
Don't you mean a 65mm wafer size? Oh wait, I'm thinking of another article.
Patrick Doyle
I mod down every jackass who puts his moderation policy in his sig. Oh, wait a sec....
of course it will. Intel still seems to think that consumers care about new 32-bit chips or x86 architectures. If I were in charge of the same teams who created Itanium and Itanium II, I'd be afraid of making an attempt to be better than PowerPC too. It's stuff like this that make it even more obvious why VIA doesn't care that they can only make C3s pin-compatible with Intel chips for another 3 years. 3 years from now, intel's sockets will be irrelevant unless Intel stops sucking at introducing new features that users give a shit about.
In SOVIET RUSSIA... erm...NSA AMERICA, the Internet logs onto YOU!
The superconductor industry has detailed plans which are known set several years in advance.
If 65nm technology is possible, actual design specs have already been approved and work has already started on the design of a fab facility. So there is no speculation in the report.
You should work for Apple.
1. Approximately how many silicon atoms in a nanometer?
2. Whats the likely minimum amount of atoms that you need for a transister. Would switching materials effect that limit?
Given these two it should be easy to predict the smallest transitor size, and thus when moores law has to end.
Veramocor
The term is correct -- see here for details. Within the realms of science, a law is specifically a generalization that may be made based *on observation*. Moore was making a generalization based on past observation. He was not making a theoretical claim about the future. All this is quite proper for a law. As a matter of fact, if he was hypothesizing that processor speeds will stop doubling in the next twenty years, that would be a hypothesis, since it's not a generalization based on a body of observation.
Also, WRT your mention of a mathematician -- mathematicians are not scientists -- they are in a class of their own, along with logicians and many computer "scientists". This group works with absolutes, with provable concepts. Scientists do not do this. Science is a system designed to deal with observation and produce effective models of observed things.
May we never see th
Assuming a constant 50W/sqr.mm, that'd be 180GW of heat. Someone find me a heatsink for that baby!
biopowered.co.uk - catalytically cracking triglycerides for home automotive use since 2008. Just say no to big oil!
New from Intel: Same shit, higher clock speed (and power consumption, and cooling requirements).
Memo to Intel: "Improving" your CPUs by doing nothing but increasing their clock speeds is like "improving" a car by painting it a sickly yellow color, bolting on a ridiculous fin, and slapping Japanese-language and/or 'Type R' stickers on it.
Only morons are fooled, everyone else knows it's just a fresh coat of paint on the same outhouse.
Isn't that close to what they said about moving to .90? That, uh, didn't happen. The Prescott is coming in at over 100 watts - CASES will need to be redesigned to handle the heat output.
.65 *might* be important. All I know is .90 really didn't solve this problem for them to the extent .13 did over .18.
Intel bet their farm on being able to ramp up clock speed as opposed to making a more efficient chip (ala Opteron) and they're finding it harder to keep up. Take a look at the efficency of even a Pentium M at 1.3 GHz and you'll see why this is important - at least from a technical standpoint.
But I guess if you're whole marketing plan is based upon clock cycles,
"...Well, there's egg and bacon; egg sausage and bacon; egg and spam; egg bacon and spam; egg bacon sausage and spam..."
Just because they say, "You can get a 40 to 50 percent increase in clock speed with no further improvements," doesn't mean they aren't going to implement further improvements anyway.
Does it say in that article that the new processor will be 32 bit x-86? No. It doesn't give any specifics at all, as a matter of fact.
Intel has a very talented marketing department. Whether or not you like them as a company, you at LEAST have to admit that. This is exactly as someone else has mentioned - it is a slap in the face to AMD who, try though they might, are still drowning in red ink.
Don't berate this new manufacturing process until you have a little more info on what they're going to make with it, hm?
I worked at intel - and it is a known fact (at least it has been previously) that it is cheaper to build a completely new fab than to re-tool an existing one.
Fabs cost multiple billions, but it costs even more to dismantel and re-tool a fab for completely new machines, hardware and processes in production.
You'd figure computer scientists and systems engineers would be a bit more rigorous and call it Moore's Theorem, Moore's Axiom, or Moore's Postulate (I'm not sure what the best terminology is for this kind of conjecture)
Axiom: Unprovable assumption - basic assumption from which you build others? No.
Theorem: Result based on axioms, through a rigorous proof? No.
Postulate: Generally used about an assumption made in a proof. Like, if we postulate that result A is true, this leads to result B. No.
Law: Typically used about phenomenons deducted from reality, like e.g. laws of gravity or termodynamics. Usually, the "lawness" is traced back to a fundamental force of nature. No.
Theory: Usually a descriptive body of some field of science. Typically not used to specify individual results, such as this. No.
Hypothesis: The possible results one intends to prove/disprove. Normally only used in the context of an experiment. No.
Conjecture: Prediction of result without actual proof. Like e.g. Goldbach's Conjecture that all even numbers 4 or over is the sum of two primes. Yes.
Unfortunately, calling it a conjecture doesn't have anywhere near the power of a law. It's mostly a 100$ word for "educated guess". Not to mention they're quite rare, because most have been proven or disproven. Some also have other names for historical reasons, like Fermat's last theorem. Assuming Fermat didn't actually have a working proof, it was really a conjecture.
And at the end of the day, I think everyone can see that Moore's law has no force of law. It's been a fairly good prediction of the future, but it's all free will. If we wanted to stop Moore's "law", we could simply all stop and sing Kumba Ya for a few years.
Kjella
Live today, because you never know what tomorrow brings
My position is based on nothing more than simple counting:
- Intel achieved 250nm process technology (deschutes) in January 1998
- ... 180nm (coppermine) in October 1999, although availability was scarce until January.
- ... 130nm (northwood) in January 2002
- ... 90nm (prescott) is not out yet, although it is supposed to be out in fourth quarter 2003. I'm going to go out on a limb here and predict January 2004.
Their track record is clear: the average time between circuit size improvements is two years. Based on their history, 2005 would be a stretch, with the most likely release date falling somewhere in early 2006.You know, with better design, it shouldn't matter. If all Intel is planning to do is scale their P4 another generation then I say, 'Big Whoop!'
.15 microns as opposed to Nvidia's 'superior' .13 process. Chip efficiency isn't totally based on wire size.
Look at how the Opteron is kicking ass at only 2.2 GHz! Or for an even more painful example, look at the Pentium M at 1.3 GHz. Unbelievable performance if you want it. But Intel seems hell bent on clock frequency and that's exactly what you get with the P4 designs.
Keep in mind though, ATi totally ruled Nvidia this year with their 9800 Pro design and you know, it's only
"...Well, there's egg and bacon; egg sausage and bacon; egg and spam; egg bacon and spam; egg bacon sausage and spam..."
1 square meter is NOT 10^6 square microns.
But bonus points for being the first one to make this mistake in this thread, someone always does.
It's not wasting time, I'm educating myself.
Look at all the problems they are having with the 90nm process right now? That thing is leaking current like you wouldnt believe. Power dissapation is 90-100W. Heat is a big issue. I'm thinking something is going to have to happen to lower current bigtime. Remember thats 100W at 1.3V or so, for 77A, whereas the current P4's use 70W or so at 1.5V, for 47A.
The Doormat
If you're not outraged, then you're not paying attention.
all i'm saying is that Intel hasn't shown a recent history of engineering exellence. they've made a few advances, but nothing strikingly wonderful for the average user. They've consistently over the years shown more of an interest in high-end stuff that doesn't benefit average user. Itanium series, for example, is not something I expect to ever become a desktop processor, while I could see Opterons potentially making their way onto some desktops. Especially if *nixes become a more popular way to go, Intel is going to need a burly consumer chip to remain competitive.
In SOVIET RUSSIA... erm...NSA AMERICA, the Internet logs onto YOU!
So.. When Doom III or any other OpenGL based game comes out, will it be listed?
I'm half tempted to see what games it might list for me right now, but it doesn't seem to be available with Mozilla Firebird..
End of line..
Ack.. This is what happens when you don't pay attention to which tab out of 30 you click on.. :(
End of line..
What exactly is "cock speed?" Is that like how fast you get it up? After a certain point, won't you get dicklash? Then you'll need even more all natural male enhancement.
Gordon Moore, as in Moore's law, was co-founder of Intel. So one might say they are staying true to their roots...
Power consumed by processors is what I actually worked on for a year. This is a very hot topic in industry right now, and whoever solves it will be a rich man. Some of the startups involved:
v e.com
www.incep.com
www.volterra.com
www.integralwa
As it is, rather predictably, we have a million comments about how it all must be BS.
As opposed to chinking (!) it up?
I think, therefore I am an Atheist.
I cannot remember exactly what Moore's law states, but I think it is merely that speed doubles and cost halves every 18 months, or at least something like that. I don't think it was tied to any kind of architecture, though I could be wrong. So, based on that, how can one predict when Moore's law will end? What about new technologies? Quantum computing? Optical? And all the other cool things they think up year after year.
I recently learned that thier 3GHz processors possess 1.2nm (12Angstroms) gate oxide thickness. I'm not exactly calibrated, but it can't be more than a Si atom conected to an Oxygen connected to a Si atom conected to an Oxygen along the thickness direction. And this is *consistently* done across a 300mm wafer (~1 foot!). It's just insane!
I'm sure as hell not going to buy one. The heat issue makes me nervous, but electricity costs money. Am I going to have to call up an electriction to install a dedicated 240 volt circuit just to run a computer? I don't think so. I just don't need it that bad.
Do not make the cores any more complicated, just shrink them and run then at a lower voltage. Not put 8 to 16 cores spaced out in one package. Same power consumption, more computational power. And since you don't need to run the chips at higher voltage and frequencies, you get more yield for those extra cores.
And BTW, this is way too soon for 65 nm. I just don't believe it. Maybe by late 2006.
BTW, on your next chip set, please kill the floppy controller and just rely on the BIOS to use a USB floppy drive if someone really needs it. On my next system I'm not even going to bother putting a floppy drive in it and instead rely on flash memory. You might as well kill the serial, parallel, and PS/2 ports in the chipset and similarly rely on them connected through USB. If someone really needs the real deal then they can install a PCI card for such lagacy support. But be sure to include 1394 support just so USB isn't overly relied upon and there is an alternative.
How about introducing a decent 64bit chip by 2005. Then I'll be impressed.
You people are flamingly stupid.
You seem to have this idiotic idea that the 'best' way to get performance is to get better IPC, not more MHz. What a stupid idea. Whatever makes the processor perform better is the 'best' way.
And, stupid ass, given some static architecture XX, XX running at 3.5GHz will always be faster than XX running at 2.3GHz. No matter what your architecture you want it to run faster.
The stupidity of you assholes boggles the mind.
So let me understand what you're saying, in words I can understand. I'll paraphrase, correct me if I'm wrong:
"I'm a stupid asshole."
Did I get it right?
See, 'new 32-bit chips' are what's selling the most, by far right now. Secondly, nobody needs a 64-bit x86 compatible processor. It's a stupid idea that you filthy nerds are buying into because you're being told to. How many of you even have 2G of memory, much less 4G? Why would you need x86 compatibility when you'll need to recompile everything to see any benefit anyway, and if you're doing that you can get a Madison/PPC/UltraSparc/PA-RISC machine thats 64-bits?
Lastly, rocket surgeon, the newest Itanium processors smoke the shit out of the PPC in their intended usage models - what the hell kind of stupid are you selling, cause I ain't buyin'.
It's great accomplishment that 65 nm chips are sampling but projecting out into the future has always struck me as silly. "will produce in 2005" is rather like:
"Provided by the management for your protection."
wow, congratulations on being a fucking idiot. Perhaps you're ignoring the fact that not everyone lives in your happy little Windows-based corporate world, where an "intended use" itanium box that sucks faster than a decent PPC processor while costing exponentially more. Maybe some of us would like to see prices on new technologies come down before we die off due to old age. And how will this happen? you guessed it, mass production! How do we get mass production? by creating a demand that makes the chips we want to have become predominant in the industry! let's hear it for supply and demand. Fuck you.
In SOVIET RUSSIA... erm...NSA AMERICA, the Internet logs onto YOU!
It wasn't that informative.
It's not wasting time, I'm educating myself.