Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

The Mile Markers of Moore's Law Are Meaningless

timothy posted about a year ago | from the we-call-this-one-petite dept.

Intel 156

szotz writes "Keeping up the pace of Moore's Law is hard, but you wouldn't know it from the way chipmakers name their technology. The semiconductor industry's names for chip generations (Intel's 22nm, TSMC's 28nm, etc) have very little to do with actual physical sizes, says IEEE Spectrum. And the disconnect is only getting bigger. For the first time, the "pay us to make your chip" foundries are offering a new process (with a smaller-sounding name) that will produce chips that are no denser than their forbears. The move is not a popular one."

cancel ×

156 comments

Sorry! There are no comments related to the filter you selected.

bad example (0)

Anonymous Coward | about a year ago | (#45295031)

If TSMC isn't keeping up with Moore's Law, that's not a problem with Moore's Law. It's a problem with TSMC.

Now if it also applied to Samsung, Hynix, IM Flash, and Toshiba-Sandisk, then it would be cause for concern.

Re:bad example (1)

stevesliva (648202) | about a year ago | (#45295323)

If TSMC isn't keeping up with Moore's Law, that's not a problem with Moore's Law. It's a problem with TSMC.

>

Waaaay towards the end of TFA, it mentions that it's GlobalFoundries who inserted finFETs into the same BEOL (wiring) as their 22nm node and called 22nm+finFET "14nm." It's buried at the end, but it's what supports the whole argument that nodes are "just marketing."

To my knowledge, the node's name was based on the DRAM half pitch. But yeah, it's not that any longer. And in defense of GlobalFoundries, finFET does literally add an extra dimension to the calculation of FET geometries.

Re:bad example (4, Interesting)

crgrace (220738) | about a year ago | (#45295477)

The problem with the transitions to finFETs is now we have an apples-to-oranges comparison between finFET (or 3D gate or whatever you want to call it) processes and surface FET processes. GlobalFoundries feels they need to stretch the truth to get the point across that the process really is better objectively, even if the minimum feature size hasn't shrunk.

It reminds me of 10 years ago when the microprocessor companies finally stopped the GHz war. For several years, clock speed was a poor proxy for microprocessor performance, and Mac fans used to scream loudly (and rightly) how the IBM chips beat Intel on real-world benchmarks while Intel touted their higher speed.

Hopefully, this "node as minimum gate width" will go away and we'll move to more meaningful process figures-of-merit such as power density, power-delay product, gm/I, transit frequency, Ioff and the like.

Re:bad example (5, Insightful)

dfghjk (711126) | about a year ago | (#45295671)

"...and Mac fans used to scream loudly (and rightly) how the IBM chips beat Intel on real-world benchmarks while Intel touted their higher speed."

Mac fans used to scream loudly about anything that made Macs look good...and still do. It's called tribalism and it isn't about being "right", it's about being on the winning team.

Apple only used an IBM "chip" once. It's clear you don't know that so it's no surprise you don't know how "rightly" Mac fans were about their screaming either. G5's were, in the balance, not faster than their Intel contemporaries. Better at some things and worse at others. One thing was clear with the G5 and it was that Apple was switching to Intel afterward.

If you asked any "Mac fan" back in the day you'd get explained to you just how superior every generation of PowerPC Mac was to any PC ever. It's surprising then, just how much better Macs got once they switched to a real processor. Macs today ARE PCs in every way yet those Mac fans still have that feeling of smug superiority. They are inherently right always, Steve told them so, they just aren't well informed.

Re:bad example (-1, Flamebait)

Austerity Empowers (669817) | about a year ago | (#45295819)

While I'm not a fan of Steve or Apple, Apple PCs are still superior PCs. It's just not in "geeky" stuff like processor speed or 3D performance which Apple has no control over, it's in some tangibles like quality and some other things that I personally don't give a shit about ("Design", "Form Factor").

I have several Mac Pro's in my home, they have been in service for 5+ years without a single need to get tech support (and I won't pay for apple care or any such thing), compared to the other name brand (Dell/HP) and no-name (new egg ala cart) options which always seem to be blowing something, usually with respect to power delivery (PSU usually, caps occasionally) or BIOS compatibility with anything modern.

The tribalism has two edges, on one hand people rant and rave over things that are probably imaginary, on the other hand to maintain that tribalism, one has to deliver a product that the tribe wants to stand behind. If our overpriced Mac's started to behave as shitty HP or Dell laptops (or god help us, Asus and points east), then that tribe would dissolve.

Re:bad example (0)

Anonymous Coward | about a year ago | (#45296667)

I put my computers behind surge protectors. I think it really makes a huge difference in terms of their longevity.

Re:bad example (1)

kylemonger (686302) | about a year ago | (#45296823)

5 years, eh? You just missed out on the previous generation workstation that experienced the coolant leak debacle, where your Powermac G5 would suddenly leak the coolant they were using down over the motherboard and power supply and then out the bottom of the chassis.

Re:bad example (0)

Macman408 (1308925) | about a year ago | (#45297423)

Only the top-of-the-line model had liquid cooling, and only a small percentage failed. I bought mine in 2005 and used it as my primary machine for 5.5 years with no issues. I then sent it to a relative, who I believe is still using it with no issues.

Any mechanical system will fail some of the time. This particular one was a catastrophic, sucky failure, to be certain. And yes, it probably happened more often than it should have; but it was far from a certain demise as you might seem to imply.

Re:bad example (-1)

Anonymous Coward | about a year ago | (#45296717)

"...and Mac fans used to scream loudly (and rightly) how the IBM chips beat Intel on real-world benchmarks while Intel touted their higher speed."

Mac fags used to scream loudly about anything that made Macs look good...and still do. It's called tribalism and it isn't about being "right", it's about being on the winning team.

Apple only used an IBM "chip" once. It's clear you don't know that so it's no surprise you don't know how "rightly" Mac fags were about their screaming either. G5's were, in the balance, not faster than their Intel contemporaries. Better at some things and worse at others. One thing was clear with the G5 and it was that Apple was switching to Intel afterward.

If you asked any Mac fag back in the day you'd get explained to you just how superior every generation of PowerPC Mac was to any PC ever. It's surprising then, just how much better Macs got once they switched to heterosexual computing. Macs today ARE PCs in every way yet those Mac fags still have that feeling of smug superiority. They are inherently right always, Steve told them so, they just aren't well informed.

FTFY.

Re:bad example (0)

Anonymous Coward | about a year ago | (#45296943)

A "real" processor? No true scotsman.

Re:bad example (1)

interval1066 (668936) | about a year ago | (#45295797)

Mac fans used to scream loudly (and rightly) how the IBM chips beat Intel...

Umm, don't you mean Motorola chips? I mean, I'm no Appel expert but I could have sworn appel was big on Motorola procs for the longest time. I always liked the flat model addressing in those...

Re:bad example (2)

crgrace (220738) | about a year ago | (#45296143)

G3 and G4 were Macs using IBM designed (largely) processors. Motorola and IBM jointly produced Power PC chips that Apple used in the mid/late 90s (G3 and G4) but Motorola eventually dropped out and IBM wasn't interested in keeping up with Intel. For a few years, the Apple chips were better than the IBM chips (I didn't own an Apple computer at the time, so I was evaluating this as an engineer). By the time Intel had closed the gap Apple wisely went over to the Intel architecture.

Re:bad example (0)

Anonymous Coward | about a year ago | (#45296981)

No, Somerset was staffed with both Motorola and IBM engineers working on microprocessor projects. This is especially true of 750 and 7400 and their derivatives.

It was IBM that dropped out of Somerset.

Re:bad example (0)

cold fjord (826450) | about a year ago | (#45296259)

It reminds me of 10 years ago when the microprocessor companies finally stopped the GHz war. For several years, clock speed was a poor proxy for microprocessor performance, and Mac fans used to scream loudly (and rightly) how the IBM chips beat Intel on real-world benchmarks while Intel touted their higher speed.

Unfortunately good marketing and mindshare tends to beat technical merit in the mass market. Even dealing with experienced engineers can be a challenge if they aren't familiar with the critical aspects for performance with the work being done. In the past I've seen repeated, somewhat heated arguments that "Linux" was faster than RISC workstations. For the work being done at the time it wasn't, not even close. The PCs running Linux didn't have the memory bandwidth, and wouldn't for a couple of years. When the cost of the workstation / server is a minor fraction of the software license cost it pays to go with the faster platform. And just because you're right doesn't mean everybody is happy. Vi or emacs, mac vs PC, Linux vs BSD, RISC vs CISC, and on, and on, and on.

Re:bad example (1)

Rockoon (1252108) | about a year ago | (#45295655)

In the middle of the article it is pointing out that Intels 22nm chips use gates that are 35nm long with channel lengths that are 30nm long, so it seems odd that people are worried about what GlobalFoundaries will be misnaming their not-yet-in-production 3D chips when Intel is already misnaming their already-in-production 3D chips.

Re:bad example (2)

smaddox (928261) | about a year ago | (#45296573)

And yet the channel width is ~8 nm, which is ~64 atomic layers. How many times do you think they can cut that in half? And does it really matter when the source and drain contacts are 10x the size of the channel itself?

Re:bad example (3, Informative)

Anonymous Coward | about a year ago | (#45296895)

To my knowledge, the node's name was based on the DRAM half pitch. But yeah, it's not that any longer. And in defense of GlobalFoundries, finFET does literally add an extra dimension to the calculation of FET geometries.

The node names are indeed based on DRAM half pitch, but CPUs haven't been made with the same process as DRAM since pitch was measured microns (eg. 0.13u).

The reality is that marketing CDs, including 32 and 22nm are only achieved through multiple patterning, and that won't change unless the industry adopts EUV or moves to a maskless process, neither of which is an economical proposition, given that the current best lightsource for EUV is a Tin vapor excimer laser, with a less than 1% dose/total energy efficiency. Part of the problem is EUV zoneplate mirrors have poor reflectivity compared to mirrors used with ArF excimer lightsources, and part of the problem is the low efficiency of the Tin vapor lasers. My prediction is that Stanford's solidstate FEL will be commercialised and used in place of excimer lasers. I'd like to see maskless litho (using DMR or DLP scanning) become a commercial reality, it will really change the market, as single dies will be manufacturable for nearly equivalent cost to volume production, but I wouldn't count on that happening too soon.

-puddingpimp

Moore's Law = Statistical Novelty (5, Interesting)

globaljustin (574257) | about a year ago | (#45295457)

You've got it switched...

If TSMC isn't keeping up with Moore's Law, that's not a problem with Moore's Law. It's a problem with TSMC.

see, when the data does not support the hypothesis, you **change the hypothesis** not how you interpret the data

Moore's Law has never been a 'law'...it was a cool statistical novelty that seemed to predict processor advancements...it is NOT and HAS NEVER BEEN fit to predict anything invovling money or resources...it's 'for fun'

I've seen Singularity/Kurzweil types in TED talks show some dumb graph of 'Moore's Law' and show how, according to the law, humans will have the processor speed to do XYZ by 2050....it's all bunk...

Using Moore's Law to make important decisions is about like using a Slashdot Poll to do the same...I don't trust people professionally who take a concept like Moore's Law and build their understanding of an industry around it. It's a common mistake of perception.

Maybe there is some sort of pattern to processor speed, but it's not helping us understand anything to be so reductive and irresponsible with how we use scientific concepts.

Re:Moore's Law = Statistical Novelty (5, Interesting)

crgrace (220738) | about a year ago | (#45295533)

Moore's Law has never been a 'law'...it was a cool statistical novelty that seemed to predict processor advancements...it is NOT and HAS NEVER BEEN fit to predict anything invovling money or resources...it's 'for fun'

I disagree with you a bit here. Moore's Law is an observation, sure, but to engineers that understand the assumptions that go into Moore's Law it has been extremely useful for making predictions involving money and resources.

At my last job I worked in an advanced development/product group working on CMOS wireless transceivers for basestations and handsets. We used Moore's Law explicitly in our planning. The IC business is brutal and you have very little room to miss your market windows. With multi-year development cycles this is tough. Therefore, like a duck hunter, you have to shoot where the technology is going to be, not where it is.

Basically, we started the design using a CMOS process that wasn't on the market yet. We were confident that it *would be* by the time we were ready to go to market. We were confident because the availability of that process was predicted by Moore's Law and any number of foundries were spending billions to make it happen.

If we hadn't used Moore's Law in our planning, we would have come out with products using two-year old technology, and our competition would have eaten our lunch.

question: did you *only* use Moore's Law? (1)

globaljustin (574257) | about a year ago | (#45296003)

hey thanks for the response

We were confident because the availability of that process was predicted by Moore's Law and any number of foundries were spending billions to make it happen.

Right, so did you just use Moore's Law or did you look at other factors as well?

What I mean by other factors:

> Trends of the capacity of other recent products? Did you look at teh speeds of CMOS processes from that company over the last 10 years and extrapolate?

> Did you talk to a sales rep or engineer or product development manager at the CMOS process company and **ASK THEM** how fast their upcomming models would be (approximately)

> Do literature review of what academic research groups and possible FOSS (idk if it applies for you) were doing in that CMOS wireless type transciever tech? My former university, Ball State University did research for WiMax coverage and speed for Cisco (before WiMax was ditched)...did you look at any of that to predict the CMOS process capability you needed?

I'm trying to be polite, but I call BS.

If you claim your company made that decision based **soley** on math from Moore's Law....well I have a hard time believe that claim's veracity. You are either fabricating or that company is not very wise. And if you company **did** use other factors, then that kind of invalidates your point and parenthetically supportsy my point...I won't deny that using it **might** have added value, but only IF you also did common practices like I mentioned above...

Seriously...did you use other factors besides Moore's Law?

Like asking the vendor? (or any of the others mentioned above)

Re:question: did you *only* use Moore's Law? (2)

crgrace (220738) | about a year ago | (#45296239)

hey thanks for the response

We were confident because the availability of that process was predicted by Moore's Law and any number of foundries were spending billions to make it happen.

Right, so did you just use Moore's Law or did you look at other factors as well?

What I mean by other factors:

> Trends of the capacity of other recent products? Did you look at teh speeds of CMOS processes from that company over the last 10 years and extrapolate?

> Did you talk to a sales rep or engineer or product development manager at the CMOS process company and **ASK THEM** how fast their upcomming models would be (approximately)

> Do literature review of what academic research groups and possible FOSS (idk if it applies for you) were doing in that CMOS wireless type transciever tech? My former university, Ball State University did research for WiMax coverage and speed for Cisco (before WiMax was ditched)...did you look at any of that to predict the CMOS process capability you needed?

I'm trying to be polite, but I call BS.

If you claim your company made that decision based **soley** on math from Moore's Law....well I have a hard time believe that claim's veracity. You are either fabricating or that company is not very wise. And if you company **did** use other factors, then that kind of invalidates your point and parenthetically supportsy my point...I won't deny that using it **might** have added value, but only IF you also did common practices like I mentioned above...

Seriously...did you use other factors besides Moore's Law?

Like asking the vendor? (or any of the others mentioned above)

Of course we used all kinds of inputs into our planning process. We would have been fools not to.

I feel like you're doing a bit of "move the goal posts" here. First you very emphatically state that "[Moore's Law] is NOT and HAS NEVER BEEN fit to predict anything invovling money or resources"

I gave you a reply from experience that that is not true, and in fact companies do use (or at least used to) use Moore's Law in their planning process (where money and resources are involved).

Now you saying I'm claiming my company invested millions blindly because we had some faith in Moore's Law. Of course we didn't, and I don't think I implied that.

First off, looking at the speed improvements from the foundry over the last 10 years as evidence is pretty much the same thing as following Moore's Law.

Second, as I'm sure you know, sales reps will say "YES" to anything, so Moore's Law helps put things in context. If they are saying something way better than Moore's Law, you have to be skeptical.

Basically, I disagree that the fact that we used a variety of factors (like virtually any company will do for any decision) invalidates my point. You said that Moore's Law isn't fit for predicting things. I disagree.

If you would have said "Moore's Law isn't fit for making significant investments in the absence of other factors or critical thinking" then I would agree with you.

Re:question: did you *only* use Moore's Law? (0)

Anonymous Coward | about a year ago | (#45296319)

I'm not the OP, however I believe you are both being rather fair. I look at singularity theories and draw the conclusion that if they rely so heavily upon moore's law then the singularity has begun and extrapolation towards some magic type AI is not likely helpful - a possibility maybe, fun - sure, a creative brainstorm - absolutely, a cure for mortality - not quite.

Re:question: did you *only* use Moore's Law? (0)

Anonymous Coward | about a year ago | (#45296947)

To be fair, Kurzweil doesn't base his theory just on Moore's Law, he bases it on the overall history of technological advancement. This advancement has been happening in a roughly exponential path, over the course of human history.

The truth is, if technology continues along that path, Kurzweil's vision of the future will in fact be bypassed almost immediately, as tech will advance much faster than any one human mind can fathom.

(In truth, we may not be able to fully capture it today. This may be why our older citizens have issues with technology.)

it was when you said it (1)

globaljustin (574257) | about a year ago | (#45296767)

thnx again...

so, go up a few branches and you'll find your original comment...it **didn't mention other factors** and, most importantly, you said that the success was **due to using Moore's Law**

indep. of each other, fine, but you used pretty flowery language to describe the pressures of your decision and cited **only** Moore's Law for your making the right choice...here's one example:

If we hadn't used Moore's Law in our planning, we would have come out with products using two-year old technology, and our competition would have eaten our lunch.

but throughout you only attributed your success to Moores Law...

Other commenter here on this branch is right...we don't need to dance around the issue...Moore's Law is an interesting novelty and that's all...nothing wrong with running the numbers on it for comparison sake (b/c others in the industry use it if nothing else!)

Re:Moore's Law = Statistical Novelty (3, Interesting)

CODiNE (27417) | about a year ago | (#45296111)

So what you're saying is that Moore's law became a self-fulfilling prophesy?

Re:Moore's Law = Statistical Novelty (1)

crgrace (220738) | about a year ago | (#45296373)

ABSOLUTELY! Necessity being the mother of invention and all that.

Re:Moore's Law = Statistical Novelty (3, Insightful)

osu-neko (2604) | about a year ago | (#45296455)

What you're describing is not to much a "prediction" as a "goal". Which is precisely how Moore's "Law" has been used by the industry. They design each new generation with the goal of doubling the transistor density by some means. The only prediction being made is that they'll meet their goal.

Re:Moore's Law = Statistical Novelty (0)

Anonymous Coward | about a year ago | (#45295665)

Are we going to let TSMC default, off the cliff!

What? Say it ain't so! (0)

Anonymous Coward | about a year ago | (#45295073)

You mean to tell me that a casual observation made about 40 years ago doesn't really mean anything in the real world? Let along be a "law"?
 
Man, that's some deep shit right there. We're talking Hindu guru kinds of deep. The Buddha would have been amazed.

What's a mile? (1, Funny)

WillAffleckUW (858324) | about a year ago | (#45295095)

Is that some archaic form of measurement used by a backwards nation somewhere?

Re:What's a mile? (-1)

Anonymous Coward | about a year ago | (#45295213)

Is that some archaic form of measurement used by a backwards nation somewhere?

What's an ass, oh look found one!~

Re:What's a mile? (1)

Aighearach (97333) | about a year ago | (#45295265)

Okay, now pull your pants up or I'll release the goats.

Re:What's a mile? (0)

Anonymous Coward | about a year ago | (#45295273)

It's a primitive unit of measure, about equal to 3500 cubits, more or less, depending on how long your nose is

Re:What's a mile? (1)

mark-t (151149) | about a year ago | (#45295307)

What does the length of your nose have to do with a cubit?

Re:What's a mile? (1)

cold fjord (826450) | about a year ago | (#45296281)

The same as the airspeed of an unladen swallow ... African ... if you must know.

Re:What's a mile? (1)

mark-t (151149) | about a year ago | (#45296363)

I know the movie reference, but I don't understand what that had to do with anything.

Re:What's a mile? (1)

BasilBrush (643681) | about a year ago | (#45295329)

Several backward nations: Am. Samoa, Bahamas, Belize, British Virgin Islands, Cayman Islands, Dominica, Falkland Islands, Grenada, Guam, Myanmar, The N. Mariana Islands, Samoa, St. Lucia, St. Vincent & The Grenadines, St. Helena, St. Kitts & Nevis, the Turks & Caicos Islands, USA, UK and the U.S. Virgin Islands.

Re:What's a mile? (1)

WillAffleckUW (858324) | about a year ago | (#45296001)

Most of those are US protectorates, not "nations".

Re:What's a mile? (0)

Anonymous Coward | about a year ago | (#45295431)

They're good old European English Units Dick Bag!

Re:What's a mile? (4, Informative)

msauve (701917) | about a year ago | (#45295545)

It's one thousand (mille) paces of a Roman soldier, as modified through history. That seems to be as reasonable a basis for a unit of length as the meter, which is 1/10000000th the distance between the poles and the equator, as modified through history. Mileposts were markers placed by Roman roadbuilders as reference points.

Why do you ask - do you live in some backwards nation without a good educational system?

Re:What's a mile? (1, Insightful)

ifiwereasculptor (1870574) | about a year ago | (#45295595)

Those romans must have had really long legs. A 1m pace is already pretty uncomfortable.

Re:What's a mile? (1)

Anonymous Coward | about a year ago | (#45295749)

A pace is two steps. It's not so bad.

Re:What's a mile? (4, Informative)

Livius (318358) | about a year ago | (#45295843)

The Romans were counting the right and left steps as one pace.

Re:What's a mile? (1)

ifiwereasculptor (1870574) | about a year ago | (#45295907)

Oh, come on. Stupid romans. That definition is even more ridiculous than the weird leaps, stretches and assorted silly walks I was imagining.

Pacing (2, Insightful)

Anonymous Coward | about a year ago | (#45297071)

If you've ever actually had to do precision pacing and measured it out, you'd know why a pace is 2 steps. It equalizes the difference between left and right. 1% accuracy in pace length over a moderately long distance (50-500 m) isn't unusual.

Re:What's a mile? (0)

Anonymous Coward | about a year ago | (#45296615)

The Roman step was 30 inches, which remains the standard for most militaries to this day.

Re:What's a mile? (0)

Anonymous Coward | about a year ago | (#45296763)

Actually, today's metres are based on wavelengths / light.

Re:What's a mile? (1)

interval1066 (668936) | about a year ago | (#45295831)

Sure. Where people still measure weight in "stone" the ENGLISH system must seem very archaic.

Re:What's a mile? (1)

jabuzz (182671) | about a year ago | (#45295899)

Really the people who actually live in English look at the system of units in use in the USA and wonder why they are still using a system of units that they depreciated while the USA was still a colony. Further they wonder why they call them English units because they are not.

Re:What's a mile? (1)

BasilBrush (643681) | about a year ago | (#45295971)

England still uses the mile as the usual measure for long distances. Road signs and speedometers are in Miles and MPH.

Re:What's a mile? (2)

msauve (701917) | about a year ago | (#45296885)

the people who actually live in English look at the system of units in use in the USA and wonder why they are still using a system of units that they depreciated while the USA was still a colony.

That's not hard to figure out - they lost to not only the colonies, but to the French. But I'm being facetious. They're "imperial units," not "English units." They're based on the British Weights and Measures Act of 1824, which postdates your claim that they deprecated such measures in colonial times. Britain didn't really embrace the SI system until the late 20th centuy.

(BTW, ITYM "England," not "English." HTH! HAND!)

Well... Thirdly (5, Funny)

bobbied (2522392) | about a year ago | (#45295111)

And thirdly, More's law is more what you'd call "guidelines" than actual rules.

Re:Well... Thirdly (1)

HornWumpus (783565) | about a year ago | (#45295313)

Just like all the other laws. Scientific or otherwise.

Re:Well... Thirdly (0)

Anonymous Coward | about a year ago | (#45295349)

Umm, no. The laws of thermodynamics are pretty much supported by the totality of human experience. Scientific laws are basic observations, not guidelines.

Re:Well... Thirdly (0)

Anonymous Coward | about a year ago | (#45295667)

Umm, no. The laws of thermodynamics are pretty much supported by the totality of human experience. Scientific laws are basic observations, not guidelines.

Which means what you call "laws" are only good until someone observes something that breaks them.

I'd go so far as to say what you call "laws" are really merely descriptions of what we've observed - so far.

Re:Well... Thirdly (2)

Em Adespoton (792954) | about a year ago | (#45295493)

And thirdly, More's law is more what you'd call "guidelines" than actual rules.

Yeah; but that's what got Sir Thomas into trouble in the first place....

Re:Well... Thirdly (2)

Xyrus (755017) | about a year ago | (#45296525)

Welcome to the IC market, Ms. Turner.

Not a law (1)

macraig (621737) | about a year ago | (#45295151)

Moore's Law isn't even a law... it's a prediction. Didn't we already agree that predictions are only useful to talking heads, pundits and hucksters?

Re:Not a law (4, Insightful)

crgrace (220738) | about a year ago | (#45295177)

I don't know about that. It's been a damn useful prediction in that it gave a pretty ambitious roadmap for engineers to follow. They've been quite successful and meeting the challenge up until quite recently.

A wise proverb that is apropos: If you don't know where you're going, you'll never get there.

Re:Not a law (2)

Kerstyun (832278) | about a year ago | (#45295315)

It's been a damn useful prediction in that it gave a pretty ambitious roadmap for engineers to follow.

Perhaps it's a useful prediction for the exact reason that engineers have been following it?

Re:Not a law (0)

Anonymous Coward | about a year ago | (#45295801)

If you don't know where you're going, any road'll take you there.

George Harrison

Re:Not a law (2)

interval1066 (668936) | about a year ago | (#45295861)

I don't know about that.

I do. Its been a fairly accurate prediction, yet a prediction none the less. The "law" part is just an anecdotal, off-the-cuff addendum. You want to support your theory that its in fact an actual law, here's room for your proof right here:

Re:Not a law (1)

crgrace (220738) | about a year ago | (#45296091)

I wrote:

It's been a damn useful prediction

You replied:

You want to support your theory that its in fact an actual law, here's room for your proof right here:

I didn't claim it was a law. No one even slightly knowledgeable about semiconductors thinks its a law. Did you read my post? The original post stated that "Didn't we already agree that predictions are only useful to talking heads, pundits and hucksters?".

My response was that this was in fact a very useful prediction for engineers and scientists actually doing the work.

So when I said "I don't know about that", it was pretty clear I meant that I didn't agree that predictions are only useful to talking heads et al.

Re:Not a law (1)

VortexCortex (1117377) | about a year ago | (#45296171)

Well, Murphy's Law is actually more of a prediction too, a pretty useful one at that.

Indeed, TFS is simply Murphy's Law applied to Moore's.

Re:Not a law (1)

jbengt (874751) | about a year ago | (#45295875)

Moore's law is an observation, assumed to be true until observations contradict it, which is exactly what a scientific law is.
Also, correct me if if I'm wrong, but wasn't Moore's law about the number of transistors in an integrated circuit, rather than the (closely related) size of features?

Re:Not a law (3, Insightful)

ChrisMaple (607946) | about a year ago | (#45297219)

Most scientific laws are orders of magnitude more precise than Moore's "law", and are quite stable over time. Moore himself varied the period for doubling from 12 to 24 months over the course of just a few years. That's better than a meteorologist but not as good as an economist, and economic "laws" are mostly poor approximations even on good days.

Re:Not a law (1)

gman003 (1693318) | about a year ago | (#45296833)

A self-fulfilling prediction. Once it was accurate for a few iterations, it moved from being a prediction to being a target, and engineers at every major foundry have worked to meet or even exceed it.

Re:Not a law (1)

radarskiy (2874255) | about a year ago | (#45297223)

"Moore's Law isn't even a law... it's a prediction."

A prediction, and an observation... just like any other scientific law.

virtuous ex post self-fulfilling projection (1)

epine (68316) | about a year ago | (#45297331)

Moore's Law isn't even a law... it's a prediction.

If you were doing more than thinking in tiresome categories you might have called it a self-fulfilling projection which is pretty much exactly what it became.

To refine this even more precisely, it's an ex post self-fulfilling projection, where "ex post" modifies "self-fulfilling".

But wait, there's more! It's a virtuous ex post self-fulfilling projection, where "virtuous" modifies "self-fulfilling projection".

We're now deep into The Remains of the Day. I might even call it a pink leather virtuous ex post self-fulfilling projection. Sailed through menopause without a hiccup—to everyone's great surprise—but even lathering on a hair-net bale of Grecian Formula teaser treats the glory days are well behind us.

Moore's law died already (2, Informative)

Anonymous Coward | about a year ago | (#45295159)

Anyone who actually works in the semiconductor industry could've told you this. (Ever notice how the GHz stopped growing a while ago? The move to multi-core happened around the same time and even that's stopped growing.) Yes, it's still possible to shrink transistors further but the speed and power reduction gains are diminishing and the costs of further shrinking are moving from merely eye-popping to astronomical.

Intel can afford to stay ahead of everyone else a bit (this is one of the primary reasons AMD is having difficulty staying alive) because of the huge volume that they have but even they're having problems.

Re:Moore's law died already (2)

SuricouRaven (1897204) | about a year ago | (#45295439)

Clock maxed out. Multicore will take you only so far before you run out of space and hit problems with coherency.

I expect the future is going to involve a lot more specialised silicon. Scientific number-crunching will move onto GPUs or things like the Phi designed just for that type of workload. Mobile processors will start featuring even more single-task accelerators like those already used for video decoding. While general-purpose processors of today become the things that tie all the other parts together, handing the calculations too complex to run efficiently elsewhere and coordinating the shunting around of data.

Re:Moore's law died already (0)

Anonymous Coward | about a year ago | (#45295553)

Nope. It's reconfigurable computing [wikipedia.org] where you set up your own custom accelerator on the fly. Beats the hell out of fixed-function accelerators that get used only once in a blue moon.

Speaking of "on the fly" (1)

justthinkit (954982) | about a year ago | (#45296843)

Heat is a big cpu problem. Have they tried rotating the active core on the fly? When core 0 gets too hot, they switch it off (under single core workload of course) and move activity to core 1. When that gets too hot, I type a bunch more, or you get the picture.

Re:Speaking of "on the fly" (1)

ChrisMaple (607946) | about a year ago | (#45297239)

Have they tried rotating the active core on the fly?

SOP for several years. I can watch the CPU meter on my three-year-old machine swap cores every 20 to 60 seconds or so.

Re:Moore's law died already (1)

ChrisMaple (607946) | about a year ago | (#45297261)

Reconfiguring involves a lot of extra hardware and delay involved in the switching between function sets. I doubt that it will give significant improvements for any but a small number of unusual applications.

MILE markers?...MOORE laws? (1)

turkeydance (1266624) | about a year ago | (#45295165)

all are antiquated.

You mean marketing isn't 100% truthful?!? (1)

harvestsun (2948641) | about a year ago | (#45295201)

Surely you jest!

Re:You mean marketing isn't 100% truthful?!? (1)

bob_super (3391281) | about a year ago | (#45295317)

Marketing is all about not getting caught lying.

Except in the entertainment industry, where lying is also included in the marketing tools.

And don't call me Shirley.

Re:You mean marketing isn't 100% truthful?!? (1)

interval1066 (668936) | about a year ago | (#45295879)

DAMN! I've been waiting years to use that!

Eelectrical Engineering Industry Stagnation (0)

Anonymous Coward | about a year ago | (#45295225)

This is sad, for EE. This rapid decline / stop of Moore's law has been the case for the last few years, and clearly its not getting better.

Overall innovation in EE has slowed down tremendously, since the mid 2000's. Most of the innovation has been 'mined out', and new innovation is mostly done at the system level where they integrate different components (digital, analog, architecture) together for unique applications (usually ultra low power related).

Unfortunately, its also why I believe the field of opportunity has mostly shifted full-way to CS. In terms of an art analogy, the canvas technology (EE) is pretty much set, and the drawing (CS) is where it's at. Sad but true.

The rising salaries and benefits in CS, compared to EE, does not help the EE industry. Furthermore, the tremendous overlap in skillsets (EE who are near the middle of the stack) means EE can jump easily into CS, meaning the industry will hemorhage good talent due to incompetitive wages.

/ a disillusioned EE

Someone should come out with Leess's Law (5, Funny)

Anonymous Coward | about a year ago | (#45295227)

That way, you'd have the option of scrolling back to less dense chip designs.

The end approaches (0)

Anonymous Coward | about a year ago | (#45295239)

If intel has to resort to this then know Moore's law is in a very bad spot.

It's not what you don't not think it is (0)

Anonymous Coward | about a year ago | (#45295241)

Moore's Law: Every discussion of Moore's Law must start with an argument about what Moore's Law means.

Re:It's not what you don't not think it is (0)

Anonymous Coward | about a year ago | (#45295695)

Moore's Law: Every discussion of Moore's Law must start with an argument about what Moore's Law means.

Luckily, there's no need to debate what Godwin's Law means.

Re:It's not what you don't not think it is (1)

interval1066 (668936) | about a year ago | (#45295893)

What a Hitlerian thing to say.

Corporations been doing this for years (3, Insightful)

Nyder (754090) | about a year ago | (#45295247)

Changing the names to make something sound better has been a strat for decades, if not longer.

So why is this a surprise that the semiconductors are using it now to sell stuff.

TSMC's 28nm is MUCH denser than Intel's 22nm (0, Interesting)

Anonymous Coward | about a year ago | (#45295523)

Intel is the King of liars. In going FinFET (Intel's biggest manufacturing disaster to date) , the 2D, top-down profile of Intel's transistor diminishes, meaning that Intel should have got a large density (transistors per mm2) boost from this fact alone. However, AMD's latest GPU, the 290X is VASTLY more dense (without FinFETs) at TSMC's 28nm process than ANY part (pure memory chips excluded) Intel makes at its so-called 22nm process (with FinFETs).

In other words, it is an absolute LIE to state that Intel currently has a process advantage. Intel does have an advantage of having a MUCH faster mains-powered x86 architecture than AMD, and using much less power (again on mains-powered systems only) to achieve this. Sadly, these two advantages are becoming ever less important in the market-place. No-one cares about power-usage on high-end mains-powered PCs, and very few people indeed need the performance of the top Intel parts, especially since almost everything once done on the CPU is now processed on the GPU or dedicated hardware blocks. Worse, now games are finally supporting multiple CPU cores properly, AMD's AAA gaming performance on its much cheaper 6-core parts matches Intel's gaming performance on its TWICE as expensive 4-core parts.

Moving from Intel's cheating, technology like FD-SOI makes the rush (the very, very, very expensive rush) to FinFET look extremely premature. FD-SOI can give better results on current generation fabrication plants than FinFET on next-gen ones, at the tiniest fraction of the cost. The industry was predicated on a shrink every couple of years, but now it is clear that finding new materials and geometries for semiconductor elements on current sizes makes far better sense.

What FinFET promised in theory, it completely failed to deliver in practise for Intel, and Intel has tried twice, totally revamping its FinFET designs from the Ivybridge to the Haswell with no luck (hotter chips that clock less well and only offer real power saving at the useless 'mains-powered' part of the power curve). For those of you dumb enough to have been fooled by Intel's Haswell propaganda, let me EXPLAIN this fact. Haswell only APPEARS to use less power because Intel has optimised power consumption when the chip is doing nothing, or almost nothing. So, on a tablet, when browsing, Haswell effectively switches itself off when you are reading a mostly unchanging web-page. On the other hand, when Haswell is doing actual processing, it is no more power efficient than the last couple of generations of Intel designs, and often uses more power (this is mobile we are talking about here).

In the near future, all fabs (including Intel and TSMC) are describing the minimum 2D geometric features of their FinFET transistors as the 'process'. So, Intel's new parts next year claim 14nm (or is that 16?) and yet AMD and TSMC are also claiming to offer 20nm AND 14nm next year as well (the size discrepancies like 32nm from Intel vs 28nm from TSMC are already down to so-called half-nodes that describe the minimum features of the smallest transistors, rather than the inherent geometry of the process itself).

Anyway, Intel is claiming a new process shrink in 2014, and its competitors are claiming TWO (which is a bit of a clue about the cheating), bringing them 'equal' in process with Intel for the first time in very many years. This means informed people will IGNORE the so-called process, and focus on die size, transistor density per mm2, power dissipation per mm2, and clock speed.

Re:TSMC's 28nm is MUCH denser than Intel's 22nm (0)

Anonymous Coward | about a year ago | (#45295579)

That's assuming a GPU and CPU have similarly sized transistors.

Re:TSMC's 28nm is MUCH denser than Intel's 22nm (1)

smaddox (928261) | about a year ago | (#45296617)

For the case of comparing GPU and CPU, that's a pretty good assumption, because they are both digital logic dominated. Once you start mixing in other functions, things can change dramatically.

Re:TSMC's 28nm is MUCH denser than Intel's 22nm (1)

radarskiy (2874255) | about a year ago | (#45297237)

That's also assuming they have the same Rent's exponent.

Re:TSMC's 28nm is MUCH denser than Intel's 22nm (0)

Anonymous Coward | about a year ago | (#45296443)

Gadzooks someone on the internet is wrong~

However, AMD's latest GPU, the 290X is VASTLY more dense

Who cares, the purpose of finfet is not to increase transistor density but to decrease short channel leakage current

Intel's biggest manufacturing disaster to date

TSMC, UMC, GF have all announced plans to use finfet at future process nodes (20nm I think?). If it is such a disaster, why are all the major founderies pursuing it?

it is an absolute LIE to state that Intel currently has a process advantage

and Intel has tried twice, totally revamping its FinFET designs

So, what you're saying is that since all the other founderies are pursuing finfet, and intel has already finished going through all the growing-pains, that means that intel....isn't ahead? huh???

No-one cares about power-usage on high-end mains-powered PCs

Haswell only APPEARS to use less power because Intel has optimised power consumption when the chip is doing nothing, or almost nothing. So, on a tablet, when browsing, Haswell effectively switches itself off when you are reading a mostly unchanging web-page.

So, no one cares about high end use cases. oh and also, no one cares about mobile use cases. is that right? Also, regarding effeciency - this is like a text book example of efficiency... doing the same job with less cost. this was one of the main targets of haswell, to allow better power gating.

Anyway, there are certainly starting to be diminishing returns at smaller process nodes (supposedly 20nm is the first process node which will be more expensive than the preceding one), but all of the claims from your post are situated cleanly between weird and wrong.

Re:TSMC's 28nm is MUCH denser than Intel's 22nm (1)

smaddox (928261) | about a year ago | (#45296629)

I'm not sure where you heard that "20nm is the first process node which will be more expensive than the preceding one". I'm curious how that could be argued. Nearly every tool has grown near exponentially in price. Perhaps by scaling up production they've been able to keep reducing cost, though.

Re:TSMC's 28nm is MUCH denser than Intel's 22nm (1)

ChrisMaple (607946) | about a year ago | (#45297305)

FinFET - by exerting control over the channel from three sides instead of just one - allows an improved tradeoff between leakage and speed. It's not just a leakage improvement.

Transistoacking has probably reached its limits. (1)

140Mandak262Jamuna (970587) | about a year ago | (#45296295)

These line widths of 22 nm or 28 nm etc are some 50 times narrower than the wavelength of visible light. Making the lines thinner is difficult and it is approaching quanum mechanics limit. Unless people start immersing the entire etching machines in water or some such medium, we cant make the lines thinner.

Even if we did, there are not enough electrons in these lines to make the "law of large numbers" work. So this time we are bumping against a real barrier.

Anyway, there are not any mass market killer apps based on computation anymore. All the action is in connectivity and bandwidth enhancement. Given the computer market has been split into makers vs takers (or content produces vs content consumers) this is changing the funding models. Earlier the large number of passive consumers buying computers way more powerful computationally than what the typical consumer needs, was subsidizing the cost of computers for the few who actually need that much of computational power. Now the passive consumers are buying simpler devices needing less computation and more connectivity. We can expect coders like us can expect our hardware to get more expensive, like the old line of unix workstations like micro-vaxes or sun-solaris or hp-ux or SG-Iris.

Re:Transistoacking has probably reached its limits (1)

crgrace (220738) | about a year ago | (#45296613)

All sub-65nm and most 65nm processes are lithographically exposed in water current for the reason you stated. The next step is extreme UV or even e-beam lithography but it's expensive and very, very difficult.

You're quite right that this is an economic/mass-market issue more than a pure technical issue.

Re:Transistoacking has probably reached its limits (1)

drhank1980 (1225872) | about a year ago | (#45297225)

As somebody who works in Lithography, I can let you know that they have not been using visible light for a long time. All fine resolution lithography is designed around as close to a monochromatic light source as possible. Having a significant spread in the light spectrum was just not consistent to do much below the 1.0 um feature size. This is because of the diffraction spread is very dependent on the wavelength and the fact that the photons have different energies thus reacting differently (or not at all) in the photoresist on the wafer.

Thus broadband lithography gave way to g-line (465nm visible blue) which gave way to i-line (365nm Ultra-Violet); Next was deep UV (248nm), Now 193nm is still used in state of the art systems today with lots of tricks such as immersion (where the light goes into water before it hits the wafer to increase the NA of the system) and double patterning (splitting up the image into multiple images that are combined in the etch processes after). Extreme UV is 13.5nm light is the next step but it is a very difficult light source to work with and the systems outrageous sums of money even for this industry.

What you are completely correct about is the importance of connectivity. I went from working in a dying 1xx nm CMOS fab this year to a thriving 1.0+um fab that makes wireless components. The lithographic part of the process (and just cramming more and more transistors on a die) is not the key value to our customers; its the exotic materials that we use to target more and more bands of wireless connectivity. I expect there will always be a demand in the market for more and faster transistors for pure computation. Its unfortunately no longer where the market growth is; thus the ROI on developing these technologies is looking more and more risky for businesses. What I have found interesting is that just about everybody working on the high end of the industry is pretty confident that the transistors will work at the 5nm-7nm node so there is still an incentive to head in that direction for now. After that will require some radical re-thinking about the materials used in computational machines.

Re:Transistoacking has probably reached its limits (1)

ChrisMaple (607946) | about a year ago | (#45297321)

The ultimate limit is the placement of individual atoms. It's already been done, but the process is agonizingly slow.

Moores Law Hits the Limits of Physics (1)

loose electron (699583) | about a year ago | (#45296905)

http://electronicdesign.com/digital-ics/tiny-transistors-giant-molecules-moore-s-law-crashes-laws-physics [electronicdesign.com]

Give this a read.

Moore's law extrapolations are hitting the limitations of physics.

As for shrinking transistors?
Pretty meaningless, silicon hit the limitations of the interconnects a while back.

Parasitic capacitance has been the brick wall that people can not get past.

How about optical interconnect? (1)

PeterM from Berkeley (15510) | about a year ago | (#45297377)

It seems to me that the next thing to really boost computer performance is optical interconnect.

With optical interconnect, parasitic capacitance and RC delays are just gone, and associated power consumption radically reduced.

I know that there are various parties working on optical interconnect and even optical transistor equivalents.

I don't mean to imply that achieving optical interconnect (or optical transistor equivalents) will be easy, I'm just saying that it has promise to remove many of the current performance limits.

--PM

Time to develop/adopt better technologies... (0)

Anonymous Coward | about a year ago | (#45296993)

Scaling may be reaching limits, but there are still gains to be had. Think T-RAM, Z-RAM, memristors, etc. There are a number of technologies that will not only scale smaller, but also have smaller structures at the same node. Using better memory technologies alone has the potential to save considerable die space. 6T-SRAM, DRAM, and Flash leave much to be desired. The question is, why do the superior technologies never seem to make it out of the lab?

At some point, we need to stop beating the nearly dead horse with incremental improvements to antiquated technologies.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?