Slashdot Mirror
Forty Years of Moore's Law
kjh1 writes "CNET is running a great article on how the past 40 years of integrated chip design and growth has followed [Gordon] Moore's law. The article also discusses how long Moore's law may remain pertinent, as well as new technologies like carbon nanotube transistors, silicon nanowire transistors, molecular crossbars, phase change materials and spintronics. My favorite data point has to be this: in 1965, chips contained about 60 distinct devices; Intel's latest Itanium chip has 1.7 billion transistors!"
That's Montecito dual core Itanium, w/24MB of cache (only about 120 million transistors actually per CPU with the balance largely that motherlode of cache) and you could probably fry a steak on.
"We can keep Moore's Law alive just by stuffing the cache!"
"Brilliant!"
"Brilliant!"
Suddenly they were crushed by a giant can of Guinness containing not even an electronic sausage...
A feeling of having made the same mistake before: Deja Foobar
So many people really doubt Moore's law will die anytime soon. Just because intel isn't jumping MHz every year, doesn't mean its ending... There are so many things left to do to squeeze out more performance in the same area or smaller. You can go to 3D stacks of transistors, higher K oxide dielectric, the list goes on and on. I agree with the article that says that we could see it go into the 2020s... the main problem that will hinder moore's law will be the economics of investing in new fabs, and waning demand of chips, not research and technology limitations. I see more money being pumped into memory chips and special purpose ARM style chips with a focus on low power. Eventually, people will just say, "Moore's law just doesn't matter anymore, the market has changed".
...to the next article discussing how Moore's law can't possibly hold up much longer begins now.
...but the article doesn't point out that the law is based on silicon transistor based computing. Obviously, if we switch to other bases for computation, it probably wont apply. IE quantum or plasmonic (yes, I know the latter will probably be in silicon).
Before anyone says, well we've adjusted the length of time for doubling already, we'll do it again. For what its worth, its a bit silly saying X=2^Y/T is a law if you redefine T everytime it doesn't fit.
Windows in 6 Bytes (IA-32) : 90 90 90 90 CD 19
The amount of articles mentioning Moore's law will double each year.
Shouldn't it be Gordon's theorem is we are questioning it? People don't question the theory of relativity or the theory of evolution (ok- I meant educated people)- and we still refer to these as theories.
People always talk about the end to Moors law stating that we cannot solve some challenges. Other people always reply "well we always manged to solve challenges and we probably always will".
What I think is more interesting is how far ahead we can solve them. The clock distribution problem was a problem for seen and solved years ahead of it biting hard. Nowadays the problems arise and we have shorter and shorter time to react before they cause serious problems.
This is the strongest proof I found that this technology will (eventually) stagnate.
Mouse powered Chips, Open source Processors and Lego
my blog
If not I herbey proclaim it Goat's Law.
My days of not taking you seriously are certainly coming to a middle...
I bet we could find an article for each year if we look hard enough. :)
I was looking for logic vs. cache break-down numbers for a while, obviously Intel is not keen on providing it on their own.
The way I see it, 24 MB = 1024*1024*8*24 * 6 transistors/SRAM cell = 1.2B transistors for cache, still leaving 500M for logic. Well, we can factor in address storage and cache access logic, but I'd still like to see some harder data than this.
Paul B.
My favorite data point has to be this: in 1965, chips contained about 60 distinct devices; Intel's latest Itanium chip has 1.7 billion transistors!
Uh, wouldnt that be two data points?
Not if we run out of juice to power our tansistors.
Intel's latest Itanium chip has 1.7 billion transistors!"
No wonder they call it the Itanic! Both were big and huge and failed miserably.
It's not a law, it's an observation. Did you know the term 'law' for a scientific theory was coined by Isaac Newton, who felt that his 'Laws of Motion' were so right and pervaded the universe so deeply that they had to be a law? He wanted to convey they had a deeper significance than a mere theory. In time of course, even these 'laws' came to be shown to be incomplete or only true for slow moving objects. Ever since, every theory both worthy and crackpot has been called a 'law'. It's about time we returned to the humbler 'theory', 'theorem' or 'observation'. In the case of Moore's 'Law', it's not even a very good theory, since it only describes a very general trend, it cannot predict with any accuracy exactly how fast/how many transistors or elements a chip will have at any time in the future.
By the way, if the Itanium has 1.7 billion transistors, (I'll take the poster's word for it) then one has to ask - are they all pulling their weight? It seems a hell of a lot for what it does. Surely one way to squeeze more out of Moore's Observation is to come up with more efficient architectures and use fewer devices, working more efficiently/smarter/harder. Just a thought.
"Forty years ago, Electronics Magazine asked Intel co-founder Gordon Moore to write an article summarizing the state of the electronics industry."
I remember Electronics Magazine. I loved it. It was great. It just sort of fizzled out. Alas and alack.
About the only thing I can think of now that covers the whole industry is Spectrum. Otherwise, all that arrives in my mailbox is stuff like Microwave Buyer's News and Circuit Cellar. Is there a great magazine out there that I'm missing?
Michale Moore has a law now? Great, and I haven't even seen his film Rescue 911 yet. Now I understand why Disney tried to crush him and his law-making ego.
It's buried right next to BSD, adjacent to the freshly dug grave for World of Warcraft.
Sometimes my arms bend back.
Moore was at Intel, and was pushing that goal for most of those years.
no, Murphys Law is eventually one day someone will make a cyborg police officer.
Also, for the record as a physicist, quantum computers won't remove the need for conventional computers in most areas - a big thing is (as I understand it) that they're not programmable, and have to be built to a certain specification. Therefore, classical computers will always have their use.
Physicist, consultant, science communicator
luke skywalker: I care.
Somewhere around there the number of transistors in a chip becomes equal to the number of atoms in the known universe.
Has anyone got any pretty graphs of the performance of particular CPUs against time? It would be cool to have some sort of visual representation of the validity of Moore's law.
~c
What amazes me the most is the amount of bugs a device with 1.7 billion transistors has compared to the number of bugs in, say, Windows XP, GIMP or Firefox.
And don't give me any crap about that software is somehow inherently harder to keep bugfree. I develop both and there really is little difference when it comes to complexity.
Sure, software performs more complex tasks, but when you add 'parallel-ness' of hardware, as well as timing issues, temperature and manufacturing issues, clock distribution, leakage and crosstalk, hardware defenetly is a pretty good match.
The simple truth is that there is simply vastly more testing that goes into hardware then most software (software in mars rovers and lunar landers would be an exception). And I bet that there are better design methods and safty guards too.
Failing to learn from history dooms you to repeat it.
Actually there's that bit in Jurassic Park by Michael Crichton regarding the more complex a system, the more likely it'll break down. (Honestly don't know who to attribute that to other than MC.)
Intel's motto? So far, so good!
A feeling of having made the same mistake before: Deja Foobar
I can just see Dr. Evil now...
"I demand the chip have...SIXTY TRANSISTORS!" (pinky lightly touches corner of mouth).
The guys at Intel start laughing hysterically...
"I've changed my mind...I demand the chip have...ONE POINT SEVEN BILLION TRANSISTORS!" (pinky lightly touches corner of mouth)
Intel guys gasp in shock...
Rather than calculating this forward in time, didn't someone trace this backwards in time, i.e. that you can see it halving every 18 months going back to the nineteenth century? I can't find a link on Google but I swear I saw it somewhere...
I vaguely remember a law that states something along the lines of:
"for a system to be inherently useful, its complexity must be such that its failure would be catastrophic"
...the moment. It depends on your application of course. But for number crunching it's hard to beat the GPU on recent graphics cards. For non-graphics applications you can expect speedups from 5-15 times (not %) for things like linear algebra, option pricing and singnal processing. This has been increasing faster than Moore's Law and will likely increase faster. Code written for GPUs is inherently streaming code, and hence easily parallelisable, so many of the complex dependencies that make CPUs tricky to speed up go away. These are exciting times and a big shift in programming paradigm is taking place.
Doesn't it make you feel good to know that our freedoms are protected by politicans, lawyers and journalists.
But for most slashdotters I think that is a pretty obscure reference.
Eighteen months from now you have to sing it again twice as fast.
"Nooooooooooooooooooooooooooooooooo-body!"
The Humungous rules the wasteland!
Basically, it has been observed that any evolutionary process (including technology) will progress exponentially as it builds on past progress, with barely perceptable slow-down/speed-up "S-curves" as paradigm shifts occur.
Moore's Law is certainly an important component of this trend, as it relates to computing power and eventual AI/IA accelerating to Singularity in ~25 years, but there are many others in parallel: storage space, networking bandwidth, # of internet nodes, transportation speed, etc.
One thing that certainly ISN'T keeping pace with our technology is our old evolutionary psychology; hopefully we can fix some of the more disgusting aspects of human nature before it's too late.
Power to the Peaceful
Questioning the theory of relativity and the theory of evolution is something that is frequently done by educated people.
This is how we get a better and more refined understanding.
Boffoonery - downloadable Comedy Benefit for Bletchley Park
Moore's Lay ... ...
;)
Things get better
Doubbly so.
That's fine and good.
But how about another law that incicates how long it will take for that technology to hit the shelves
If I make a processor the size of a dinner plate I could probably put over a trillion gates on it. Doesn't mean that I 'broke' moors law, just means I make bigger processor dies.
Steve's Computer Service, Hobbs, NM
Software efficiency halves every 18 months, so make sure to download newest Gnome/KDE/whatever after your CPU upgrade.
Gates Law: MS Code bloat will double at the same interval as Moores law.
I don't pretend to understand Goat's Law, I merely enforce it.
What would Brian Boitano do?
I'm surprise that no one has spoken up and pointed out that Moore's law has not been true for the past few years. In 2003, I purchased a P4 3.06ghz, which I'm using right now to type this message. 2005-2003 = 2 years. Where are the 6.12ghz machines?
"Well, it's not about hertz, it's about perforamnce!"
Judging from benchmarks, the current top of the line CPUs are not twice as powerful as my P4 3.06ghz. Sooo... anyone care to explain how Moore's Law is still been used?
..but think it's bunk. There is absolutely no evidence to suggest that more-than-human AI is an inevitable consequence of continued development of computer hardware. The last 50 years of faster computers haven't helped much so far. Nor am I aware of some brilliant AI technique that will be made possible by much faster conventional computers. Technological progress generally happens in fits and starts, with radical jumps long periods of slow, gradual improvement in between. The chip industry is possibly an exception; but, frankly, I suspect if you could come up with a "utility gained" measure it would grow a lot more slowly than chip density.
Any sufficiently advanced technology is indistinguishable from a rigged demo
--Andy Finkel (J. Klass?)
From Popular Mechanics, march 1949:
"...computers in the future may have only 1000 vacuum tubes and perhaps weigh only 1 1/2 tons."
Jhyrryl
You kind of forgot the major reason there ...
The second point is a datum, the first point is a reference. If you say "this site is 150 meters above sea level", how many data points do you have?
Two page story on the "new" Intel and Craig Barett's successor...I thought it was an add at first. don't mistake my sniping at their PR machine for dislike or ill wishes...we all have a lot riding on Intel even if AMD is coming on strong.
SLASHDOT: news for people who can't concentrate on work or have no life at all and got tired of yelling back at the TV.
"Everything that can be invented has been invented."
--Charles H. Duell, Commissioner, U.S. Office of Patents, 1899.
Chicken fried butter sticks? Do
Peak Oil folks take one valid idea (oil is finite, and running out will be painful), but then devolve into irrational fear-mongering about it. If thermal depolymerization can net the US four billion barrels of oil from agricultural waste we currently throw away, running out of ground oil ain't going to be causing a new Stone Age.
Obviously there is nothing wrong with my simple programs. Any odd behavior can be explained by the complex hardware, you know, sun spots flipping bits and other errors induced in hardware, I know it is not my code ;-)
This issue is a bit more complicated than you think.
wow
...that specialized processors can temporarily exceed Moore's "law", by doing things smarter. It's kinda like finding a new algorithm that scales to order n*log n instead of n^2, and claim the processor got faster though.
Code written for GPUs is inherently streaming code, and hence easily parallelisable, so many of the complex dependencies that make CPUs tricky to speed up go away.
I think you put the cart before the horse there. The task you're trying to solve must be easily parallelizable and thus free of complex dependencies in order to be implemented (effectively, they are Turing complete) in GPU code. In other words, it only applies to a subset of problems.
Kjella
Live today, because you never know what tomorrow brings
I sort of disagree with this comment: "Not everything he's said, however, has come true. He once predicted that wafers, the round disks out of which chips are harvested, would measure 56 inches in diameter about now. They measure 300 millimeters, or 12 inches. " LCD flat panel TVs are approaching that size, and are made in a similar fashion to computer chips.
Intel's latest Itanium chip has 1.7 billion transistors! I can see the poor guy now... 1,452,178...1,452,179...1,452,180...1,452,181...*Y AWN*...AHHH CRAP!!!
That it's mostly useless in real-world terms anyway.
Sure, taking Moore's law literally, computers are 1 million times faster than 30 years ago. Arguably that should translate into _more_ than 1 million times more work per second, because compilers have evolved too, and expensive optimization techniques have become more affordable. (A compiler optimization technique that would have taken a week on a 70's mainframe, now takes seconds.) We also have better tools.
But are we doing 1 million times more with them? Nope.
Every time we get better tools, the accounting dept just get the idea "w00t! Now we can _really_ hire untrained monkeys to use them." In fact, the better tools and computers you get, the worse code you get.
It's not just code _performance_ that went south, any clue about security or good design went south too. Actually analyzing what could go wrong got at some point replaced by magic talismans like "we use Java so we can't possibly have a security problem" or "we use HTTPS, so our site is by definition secure." Too bad that one only has to edit an URL to bypass all those magic talismans.
And then there's the BDA (Buzzword Driven Architecture) effect.
The whole computer industry is one big scam where marketting is in control, and the biggest outright liar and con wins the contract. So every single dud or unfinished (or outright _stupid_) idea is marketted as _the_ second coming of christ, cure for all enterprise problem, cure for cancer, etc. And there's one born every minute who actually believes that drivel... yet again.
So programs are written with the sole purpose of having as many buzzwords in them as possible. Everything _must_ involve a SOAP call, to an EJB, which uses XSLT instead of just processing the damn data, etc.
True story: I've actually benchmarked one such crap buzzword-driven framework we were forced to use here. It took 1.1 seconds for a call to an empty method, on a 2.26 GHz P4 computer. No, not milliseconds. 1.1 _seconds_. A cool 2.5 billion CPU cycles just for a function call to an empty function.
We've actually exceeded Moore's law. A computer in '70 may have been 1 million times slower, but we're taking a _billion_ times more computer cycles to do the same. Yep, the modern version actually runs _slower_.
Being an ex-assembly programmer, that realization hurt. I'm talking physical pain.
So to end this long rant, IMHO I'm not sure that Moore's law will become that irrelevant any time soon. You could increase the CPU speed another 100 times, and someone will just find the monkeys to write 1000 times slower code for it.
A polar bear is a cartesian bear after a coordinate transform.
Somehow, sometime, Moores law will fail.
Then you will have Lazenby's, Connery's, Dalton's, then (perhaps) Brosnan's law fail as well. Some laws can be.....broken, and twisted, and....um suckey. That last illiterative is mine....all mine, Mr. Bond.
Never play chicken with a passive aggressive.
A device had about a two millionth of a component.
I’m old enough to remember 16K of memory being described as “whopping”
...in 1956, when they managed to fit one component on to a device.
I’m old enough to remember 16K of memory being described as “whopping”
Intel's latest Itanium chip has 1.7 billion transistors!"
And it's as hot as one vacuum tube!
(insert drom-rulls and cymbal hit)
40th anniversary? That's weird, I swear just about a year and a half ago it was the 20th anniversary.
Myself, I prefer Cole's Law. (thinly sliced cabbage)
I'm making a
It has very slow(compared to transistors, gates, flip flops) individual processing and storage elements yet has incredible throughput and paralell processing power.
Good judgement comes from experience, and experience comes from bad judgement.
- W. Wriston, former Citibank CEO
- Formal verification is probably easier to perform with hardware.
True. And this is the reason that we should be writing software pretty much the same way logic designers design logic circuits. That's the basic idea behind synchronous reactive programming languages like Esterel, Signal, Occam and others. Also check out Project COSA at the link below.
The Itanium contains 300,000,000 times the number of devices than the 1965 devices (60). This 2^28 power over 480 months, or 17 months each doubling.
People were already doing parallelisable problems before GPUs appeared. For example 3D rendering is highly parallelisable. But unless you had access to specialised hardware you were unable to exploit it. Consider GPU Gems 1 or 2. The applications are from quite a few different disciplines (computational chemistry to finance) and yet very little reference is made to parallel programming because the code to do these things was already completely in a streaming form.
Doesn't it make you feel good to know that our freedoms are protected by politicans, lawyers and journalists.
The number of connections does not represent the ammount of data the neuron has direct access to but rather the level of parralelism in the computation.
The "data" of a neurion is actually stored in the neural junctions. It is stored by modifying the sensitivity to neurotransmitters and whether stimulation by the neurotransmitters means fire the neuron or suppress the firing. This is also where the neuron "processes" information.
While the parrelelism of the brain is unquestioned, the neuronal access to information is limited to a few hundred to a thousand pieces of data.
Now this is already far in excess of silicone but it is no where near "infinite" data access. However at the same time this basic data must then be processed and combined into usefull signals....this is what slows the brain down while at the same time making it an incredibly dynamic yet stable structure.
Now if we were to transalte this into silicone we would essentially give every gate a place to store it's recent states while at the same time giving hundreds to thousands of other gates the ability to directly query the state of that gate X # of cycles ago.
( 1965, 60 )
( 2005, 1.7 billion )
If you realize that a cache transistor uses about 10% of the power consumed (and hence, heat generated) by a logic transistor, you see why the power/thermals issue IS EXACTLY why Intel is shifting a high percentage of die to cache since it generates excellent performance-per-watt compared to logic. Itanium, by the way lives in a much more disciplined thermal-design-point than most modern 'big' chips (eg. 160 watt Power 5) being 130 / 99 / 62 watt (depending on model) - which is actually better than most Xeons, Pentium 4s and other Prescott-core designs :-).
BTW, Another poster (later on) also correctly mentions that Moore's Law simply talks about number of transistors on a chip - not which type and what they're used for - stigmatize cache when you get your own law
So, yes, I actually do consider myself qualified to talk about such things, pal.
Any sufficiently advanced technology is indistinguishable from a rigged demo
--Andy Finkel (J. Klass?)
We've actually exceeded Moore's law. A computer in '70 may have been 1 million times slower, but we're taking a _billion_ times more computer cycles to do the same. Yep, the modern version actually runs _slower_.
Being an ex-assembly programmer, that realization hurt. I'm talking physical pain.
Hey, why don't you go back to assembly then? Now THAT'S physical pain. Ha!
But seriously, computers today are asked to do much of the same thing computers in the 70's were asked to do. Play games, add numbers, make letters, etc. What is burning all those clock cycles is "modeling reality":
For instance, what did you use to process and print a mail merge letter in 1984? Wordstar. ^KB bullshit. Kaypro. Your choice of 8 different dot matrix fonts.
Then in the late 80's Wordperfect came out and you could view what your document would look like after it was printed.
Then you could actually move stuff around on the actual piece of paper.
In the last 10 years, it's mainly been making that piece of paper look better.
Photoshop revolutionized the world of photography and graphics and now you can import a whole reel of images and edit them in real time on your desktop and make your own film. All for $400 or about the price of 4 nice dinners out with your girlfriend.
The games are so close to reality, people playing them often forget about their real lives, and it's only getting better.
So you see, a lot of those billion processor cycles are going into asthetics, not just the bare mathematical logic of what's really happening.
"So", you say, "who cares about asthetics? The code should be faster!"
Well, consider this analogy:
Let's compare a 1969 Chevy Malibu and a 2005 Chevy Malibu.
Billions of dollars have been spent in 36 years to bring about the product the 2005 Chevy Malibu. The '69 Malibu can take you to the grocery store and back. But it has springs that stick you in the ass, it takes about 4 minutes to start and another 4 to warm up, it burns around a gallon of gas to do it, it pollutes horrible smoke and smell, it only has an AM radio, it's noisy, unsafe (front seat can detach from floorboard in an accident), and wasteful.
The 2005 Malibu can take you to the grocery store on 1/8 of a gallon, it's quiet, comfortable, you can watch a DVD, it has airbags, Air conditioning, etc. It simply makes your life better, easier, simpler.
Asthetically, software has improved drastically. Most people couldn't use computers and software in the 70's; Now most people can.
So, go back to assembly. I wish the demo scene was still kicking because people made some amazing shit with today's hardware and 32, 16 or even 4k of code.
And try to write something that will take advantage of 1000 different video cards, 2000 different networking cards, 100 different types of MICE--it takes muscle to do all that today's computers do.
What I'm saying is I disagree with you. It doesn't make me angry that more people are coding because I get to see more new ideas and gadgets.
Cool! Amazing Toys.