Slashdot Mirror
Understanding Moore's Law
S. Blocher writes "Ars Technica has a great article up, 'Understanding Moore's Law', that I think most geeks should read. The misrepresentation of Moore's Law in the media has always been a real pet peeve of mine, and this article does a great job of looking at the flipside of the 'bigger and faster' thesis to show how the Law isn't really just about doubling computer power."
It seems like a good start would be to stop calling it a "law," a term that has some kind of meaning, in a scientific sense. Exactly where that line gets drawn may be a little fuzzy, but I think it's fairly obvious that Moore's observations don't make the grade.
It Is the Nature of Information to Transgress Artificial Boundaries
The article and the predictions that it made have since become the stuff of legend, and like most legends it has gone through a number of changes in the telling and retelling.
Just curious, but has anyone ever even heard of this before? It's very interesting, but the article was written in 1965, and I don't think current geeks know a lot about this. I certainty didn't
Etiquette is etiquette. He kills his mother but he can't wear grey trousers.
I'll comment w/o reading the article.
Roger Moore's Law is: you get more chicks when you are James Bond than when you're Roger Moore. That's it right?
Microsoft's law: what you get when you put Moore's law and Murphy's law together.
...just my 2 gil.
For every news artical about Moore's Law, there will be a two fold reduction in the amount of Moore's Law that is explained. Which at some point it becomes impossible to comprehend the difference between Moore's Law and Artical Fodder about why you need a new computer.
Neck_of_the_Woods
#/usr/local/surf/glassy/overhead
Moore is better, lesse is worse.
Really? How would Intel realistically expect to generate revenue if they didn't have such a "law" as a guideline?
Life moves pretty fast; if you don't stop and look around once in a while, you could miss it. -FB
The rate at which the Moore's law is quoted in lectures and articles doubles every 18 months
it is a theory, or a hypothesis, or an observation. A law in the scientific jargon must be something which is:
6 a : a statement of an order or relation of phenomena that so far as is known is invariable under the given conditions b : a general relation proved or assumed to hold between mathematical or logical expressions
Moore's Law only holds true to a point. There comes a time when only so much can be fit on that piece of silicon. The term conjecture might also be applicable.
In SOVIET RUSSIA... erm...NSA AMERICA, the Internet logs onto YOU!
Haven't we been beating this dead horse long enough?
Admonitions against misinterpreting Moore's law are about 3 minutes less old than Moore's law itself, and will probably be the part of Moore's law that outlives the law by 20 years.
Moore's Law is so perennially protean because its putative formulator never quite gave it a precise formulation.
I tried to read further, but started twitching uncontrollably. How about Mace's Law: "The skill of tech writers halves, and their pride doubles, every 12 months."
I always gave about the same credence to both Moore's Law and Murphy's Law.
Ok, I finished the article. I learned some history, saw some graphs, and care not one bit more about Moore and his infernal Law.
...
A site about technology, which is currently getting slower and slower.......
RoseColor red={0, 0xffff, 0x0000, 0x0000};VioletColour blue={0, 0x0000, 0x0000, 0xffff};find / -name *mybase*|chown you
you get more chicks when you are James Bond than when you're Roger Moore
I am Roger Moore, you insensitive clod!
Again with Moore's ex recto Conjecture?
6 a : a statement of an order or relation of phenomena that so far as is known is invariable under the given conditions b : a general relation proved or assumed to hold between mathematical or logical expressions
I agree,and I would actually give Moore's Law less credit than that. I would infer from your definition that, generally, a "law" is something fundamental and immutable that arises from the underlying nature of certain phenomena. Boyle's gas law is a good example: increase the temperature of a gas at constant pressure, and it expands. This is fundamental and can be explained as such.
Moore's "law" is just a relationship built from Intel's marketing engine and economics. Let's say I was rich and decided to start marketing cheap, low-defect silicon. Moore's "law" suddenly changes.
Basically, Moore's law could change at any time (and has) if Intel decides to accelerate their R&D facilities. Or if they decide to invest more in silicon fab facilities. Or if they decided to raise their prices, allowing them to get a lower yield of smaller-featured chips.
When you get right down to it, Moore's law only holds as long as Intel wants it too. Or, if they get more competition that forces them to accelerate their chip release schedule (like the last 5 years thanks to AMD).
-Looking for a job as a materials chemist or multivariat
Is to give you an excuse to avoid work. See http://arxiv.org/abs/astro-ph/9912202 for a paper (in PDF) describing this
There was already a Slashdot story about this from a different source this year. This article covers exactly the same territory, and was most likely inspired by it.
Now which Ars hole wrote this article?
Amdahl's law is more of a "law" than Moore's law is. It's a way of figuring out how much of a speedup is really possible from parallelization. The formula is:
S=N/((B*N)+(1-B))
where S is the speedup, N is the number of processors, and B is the percentage of the program that must be serially. The upshot is that as long as B is greater than 0, you'll never get the N-times speedup you'd hope for from throwing N processors at the problem.
It seems a pretty trivial result, but it's basically Gene Amdahl's way of throwing the "multiprocessing will save us" theory back in the faces of its proponents. Multiprocessing is the obvious way to speed things up, but if it won't work on every problem, we'll have to look elsewhere.
Psh. Mamas boy.
This is due to management overhead, ratio of parallelizable to non-parallelizable portions of the task, etc.
Very important stuff to consider when doing multi-threaded/process/tasking and clustered design and development.
No sig, sorry.
He didn't say just how long his "law" would last, however. He made the huge assumption that intel would keep on keepin on with their technology breakthroughs, and if they perfect that terahertz transistor technology, THEN Moore's law will stay in effect for a little longer
But, something that most people don't take into account (and moore probably didn't either) is the fact that we don't NEED faster computers. We want them. You don't need more than a P4 to do just about anything, but becuase of games that require horsepower, you are required to buy them. Of course theres the server side of things, which is a totally different ballgame. YES, they DO need faster computers as workloads get heavier.
The number of stories posted on Slashdot about death of Moore's Law will double every 18 months.
Basically, Amdahl's law says that you can only optimize to a point before it becomes pointless. Also, it is often used to demonstrate that it is useless to optimize a single aspect of a system when the other aspects are still unoptimized.
For example, let's say you have a computer that executes something within 10 seconds. 5 of those seconds are spent reading from disk, 5 are spent doing calculations on the CPU.
Now if you upgrade the disk to a disk twice as good, you're gonna get an execution time of 7.5 seconds(5 for CPU, 2.5 for disk). So you gained 2.5 seconds.
Let's say you still think it's too slow, and upgrade the disk again to a disk twice as good. You're now getting an execution time of 6.25 seconds(5 for CPU, 1.25 for disk). You thus gained 1.25 seconds.
You should get the trend here, if you continue upgrading only the disk, it will come to a point where, even by increasing the speed of the disk tenfold, you will only gain small fractions of second on your execution time, and small fractions of second over more than 5 seconds is definitely not a good improvement.
The same reasonning can be applied(this is the original intent of Amdahl's law) to multi-processor machines. Assuming only 50% of a program is runnable in parrallel processing, it comes to a point where adding processors brings very little improvement, even were you to increase the number of processors tenfold. (The explanation for this is left as an exercise to the reader... Hint: it's the same explanation as the disk/cpu above.)
...already exists, in philosophy, for anyone that's wondering. It is a statement of the form:
A is and I don't believe A.
Such as: It's raining and I don't believe it.
The paradox lies in questioning the belief in a fact you've already attested to in the same statement.
-R
I have asked numerous people and no one has been able to answer this question.
Why does Moore get credit for this "law" and the "Moore machine"?
A.M. Turning in Mind, October 1950 p433-460 discussed both his predictions on the growth of computers (p442) and had diagrams and equations for what is now called in computer engineering a "Moore machine" (p440).
I will agree with anyone who says that Moore refined Turning's ideas. The way Turning predicted growth is hard to use as any sort of "law." However, the state diagram in Turning's article is pretty clear. I would call it a Turning machine rather than a Moore machine if I had my say.
Maybe someone here can finally provide me with a reason why Moore gets all the credit for Turning's ideas.
To me it seems clear that Moore had read Turning's article 15 years prior and used it as a basis for his ideas. Should Turning be given some credit?
This message is encrypted with Quad ROT-13 to protect the author's copyright under the DMCA.
My new law/observation/theory/detriment/prophesy is:
Every 18 [eighteen] months a new faster and more powerful processor is released to the masses that makes my 1Ghz seem obsolete.
Not a sermon, just a thought.
[n8.r0n] http://petesweb.spymac.net/
Well then they better change the ads. On every page, there's a big animated gif ad for 'American Singles' asking ARE YOU SINGLE? Yes! Of course I'm single! I'm reading this fscking article! Do they think I could get a date? hrmmph.
Damn Marketers.
HURD - Hurd's Under Research & Development
Quite simply, companies expect Moore's law to remain true. Software companies plan product lines in anticipation of processor capability doubling every n years. Processors are going to get improve at this rate, therefore we know how quickly bus performance and peripheral performance need to improve.
Semiconductor manufacturers know this. They plan product lines in a Moore's-law-consistent manner (not necessarily explicity, but surely as a matter of economics). If they're a little behind the curve, more money gets put into keeping up with it... or somebody else steps up and keeps it true. If they're at or ahead, they hold the course.
If someone were to introduce a processor that was 10x the density/speed of current processors, don't you think more resources would then go into peripheral design/heat management/software development to utilize the improvments, rather than continuing to focus on improving the processor?
The reason the law has held so long and seems to be so consistent is that it sets everyone's expectations, and people plan towards those expectations. Not less, not more.
You've all been Jedi mind tricked.
http://firstmonday.org/issues/issue7_11/tuomi/inde x.html
This is much better article IMO.
It doesn't say Moore's Law isn't a powerful force for technical and social engineering, or that it doesn't drive the PC and high-tech industry, but the simple truth is that Moore's Law doesn't exist as a law at all - and the only place it does exist is in the minds of journalists!
How many escape pods are there? "NONE,SIR!" You counted them? "TWICE, SIR!"
This has been achieved by getting a more and more detailed understanding of the processes and eliminating the fundamental sources of the problems. The costs of doing this are immense, but it works. It's striking to look at micrographs of chips today - everything looks so good. No ragged edges anywhere. Think for a moment about what that means. In some of those pictures, you can see atoms, and they're in the right places. Atoms.
It's not like the bad old days of the "purple plague", ceramics with traces of radioactive minerals, or the HP fab with the 4% yield.
they'd cost $25, get $1 Million MPG, travel 2000 MPH,
and fit in the palm of your hands.
Turing. Alan Mathison Turing. And here is a link.
There comes a time when only so much can be fit on that piece of silicon.
e lemen t/C
.525 the size of a Si atom.b /elemen t/C
Couldn't resist replying since i'm on your foes list for god knows what.
Moores law doesn't just apply to silicone, it applies to integrated circuit design in general. If moores law was based purely on the manufacturing techniques at the time, of course it wouldn't hold true in 20 to 30 years.
What we've seen though is a change in manufacturing processes, and with the research going on in quantum computing, light computing, and biological computing, I would speculate that we will see "moores trend" (calling it that because it's not really a law) will continue on course as these advancements are made.
Take for example our use of Si (silicon) for every IC designed today. We use it because of it's strength, and low electrical conductivity. It's a rather large atom though, and we will run out of space eventually using it.
http://www.cs.ubc.ca/cgi-bin/nph-pertab/tab/
But wait! Right above Si on the periodic table of elements is C (carbon) which is roughly
http://www.cs.ubc.ca/cgi-bin/nph-pertab/ta
Now why don't we use carbon based IC's? Well for one thing, carbon does not play well with itself unless you use a lot of heat and pressure (Carbon melting point is 3727c vs Si's 1410c). Secondly we haven't really mass produce the carbon buckyballs/nanotube enough where we could actually use them in place of Si.
Now where was I going with this... Oh yeah..
Basically Moores law will continue to hold true as long as material manufacting keeps up. Silicon has nada to do with it.
experience curve. To quote an article from the Harvard Business Review
"Building stategy on the experience curve" (HBR March-April 1985, pg 143):
The author then presents a graph showing that Dynamic RAM costs fell at 30%
per every doubling of cumulated output from 1976 to 1984. Besides semiconductors,
the author gives examples from the chemical industry and also the Model T Ford.
No electrons were harmed creating this post, though some may have been subjected to electrical and/or magnetic fields.
Moores law doesn't just apply to silicone....
When applied to silicone, it is formulated as follows:
"The size of Britney Spears's breasts doubles every 18 years."
Hey kids, there's only 5 days left 'til Yak Shaving Day!
This sentence in the article triggered my bullshit alert.
..that Motorola is somewhat immune to the ravaging effects of Moore's Law.
How did they escape "Moore's" clutches, and more importantly, how do we get them back in?
Coincidentally, I just today received my 11 x 17 inch print of this Zippy cartoon from April 2001, signed by Griffy himself. Destined for my office wall, of course.
my pet peeve is people who pompously pontificate about meaningless crap like Moore's Law.
"And this is my boy, Sherman. Speak, Sherman." "Hello." "Good boy."
By the time they actually release Doom III, there will be a computer that will actually be able to play it...
*keeps fingers crossed*
Moore always pulls through!
..they'd crash every couple hours
nah, give me a good old fashioned vegetable-diesel car anyday.
The article and my recollection say that Moore's law predicts a doubling (of whatever) every 12 months, but I regularly see it sited as 18 months. So my question is: after how many or how much altering of the original numbers does Moore's law become something else?
It is, after all a fact that at some point these densities CAN'T double any longer and while we are not right up against the speed of light and molecular limitations yet, we are suring getting into the same ball park.
At some point (and I think we may have reached it) the constraints placed on us by physics will have to be overcome by cleaver use of software, massively parallel systems etc. and at that point, Moore's law becomes relatively moot.
"The misrepresentation of Moore's Law in the media has always been a real pet peeve..."
./ articles have mentioned the increasing specialization of society as a source of many problems and changes. Is the inability of the media to accurately report on subjects yet another product of this specialization? Both the reduced ability of the reporter to understand technical information and the reduced ability of Americans to spot (and hold media responsible for) incorrect/bad/misleading reporting have, perhaps, allowed the problem to bloom enormously.
Is it possible that Americans have come to mistrust the media, because the media reporters no longer understand 99% of the subjects on which they report?
Earlier
Perhaps Moore's Law is inversely applicable to media reliability. Every two years the reliability and accuracy of the media is halved. Every two years the ability of the average American to spot the innacuracies is reduced by half.
better that than "Daddy's Little Holster", like you
hm. I don't remember why you were on the foes list, but you seem intelligent enough not to be there. removed. And i must say, i agree wholly with your post, but maintain that if it were not for Moore's Trend, one of two things would have happened:
1) chips would run cooler and slower than present, but would still be more efficient than their contemporaries (such as comparing a Astro or Crusoe to its speedmates)
or
2) chipmakers would be ignoring this rate and going potentially higher than Moore claimed.
I may be wrong, YMMV, etc.
In SOVIET RUSSIA... erm...NSA AMERICA, the Internet logs onto YOU!
You gotta love Ars. In a day and age when some people purporting to be geeks still belive that a "G4 is up to twice as fast as the fastest Pentium 4," and when tech articles and writing (even in the Linux world, and in Maximum PC) have been incredibly dumbed down, Ars Technica still isn't afraid to have in depth, technical articles. Their articles have words like "pipeline" and "execution unit" and their CPU articles (in particular the PC vs PS2 one) are very informative. Good job guys!
A deep unwavering belief is a sure sign you're missing something...
You think you've got it bad? On mine it was a GIANT FLASHING XBOX AD! With GIANT FLASHING TEXT
ugh.
*hopes that you parse html in your head*
Feel that power? That's mah MOUSING FINGER
NO, No... her breast size doubles every 18 months is seems... the height of her breasts halves every 18 years. With all that dancin' and silicone, 18 years from now her tits will be at her waist (and in another 18, her knees). That is unless the advances in plastic sugurey can keep up.
The most interesting thing about Moore's Law, to me, is that it implies that technology advances at an exponential rate. If that's true, then there are some obvious, serious consequences ahead.
IBM announced recently that they will be producing a computer with roughly the same computing power as the human brain, possibly by 2005. That's a pretty significant milestone, if you think about it. Following through with Moore's Law, we should have a computer that is 1000 times more powerful than the human brain as soon as 2020... and a computer that is a million times more powerful than the human brain by 2035.
A million times more powerful than the human brain! What will we do with a computer that powerful? Or, maybe a better question is: What will a computer that powerful do with us?
Kurzweil has a lot of great articles on this sort of thing.
Just not in the sense of a scientific law. It is more like Murphy's law, Parkinson's Law (Work expands to fill the time available) Clarke's Third Law (Any sufficiently advanced technology is indistinguishable from magic) or Beauregard's Law (When you're up to your nose, keep your mouth shut)
Moore's is based on the unscientific observation of a trend. If you watched early life form with the same mindset you'd have seen increasing size from bacteria to pond slime etc and have extrapolated that by now all life forms would be the size of supertankers.
Engineering is the art of compromise.
> Current evolution should be taught as and called "The Law of Evolution."
I'll stick with "Theory," on the grounds that one meaning is "a systematic statement of principles involved." That is broader than "Law," and better describes the standings of both evolution and relativity.
As for the "it's only a theory" people, I doubt that calling evolution a "law" will change their minds.
There were a link on pages linked off of that story. Found it at http://www.intel.com/pressroom/kits/quickrefyr.htm and also links to History of the Microprocessor.
These show the history, compare die sizes, etc. and add some context to this article. Had to dig a bit, but I love this kinda stuff. Bet Im not the only one.
Tequila: It's not just for breakfast anymore!
2) chipmakers would be ignoring this rate and going potentially higher than Moore claimed.
.gov.
.13 micron process, which is basically a nice way of saying "We can get it within .13 microns accurate" Each lith is going to be off just by a tiny bit.
.Gov get's the processors that are 10x faster in clock speed than the public for a set time, eventually the public catches up. Then it's time for a new architecture so the .gov can stay one step ahead of the public.
.gov turning cheeck to intels blatent enviromental superfund area's created in the bay area and around the world? All over the web you read about all these .gov's letting intel get away with everything from dumping toxic crap to having people work in dangerous working conditions. It's not a joke, it's all over the web.
:D
Oh absolutely. I sometimes wonder if the chip companies haven't already reached the "theoretical" limit first lithography out of the die.
I'll expand a bit. For instance, currently we have P4's that run at 3ghz. BUT the bin sorting may yeild chips that can run way above that. Possibly 10ghz or 20. These "superchips" may be in the top %99.9999999 percent of the bin sort.
So what happens to these chips? Well, i'd imagine they keep a few to learn why it runs so nice so they can make more, and the rest are given to the
Now what makes this chip so perfect is the accuracy of the lith transfer used, despite our best efforts the closest we are so far is a
Now the real gamble is how well you can replicate the best of the bin. If it only takes intel a few months to tweak their lith's, they can slowly release sub speed processors to the consumer market. The
I dunno, it's a weird conspiracy theory of mine, but I use conspiracy theory as an exercise in creativity. But how else would you explain the
Friend added
I can't help but be reminded of the Dune (Frank Hurbert) series' take on all of this. In this fictitious future it is discovered that indeed the human brain is capable of far greater than even the greatest quantum artificial computing devices and best software algorithms. More and more our society is less utilizing computing devices in order to increase understanding and productivity but becoming dependant on them like a crack baby. Computers, networks and the like are amazingly interesting yet why have we forgotten what so many in our history have taught about increasing the power of the mind. Forget the talk of computers taking over... I am just referring to mental atrophy where knowledge replaces intelligence. We may know more buzz words and technical schematics today yet I feel like most know even less useful information than before as well as having the ability to grow, adapt and USE any knowledge. Just like an overprotective parent our society is setting ourselves up for the possibility of a very rude awakening.
I have seen the chaos of a regular grocery store network going down and nobody being able to cope and adapt yet I seem to remember grocery stores before realtime database storage that did just fine with large supply and demand of items.
However, besides all this I really have to question anyone that can say with a serious tone that a computer would have the same computing power of the human brain in 2 years. We are not even sure what the brain is capable of so how can we swear by a comparison? If someone built a mechanical/eletrical (or other method) neural net of tiny nodes with not only the billions of interconnecting data links but the ability to remap them as needed and change the internal sequencing codes as well, and then made it faster and doubled the connections and speed at which adaptations happened... I think that still we would find that the human brain could out process it in certain arenas. Don't get me wrong, I am impressed by what IBM and others are building but lets not water down the achievement by reducing the comparitive object.
Or even easier, just forget the -j 2 on your 'make.'
Mean that buying any PC immediately causes Best Buy to sell it for $100 less than you paid.
The first computer I owned was a Compaq Portable (about as portable as a 20" color TV with a handle on it). I paid $3,000 for it - with a 10mb hard drive and a 1200bps Hayes modem.
Today, that same $3,000 - not even adjusting for inflation, and buying only retail equipment, would get me a 2.5+ghz machine with a 20" LCD flat panel. And if I noodge the sales droid enough, toss in a disposable HP printer (as if they make another kind...)
The only concern I have about personal computers these days is... how the heck do I keep track of the exploding volume of information on them?
How do I keep 2,500 family pictures? And find the one of a friend's birthday party?
How do I organize 10 years of letters and emails? And not lose track of the ones from my dad?
Carbon and silicon have a slight difference -it's a network molecule. If you look at CO2, for example, it looks something like O-C-O, while a Si02 looks more like O-Si-O-Si-O-Si, and so on. It forms many many more sigma bonds. That's why it's such a great conductor.
-----
Score 3? For what? Being wrong, at length? - smirkleton
This section of the present article aims to give you a general understanding of the various trends and factors that Moore wove together to predict the rise of the personal computer, the mobile phone, the digital wristwatch, and other innovations that we now take for granted.
Actually I think the digital wristwatch is a pretty neat idea!
It seems like a good start would stop calling all known facts of science "laws", a term that has some kind of meaning, in a juridical sense.
When and where science were given right to have "laws" and everyone else don't?
My bad. It was a typo in index of the reader I was quoting from. The actual article had the name correctly printed, but I copied it from the incorrect index.
This message is encrypted with Quad ROT-13 to protect the author's copyright under the DMCA.
Moore was talking specifically about the number of devices per square inch on a single substrate. In other words, he was talking about integrated circuit semiconductor fabrication technology and the economics involved. Turing was dealing in much broader concepts.
I see even classic Slashdot is now pretty much unusable on dial up anymore.
Fellow programmer, greetings! You are reading a letter which will bring
you luck and good fortune. Just mail (or UUCP) ten copies of this letter
to ten of your friends. Before you make the copies, send a chip or
other bit of hardware, and 100 lines of 'C' code to the first person on the
list given at the bottom of this letter. Then delete their name and add
yours to the bottom of the list.
Don't break the chain! Make the copy within 48 hours. Gerald R. of San
Diego failed to send out his ten copies and woke the next morning to find
his job description changed to "COBOL programmer." Fred A. of New York sent
out his ten copies and within a month had enough hardware and software to
build a Cray dedicated to playing Zork. Martha H. of Chicago laughed at
this letter and broke the chain. Shortly thereafter, a fire broke out in
her terminal and she now spends her days writing documentation for IBM PC's.
Don't break the chain! Send out your ten copies today!
For example, if \thinmskip = 3mu, this makes \thickmskip = 6mu. But if
you also want to use \skip12 for horizontal glue, whether in math mode or
not, the amount of skipping will be in points (e.g., 6pt). The rule is
that glue in math mode varies with the size only when it is an \mskip;
when moving between an mskip and ordinary skip, the conversion factor
1mu=1pt is always used. The meaning of '\mskip\skip12' and
'\baselineskip=\the\thickmskip' should be clear.
-- Donald Knuth, TeX 82 -- Comparison with TeX80
- this post brought to you by the Automated Last Post Generator...