Talk:Moore's law

From Wikipedia, the free encyclopedia
Jump to: navigation, search
Former good article Moore's law was one of the Engineering and technology good articles, but it has been removed from the list. There are suggestions below for improving the article to meet the good article criteria. Once these issues have been addressed, the article can be renominated. Editors may also seek a reassessment of the decision if they believe there was a mistake.
          This article is of interest to the following WikiProjects:
WikiProject Computing / Hardware (Rated B-class, Top-importance)
WikiProject icon This article is within the scope of WikiProject Computing, a collaborative effort to improve the coverage of computers, computing, and information technology on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
B-Class article B  This article has been rated as B-Class on the project's quality scale.
 Top  This article has been rated as Top-importance on the project's importance scale.
Taskforce icon
This article is supported by Computer hardware task force (marked as Top-importance).
WikiProject Computer science (Rated B-class, Mid-importance)
WikiProject icon This article is within the scope of WikiProject Computer science, a collaborative effort to improve the coverage of Computer science related articles on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
B-Class article B  This article has been rated as B-Class on the project's quality scale.
 Mid  This article has been rated as Mid-importance on the project's importance scale.
WikiProject Engineering (Rated B-class, Mid-importance)
WikiProject icon This article is within the scope of WikiProject Engineering, a collaborative effort to improve the coverage of engineering on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
B-Class article B  This article has been rated as B-Class on the project's quality scale.
 Mid  This article has been rated as Mid-importance on the project's importance scale.
WikiProject Business (Rated B-class, Low-importance)
WikiProject icon This article is within the scope of WikiProject Business, a collaborative effort to improve the coverage of business articles on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
B-Class article B  This article has been rated as B-Class on the project's quality scale.
 Low  This article has been rated as Low-importance on the project's importance scale.
WikiProject Transhumanism (Rated B-class, Mid-importance)
WikiProject icon Moore's law is part of WikiProject Transhumanism, which aims to organize, expand, clean up, and guide Transhumanism related articles on Wikipedia. If you would like to participate, you can edit this article, or visit the project page for more details.
B-Class article B  This article has been rated as B-Class on the project's quality scale.
 Mid  This article has been rated as Mid-importance on the project's importance scale.

Future trends[edit]

Future trends omit the most important developments extending Moore's law. These are the real world technologies which are extending Moore's law today. That's not speculation:

Vertical stacking (Three-dimensional integrated circuit): Already in use on consumer products, like Samsung SSD 850, which piles 24 layers.

Many-valued logic: Also on sale in consumers products, and on his 3rd generation! Again, a consumer product on sale is the Samsung 840, which stores 3 bits per cell, and is capable of manage 8 binary values at once.

this page had a reference, but it was deleted. That's nonsense, since these technologies are the real world ones extending Moore's law. — Preceding unsigned comment added by (talk) 22:37, 7 July 2014 (UTC)

Both IBM (2014, and Kahng (2014, support your observation that new directions are needed. IBM (2014) is expanding research beyond CMOS scaling. Kahng (2014) notes that:

the 'heartbeat of the roadmap' – Mx pitch scaling – is slowing due to many reasons that are not directly related to patterning. These reasons, spanning material properties, variability and design margins, electrical performance, and design tool limitations, have reduced the design benefits of recent technology nodes”

Kahng (2014) goes on to say:

realities of cost and risk force aggressive exploration of 3D scaling (for NAND flash and multi-die integration) and heterogeneous integration (More Than Moore, and beyond-CMOS) paths for future semiconductor products. Lithography and patterning have been joined by 3D scaling, deposition, etch, planarization, next-generation interconnect materials, etc. as first-class enablers of the continuation of Moore’s Law. (talk) 22:41, 10 July 2014 (UTC)

I find it hard to believe this law still works.[edit]

It's for a few years now that I notice a distinct slow down. In the 90s, early 00s and certainly the 80s I distinctly remember computers almost doubling in power in almost a year and now it appears to take around 4-5 years. And no, I don't think a couple more cores on a x86 actually double its power, and we even stopped doing that.

And this is not unsourced. There are sources explicitly calling for a noticeable slowdown. e.g. I just watched a Michio Kaku video with him explicitly calling it. I'm just saying this article sounds too favorable to the law compared to the obvious signs. --fs 03:52, 13 December 2012 (UTC)

Moore's Law is about the doubling of transistors, not performance. Tom.gangemi (talk) 15:45, 31 July 2013 (UTC)
We need sources that say this. ---- CharlesGillingham (talk) 04:39, 27 January 2014 (UTC)
The slow pace of the quality adjusted IT equipment price index since 2010 supports your observation. (talk) 03:28, 21 May 2014 (UTC)
First of it's not a law in any scientific (natural) sense. Second its definition is not the true reason it's true. The true reason lies in costs, efficiency, and yield. Developing process technology isn't cheap and yield vary wildly. These limit the choices for the next step one wants to take. The simplest minimum improvement or smallest improvement factor that is acceptable satisfying is two, hence, this is the choice chosen all the time. That's why doubling is always true but not necessarily time in between. Mightyname (talk) 12:24, 25 August 2014 (UTC)
Just for the fun of it a "truer" "law" would be:
P_{\text{(n)}} = \frac{P_{\text{(n-1)}}}{\sqrt{2}}
where P is a manufacturing process and n the process generation. Compare it with historic records in Semiconductor device fabrication. Mightyname (talk) 13:15, 25 August 2014 (UTC)

GA review improvements[edit]

A 2011 GA review by Astrocog (talk · contribs) contains some good suggestions for improvements. Not much of it has been addressed in the current version. I'm inclined to implement these suggestions when I have time unless anyone finds anything in these suggestions to be controversial. ~KvnG 17:45, 2 August 2013 (UTC)

I've been watching this article for about five years, and it seems to me that nobody really wants to take the time to take it to GA or FA, so if you want to take it on, that would be great.
The article suffers from a large number of "drive-by" edits, some of which help, some of which don't. There are several of us watching here to try to prevent nonsense and keep the balance. Only the worst edits actually get fixed. Thus the article is quite spotty over all without a real editorial hand to keep it organized, even out the prose, keep the balance, and track down the sources. ---- CharlesGillingham (talk) 04:44, 27 January 2014 (UTC)
This article was over-hyping the excimer laser before recent edits, as the excimer laser main article still does. Other innovations deserve mention, like the sensitive photoresist that enables use of the laser. (talk) 03:55, 21 May 2014 (UTC)
V93a98 wrote the following edit summary on 2 June 2014‎:

Undid good faith revision 610969766 -- reference is inappropriate, just as when describing invention of a new surgical procedure, one does not cite invention of the knife. Proper place for the reference is in article on excimer laser, where it exists.

Eons separate the invention of the knife and of the new surgical procedure, and these two don't sound alike. Mere centuries separate the invention of telescope lens polishing and of a new chemical-mechanical wafer polishing procedure. Nonetheless, the article mentions the antecedent polishing to provide insight, credit to the original inventors and historical context.

Bear in mind that just one decade separates the excimer laser in 1970 from the excimer laser for photolithography c. 1980 (Jain, Willson patent). Moreover, these two are confused easily, because of their similar nomenclature. Lasing excimers may sound alike to readers who are not immersed in the photonics or in the semiconductor photolithography equipment industries. And even to some who are. Therefore IMO and in the opinion of D. Greenwood, one should cite both the new invention and its antecedent.

Secondly addressing V93a98 in particular, one would not remove good-faith edits (as you did on 31 May and 2 June) without discussing first on the talk page. Under these circumstances, your deletions might seem inappropriate. (talk) 23:22, 12 June 2014 (UTC)

The picture in the top right corner only goes to 2011[edit]

this image

Shouldn't the picture be updated soon? Why not update in on a yearly basis? Why not make a script to update it automatically, even more often? Zanthius (talk) 19:11, 6 February 2014 (UTC)

Interesting idea. Is there a source of data that would support automatic updates? You could ask the author of the image where he got data and see if he can easily update. I'd like to see other improvements, too, like something that makes it easy to see a doubling every two years; I can't tell from the line whether it's on that slope, or a fit to the data. Also the styling in the title would be better if it conformed to MOS:CAPS and MOS:DASH. Dicklyon (talk) 21:16, 6 February 2014 (UTC)
The microprocessor chronology here on wikipedia lists this data for least eight newer cpu's, dated 2012-2014.
I tried unsuccessfully to update the hard disk drive chart a little further down in this article with 2014 popular models sold at Newegg (in GB): 300 500 1000 2000 3000 4000. Any suggestions? (talk) 03:41, 21 May 2014 (UTC)

This whole article, but this graph in particular, is so lacking in any mathematical rigour as to beggar belief. There's not even the equation for Moore's law: f(x)=2^(x/2) which this graph patently does not follow. It might be called a best fit logarithmic line, but there's not even any sourcing to show if the data are correct.Myersdtm (talk) 07:26, 11 September 2014 (UTC)--Myersdtm (talk) 07:26, 11 September 2014 (UTC)

The graph has a two-year doubling time, verified by (LN(2) / LN((1.2E9 transistors / 2000 transistors)^(1 / (2010 – 1971)))). As for sourcing, the microprocessor chronology and transistor count articles have references that could be used in this graph.
Even so, I agree that the graph and the article lack rigor. The graph is not updated after 2011; there's no indication that these transistors were minimum cost,[1] nor that these MPUs were produced in high volume; transistor count may not represent performance; and “dark silicon” presently limits thermally the number of usable transistors.[2][3] (talk) 23:35, 11 September 2014 (UTC)

I produced this graph and in light of the discussion here will update it. I used the microprocessor list from Transistor count as a source for the current image. Does anyone have a suggestion as to what raw data I should use for the update? As far as the line on the graph goes, the slope is that of the trasistor count doubling every two years, which is consistant with the definition of Moore's Law in this article's introduction. I felt it was better to include the Moore's Law line rather than that of the best fit to the data, which would constitue original research. The only variable in that case is the position of the line on the graph: its intercept rather than its slope. I chose to position it as if it was a best fit to the data to facilitate a rough visual comparison. Do let me know if anyone has an other idea about how to position it. This discussion may be more appropriate on the talk page of the image as it is also used on the Transistor count article. However, probably more people will see the discussion if it is here. -- Wgsimon (talk) 12:55, 12 September 2014 (UTC)

I suggest u position the line at the 1975 date and transistor count when Moore restated his observation and so label it so as to avoid misunderstanding (something like "Doubling of transistor count from Moore's 1975 observation"). For consistency u should continue to use transistor count from microprocessors. You might want to consider adding transistor counts from Flash Memory as a second set of data points starting circa 2000. Finding reliable sources for the additional data shouldn't be hard, you'll probably have to make a choice between several apparently reliable sources so be careful :-) Tom94022 (talk) 19:36, 12 September 2014 (UTC)
Updating post 2011 with Transistor count and/or Microprocessor chronology raw data would be a step forward. The slope (two year doubling time) and position seem reasonable. Changing the 1971 start date when MPUs originated or the title of the graph to conform to a particular prediction (1965, 1975 or 1979) isn't warranted. The focus ought to stay on MPUs: adding flash memory, DRAM or GPU data would complicate the graph. (talk) 20:48, 13 September 2014 (UTC)
(Personal attack removed) (talk) 01:22, 16 September 2014 (UTC)

See also[edit]

I made some progress cleaning up the See also section as per GA review suggestion. I believe the following links don't belong in the See also section but the article should be improved to include them as links in the body. ~KvnG 14:36, 28 March 2014 (UTC)

Should "processor speed" link to Clock rate?[edit]

The introductory paragraph states "The capabilities of many digital electronic devices are strongly linked to Moore's law: processing speed". I assume that what the original author meant was performance not merely clock speed. If so, having "processing speed" link to Clock rate would be somewhat misleading. — Preceding unsigned comment added by Paul A. Clayton (talkcontribs) 17:51, 8 June 2014 (UTC)

Yes, the clock speed trend is flat for the past decade, and performance isn't easily measured. Transistor count is another obsolete performance metric. During the past decade, quality adjusted microprocessor price indexes, which try to incorporate performance, indicate that Moore's law advancement has continued.((ref. Byrne(2013)) I've replaced clock speed with microprocessor prices. There are likely many more Moore's law indicators. — Preceding unsigned comment added by (talk) 21:25, 9 June 2014 (UTC)

Picture caption question[edit]

What year/version smartphone does the picture caption refer to? I am referring to the current version of this article as of this comment, there is a picture of an old computer, the caption under the picture reads: "An Osborne Executive portable computer... weighs 100 times as much, has nearly 500 times ... 1/100th the clock frequency of the smartphone." I don't know what "the smartphone" is, since each year they keep getting better and better (... which is kind of the point of this article, no?...)

More generally, should this caption be qualified and referenced? I would suggest replacing "the smartphone." with something like "the Google Nexus 5 smartphone released in 2013 [ref].". (talk) 19:55, 11 June 2014 (UTC)

It clearly states in the caption that it is a '2007 Apple iPhone with a 412MHz ARM11 CPU' -- Wgsimon (talk) 21:34, 11 June 2014 (UTC)

The caption states the Osborne cost ten times as much as the iPhone after adjusting for inflation. The Osborne listed for $2,495.00 in 1982 which is equivalent to $6,100 in 2014. Did the iPone actually cost $600 in 2007? I don't have trouble remembering prices of computers in the early 80s but I'm not sure the iPhone cost that much. If I'm wrong, I apologize. (talk) 03:10, 16 July 2014 (UTC)

From the iPhone article:
The two initial models, a 4 GB model priced at US$ 499 and an 8 GB model at US$ 599, went on sale in the United States on June 29, 2007...'
According to the inflation adjusted price of the Osbourne is $5,360.00 in 2007 dollars. This is 10.7 or 8.95 times the price of the phone. -- Wgsimon (talk) 17:19, 16 July 2014 (UTC)
Oh boy, I'm always so busy calculating inflation to today that I completely spaced on doing it for 2007. D'uh!
I also forgot to make a couple of other points. Comparing an Osborne to an iPhone has two problems. One is that iPhones come with Apple's inflated price tag, which skews the price value compared to a modern day device. Also comparing the iPhone to an Osborne is like comparing apples to oranges (sorry about that). The Osborne includes components the iPhone doesn't have, which inflates its costs and skews the cost value relative to the Osborne. I wouldn't even compared an old computer to a phone, since part of the phone's cost is the service plan. (I realize the compactness of the phone is part of the reason to use it,) It would be better to compare two computers that are more comparable to each other, which I admit isn't easy, given all of the technological changes over the years. (talk) 01:38, 20 July 2014 (UTC)

"Moore's law" for ARM faster?[edit]

With Apple A8 at 2 billion transistors, I saw that CPU speed is 50x the original iPhone (note, not since original ARM). Isn't the speed growing faster than for say Intel (I know the "law" is about transistors). Even counting transistors desktop Haswell is about the same (2 billion?) and if ARM used fewer than Intel in the past and same or similar now (or relatively now higher fractiopn) then also applies for transistors. comp.arch (talk) 11:39, 16 September 2014 (UTC)

"predicted that growth will slow at the end of 2013"[edit]

i tagged this with "when", and i'm sorry if that's wrong, but i don't know how else to draw attention to the fact that it seems wrong to use a sentence wording with "will" at this point of the sentence. shouldn't it be a quote instead? writing "would" seems to go against the guidelines of not using timesensitive language. — Preceding unsigned comment added by (talk) 19:23, 23 September 2014 (UTC)