Talk:Moore's law

Future trends

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 181.20.137.16 (talk) 22:37, 7 July 2014 (UTC)

Both IBM (2014, http://www.prnewswire.com/news-releases/ibm-announces-3-billion-research-initiative-to-tackle-chip-grand-challenges-for-cloud-and-big-data-systems-266536231.html) and Kahng (2014, http://vlsicad.ucsd.edu/Publications/Conferences/306/c306.pdf) 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.
71.128.35.13 (talk) 22:41, 10 July 2014 (UTC)

I find it hard to believe this law still works.

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. 71.128.35.13 (talk) 03:28, 21 May 2014 (UTC)

GA review improvements

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. 71.128.35.13 (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.71.128.35.13 (talk) 23:22, 12 June 2014 (UTC)

Hendy's law

Description and diagram was removed by 93.180.4.4 with the edit comment "Chart is plotted awfully, there are even two identic models relesed in sequential years, I mean CX 7300. The years are outdated and the dependency is so straight, that I think there are mistakes." I think we should consider restoring this but we need to find a reference. Here are some candidates I found in a quick search: [1], [2], [3], [4]

I created this graph.

Yes the CX 7300 is listed twice. It had a significant mid/late life price drop that created the new benchmark Pix/$ at the time, so it deserved a new plot.

I only chose the best Pix/$ cameras as they came along, and I agree teh line looks suspiciously straight, but I can only plot the data I collected!

Happy to debate ... although recollecting the raw data might be a challenge!

Barry Hendy Barry.hendy (talk) 10:08, 2 December 2013 (UTC)

It seems to me you should restore it (if you haven't already). ---- CharlesGillingham (talk) 04:47, 27 January 2014 (UTC)

I don't see anything I'd call a WP:RS on this. And if there is, it shouldn't be the author with the WP:COI who restores it. Dicklyon (talk) 08:07, 27 January 2014 (UTC)

I had a private discussion with Barry.hendy and added back a brief discussion with references. I did not restore the graph because of WP:RS and WP:OR concerns. ~KvnG 15:10, 30 January 2014 (UTC)

The picture in the top right corner only goes to 2011

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? 71.128.35.13 (talk) 03:41, 21 May 2014 (UTC)

Murphy's Law and Quality Control

Line 182 (I think):

"Moore says he now sees his law as more beautiful than he had realized: 'Moore's law is a violation of Murphy's law. Everything gets better and better.' Some believe Murphy's law has been cleverly hidden from end users by increasingly skilled quality control."

The first bit is attributed to Gordon Moore himself, but the latter is currently my own statement (I dropped a {{cn}} tag on it.) We have all kinds of articles about the technical specifics of Murphy's law (paraphrased: "Anything you allow to go wrong will go wrong") and not allowing too many things to go wrong, even as transistor counts soar into the trillions. This includes design-for-test circuitry, radiographic inspection, error correction coding, automated test equipment, skilled process engineering and FCC/IEEE/IPC/ISO/JEDEC/ETC/ETC/ETC quality standardization. Murphy's law can't be truly violated in the manner Moore describes, and the industry does know this. I just haven't seen a published generalization of that, except my own, obviously. I'm guessing there has to be one already out there for the finding. Featherwinglove (talk) 01:46, 13 February 2014 (UTC)

See also

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)

• Empirical relationship
• Grosch's law
• Haitz's law
• Koomey's law
• Microprocessor chronology
• Quantum computer

Should "processor speed" link to Clock rate?

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 (talk • contribs) 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 71.128.35.13 (talk) 21:25, 9 June 2014 (UTC)

Picture caption question

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].". 128.102.242.117 (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.209.179.21.14 (talk) 03:10, 16 July 2014 (UTC)