backtop


Print 57 comment(s) - last by JumpingJack.. on Oct 12 at 10:50 PM


A young Gordon Moore circa 1975  (Source: Reuters)
Gordon Moore took part in the afternoon keynote during IDF 2007

The fall edition of the 2007 Intel Developer Forum (IDF) is officially underway from the San Francisco Moscone Center.  The Tuesday morning keynote featured more details about the Nehalem architecture as one of the main points of the discussion.

In a later session, Dr. Moira Gunn, host of NPR Tech Nation, hosted a fireside chat with Gordon Moore, Intel co-founder and creator of Moore's Law.  Moore received a well-deserved standing ovation from the crowded conference hall packed with thousands of attendees more than willing to respect a Silicon Valley legend.  

Of course, the question on everyone's mind was the validity of Moore's Law. Specifically, whether or not it holds up today the same way it did when Moore first documented his observations almost forty years ago.

Moore's Law -- actually more of a conjecture -- essentially states the number of transistors placed on an integrated circuit doubles every two years.  His observation helped outline trends the semiconductor industry for more than 40 years. 

"We have another decade, a decade and a half, before we hit something that is fairly fundamental," Moore said during the session.  That something "fundamental" is material science.  Even the most advanced lithography conceivable today can't eliminate the brick wall that is the nanoscale. 

Even at some point, lining up individual atoms no longer becomes feasible for transistor design.  Researchers from Intel are already easing into the field of using carbon nanotubes for processor interconnects; a team from the University of Pennsylvania just announced a new method for storing data via phase-changing nanowires.

"It's an exciting time," he said.  "I'd love to come back in 100 years and see what happened in the meantime."

Of course, even Moore's understanding of transistor trends is no match for the prowess of ambitious engineers. Conventional computing principles go out the window with the advent of quantum computing, for example.  Other types of alternative computing, including biological-based neural-computing, does not readily translate to transistor-count -- but that hasn't stopped researchers from making enormous progress in the last few years.

The death of Moore's Law is imminent, but new research and new materials assure that its successor will pack the same punch.


Comments     Threshold


This article is over a month old, voting and posting comments is disabled

RE: Already dead
By DOSGuy on 9/20/2007 6:54:08 PM , Rating: 2
quote:
When Moore first stated his "law" in 1965, he gave the interval of 12 months. In the early 1980s, Intel was quoting it as 18 months. Today, its been revised to "about two years" between nodes. In a decade, Intel will be telling us Moore's Law means "transistor counts double every 3-4 years".


I'm sorry, but I just can't let this statement slide. A little research is in order here.

When people say that Moore stated Moore's Law in 1965, they're referring to an article in Electronics Magazine's April 19, 1965 edition. He wrote:

"The complexity for minimum component costs has increased at a rate of roughly a factor of two per year ... Certainly over the short term this rate can be expected to continue, if not to increase. Over the longer term, the rate of increase is a bit more uncertain, although there is no reason to believe it will not remain nearly constant for at least 10 years. That means by 1975, the number of components per integrated circuit for minimum cost will be 65,000. I believe that such a large circuit can be built on a single wafer."

The complexity for minimum component costs is quite a bit different from how we think of Moore's Law today, which Wikipedia describes as, "the number of transistors that can be inexpensively placed on an integrated circuit is increasing exponentially, doubling approximately every two years." It feels good to pretend that Moore might have stated something like that as far back as 1965, but he didn't.

The term "Moore's Law" was coined around 1970 by the Caltech professor, VLSI pioneer, and entrepreneur Carver Mead. So, when did Moore actually make a prediction about transistor densities? According to Wikipedia, "In 1975, Moore projected a doubling only every two years. He is adamant that he himself never said "every 18 months", but that is how it has been quoted."

In fact, Moore's Law, the version that we follow today (two year version), has held since at least the Intel 4004, the world's first commercial single-chip microprocessor, was released in 1971.

What exactly Moore's Law is and when it began is debatable. What is certain is that the 24 month version of it has been true since at least 1971, and Moore himself defined it that way by at least 1975. To suggest that the stated timeframe has changed from 12 months to 18 months to 24 months is not supported by any evidence that I'm aware of, and if Moore's Law ever did predict doubling at a rate faster than once every 24 months, it was only for the first 6 years after Moore's 1965 article. To suggest that Intel would change the definition that they have adhered to for 36 years at some point in the future is preposterous. It's simply too well known, and too important to the industry. They might admit that they can no longer maintain Moore's Law, but they would never dream of changing it.

For more information about Moore's Law, consult your local library, or read an excellent article on Wikipedia at http://en.wikipedia.org/wiki/Moore%27s_Law


RE: Already dead
By TomZ on 9/20/2007 7:30:16 PM , Rating: 2
I Moore's Law is just a conversation piece that really has no significant meaning at all. It neither drives nor impedes progress. It doesn't determine product development or release schedules. I think it is much ado about nothing.


RE: Already dead
By JumpingJack on 9/21/2007 2:15:51 AM , Rating: 2
To an extent ... however, if you read Moore's papers, it is really just a statement of an observation, cleverly graphed. The technicality of the shrink is an engineering problem but the rate of the shrink is driven by economics.

The motivation for shrinking is driven by reduction of costs, hence Moore's famous plot is pitched in terms of costs vs number of transistors separated into temporal curves. He simply plotted the minima in costs for a set transistor count and extrapolated the rate at which transistors increased per unit area over time.

The trend has held true since 1975 or so.... so it is not meaningless, and reflects the drive and competitive nature of this industry.

In 1965 he postulated this rate, in 1975 he revised his rate curve, and in 2007 he predicted the end... I would listen as he seems to know what he is saying :) ...

The scary part of this is when the progress does reach it's end using conventional semiconductor methods, a drastic paradigm shift will need to take place ... it will be interesting to see what that will turn out to be... new materials, completely new computational method for binary work (quantum computing, spintronics, ...) who knows.


"I'd be pissed too, but you didn't have to go all Minority Report on his ass!" -- Jon Stewart on police raiding Gizmodo editor Jason Chen's home














botimage
Copyright 2014 DailyTech LLC. - RSS Feed | Advertise | About Us | Ethics | FAQ | Terms, Conditions & Privacy Information | Kristopher Kubicki