Andy Grove Says End Of Moore's Law At Hand 520
Jack William Bell writes "Intel chief Andy Grove says Moore's Law has reached its limit. Pointing to current leaks in modern chips, he says -- "Current is becoming a major factor and a limiter on how complex we can build chips," said Grove. He said the company' engineers "just can't get rid of" power leakage. -- But, of course, this only applies to semiconductor chips, there is no guarantee that some other technology will not take over and continue the march of smaller, cheaper and faster processors. I remember people saying stuff like this years ago before MOSFET." Update: 12/11 22:01 GMT by T : Correction: the text above originally mangled Andy Grove's name as "Andy Moore."
Andy Moore? (Score:5, Informative)
Well, possibly... (Score:2, Informative)
Just recently I attended a seminar by a Cambridge lecturer discussing the performance benefits of quantum computing - 1/n*root(n) maximum search relationship for unsorted lists, which seems silly - but thats just quantum stuff for you - who knows, maybe it'll be the next jump to break against Moore's law. Does still look like its a while off though.
Yes... -- was Re:Andy Moore? (Score:4, Informative)
Re:Short sighted, or just playing it safe? (Score:2, Informative)
It was just a few weeks ago that AMD essentially announced their pulling out of the speed game. Just a couple of references:
http://www.forbes.com/technology/newswire/2002/11
http://www.tomshardware.com/technews/20021120_020
To me, it seems this Intel person is only validating what AMD and Ruiz have implied already, just beating them to the punch. Intel have let AMD take the fall -- perhaps.
Moreover, AMD were trying to spin this as "listening to the customer", which was arguably the Right Thing(TM) but also to stir the fear in consumers who feel enslaved to Intel.
Re:I guess it isn't a Law then (Score:2, Informative)
Actually it is transistor density on the chip. But that's just nitpicking. Moore's hypothesis has nothing to do with Mhz and/or power (which both are unrelated too), but with transistors
Re:Andy Moore? (Score:5, Informative)
Re:Other materials (Score:3, Informative)
Interesting to note, though, that while a germanium PN junction only has a voltage drop of 0.3V, silicon has a drop of 0.7V. Anyone know what the voltage drop would be for a carbon junction?
Also, one of the main reasons they switched from germanium to silicon was silicon's greater endurance to physical stress. I'm pretty sure diamond will be still stronger, despite the doping.
Maybe, just maybe, they'll be able to use channels in the diamond crystal as optic conductors. Considering crystalline Si is opaque, that would be a huge advantage. Wouldn't it be great if your clock signal was represented as a flash of light through the entire die? (Have to worry about reflection off the sides, though. Hmm.)
Anybody else have thoughts or knowledge?
Re:[ More Quotes Like This ] (Score:4, Informative)
Gates is supposed to have said, "640K should be enough for anyone." The remark became the industry's equivalent of "Let them eat cake" because it seemed to combine lordly condescension with a lack of interest in operational details. After all, today's ordinary home computers have one hundred times as much memory as the industry's leader was calling "enough."
It appears that it was Marie Thérèse, not Marie Antoinette, who greeted news that the people lacked bread with qu'ils mangent de la brioche. (The phrase was cited in Rousseau's Confessions, published when Marie Antoinette was thirteen years old and still living in Austria.) And it now appears that Bill Gates never said anything about getting along with 640K. One Sunday afternoon I asked a friend in Seattle who knows Gates whether the quote was accurate or apocryphal. Late that night, to my amazement, I found a long e-mail from Gates in my inbox, laying out painstakingly the reasons why he had always believed the opposite of what the notorious quote implied. His main point was that the 640K limit in early PCs was imposed by the design of processing chips, not Gates's software, and he'd been pushing to raise the limit as hard and as often as he could. Yet despite Gates's convincing denial, the quote is unlikely to die. It's too convenient an expression of the computer industry's sense that no one can be sure what will happen next.
Helpful battery tip: (Score:0, Informative)
Apropos links (Score:3, Informative)
Re:Other materials (Score:1, Informative)
Number of transistors per square inch is what doubles according to Moore's law.
If leakage current is approximately constant for a given process (fabrication recipe) then the static (no clock running) power dissipation for a chip made with that process will be dependent on the number of transistors. I imagine it will be linear with the number of transistors.
Until recently, the static power dissipation has been negligible, and that is why most power saving schemes center around stopping clocks when possible. But the techniques for reducing switching-related power dissipation lead to increased static power dissipation. When the two cross over, no further improvement will be possible without some kind of new approach.
This is what Grove and Moore are talking about.
--AC
What about silicon-on-insulator (Score:2, Informative)
Re:What about silicon-on-insulator (Score:3, Informative)
IBM has been using partially-depleted SOI which actually increases leakage current and therefore increases standby power.
Fully-depleted SOI should have lower leakage current due to better control over the transistor channel. While Intel doesn't call it SOI, they announced their "terahertz transistor" sometime last year which is actually a fully-depleted SOI device.
Another way to reduce leakage power would be to use dual-gates when building the transistor. There is a decent amount of research going on in this field. Dual gate would offer large decreases in leakage current.
Re:Newton? (Score:3, Informative)
so sorry newtons laws are already old
Re:A bit overestimated (Score:3, Informative)
Anyway taking your comparison and using a benchmark of the time (the Norton System info benchmark [tripod.com]):
80286-16 got a 9.9 (i.e. 9.9x as fast as the XT)
80386-20 got a 17.5
More importantly the cache configurations that came with the 80386-25 raised the score to a 26.7
adjusting for the increase in mhz:
26.7 * 16 / 25 = 17 which is close to double.
I'll stand by my statement.