I've just read the news, a 100-core CPU was released. Though the news is two years ago.

enter image description here

I'm wondering whether the size of the 100-core CPU is more or less just the same as Intel CPUs.

The nano-wire is already so small, as the Moore's Law seems to be dead in foreseeable future, the size of a core will be reach a limit then, how can too many cores built into one chip?

closed as not constructive by Benjamin Bannier, Sathyajith Bhat, Mike Fitzpatrick, Bobby, DMA57361 Jan 4 '11 at 9:17

As it currently stands, this question is not a good fit for our Q&A format. We expect answers to be supported by facts, references, or expertise, but this question will likely solicit debate, arguments, polling, or extended discussion. If you feel that this question can be improved and possibly reopened, visit the help center for guidance. If this question can be reworded to fit the rules in the help center, please edit the question.

migrated from serverfault.com Jan 4 '11 at 1:36

This question came from our site for system and network administrators.

  • I read it was up to 1000. – jscott Jan 4 '11 at 1:33
  • The possibilities are endless... / Nothing is impossible... – squircle Jan 4 '11 at 1:33
  • 100-core CPUs are neat and all, but how is this related to system administration? Your question is probably more appropriate on a electronics or chip manufacturing forum. – Zoredache Jan 4 '11 at 1:34
  • 4
    Over 9000, of course. – SilverbackNet Jan 4 '11 at 1:37
  • 2
    "If you were plowing a field, which would you rather use: Two strong oxen or 1024 chickens?" -- Seymour Cray – Aki Jan 4 '11 at 8:11

Moore's Law is far from dead. Read up on semiconductor device fabrication. We are only at 32nm right now, and the road map has already been laid for 22nm, 16nm, and 11nm. Moore's Law will not die until the PNP or NPN of a transistor are each one atom thick... and it may not even die then (if we can learn to manipulate quarks that is).

With that said we can expect to see as many cores on a processor as will fit in die space x given manufacturing process y. Hundreds of cores will probably be mainstream in the very near future, and thousands may be on the horizon as well.

  • Strictly speaking, the transistors in modern CPUs use gates, not junctions. Your point does stand though. – Ignacio Vazquez-Abrams Jan 4 '11 at 1:57
  • 1
    I've been told by an AMD engineer that the scales we are at are starting to see quantum effects such as electron tunneling that is limiting how small you can go. The solution has been, as you have seen, to scale out (rather than down) with multiple cores. – Keith Jan 4 '11 at 2:13
  • 1
    I think saying "FAR FROM DEAD" isn't being realistic. 32nm to 11nm is just 3 generations, @ 3 years for a generation to keep w/ Moore's law that is only a decade. A single silicon atom is 0.2nm across and even perfectly constructed a NAND gate requires 5 atoms (~1nm).Below 5nm is unlikely due to quantum effects. One way to look at is is realizing we went from 1500nm (286 CPU in 1978) to 32nm (Core I-7in 2011). If we consider the size of a silicon gate @ 1nm as the absolute limit and 5nm as a realistic limit we are much closer to the finish line than the beginning. – theUnhandledException Aug 30 '11 at 20:00
  • 2
    @theUnhandledException I'll post back in 10 years :) – ubiquibacon Aug 31 '11 at 1:41
  • 1
    @typoking That's worth a +1. :) – theUnhandledException Aug 31 '11 at 2:24

If I write a number from my imagination or if I find and cite a research paper and someone reads this 10 years from now, he will probably laugh at bad predictions.

So I'll just say that the number will be limited by Amdahl's law and specific needs of target market.

A bit of clarification on the needs part: To put it simply, compare today's GPUs and CPUs. GPUs have large number of relatively limited cores, which is OK for graphics processing, while each CPU core can do much more complex operations.

  • Agreed. See the link for the 1000-core processor in one of the comments, it's effectively a hardware MPEG-decoder. We may well end up with a very large number of very simple cores – j-g-faustus Jan 4 '11 at 5:50

Not the answer you're looking for? Browse other questions tagged or ask your own question.