The maximum cores a CPU will contains?

cpu

07
2014-07

Xiè Jìléi

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?

Answers

ubiquibacon

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.

AndrejaKo

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.

Related Answers

Seasoned Advice (cooking)

Your primary problem is software not written for multi-core.

Look at Jeff Atwood's excellent article on Choosing Dual core or Quad Core.

for most software, you hit a point of diminishing returns very rapidly after two cores. In Quad-Core Desktops and Diminishing Returns, I questioned how effectively today's software can really use even four CPU cores, much less the inevitable eight and sixteen CPU cores we'll see a few years from now.

You are answered here (highlight copied from Jeff's article),

However, there were some surprises in here, such as Excel 2007, and the Lost Planet "concurrent operations" setting. It's possible software engineering will eventually advance to the point that clock speed matters less than parallelism. Or eventually it might be irrelevant, if we don't get to make the choice between faster clock speeds and more CPU cores. But in the meantime, clock speed wins most of the time. More CPU cores isn't automatically better. Typical users will be better off with the fastest possible dual-core CPU they can afford.

The issue of the Front-Side Bus (that term always amused me).
With Nehalem things change... as ArsTechnica said last year.

Moore's Law has given processor designers an embarrassment of transistor riches, and nowhere is that more apparent than in Intel's 45nm Nehalem processor. Debuting in 4- and 8-core variants later this year, Nehalem packs a ton of hardware into a single processor socket. (Early numbers put the transistor count of a quad-core Nehalem at 781 million; no numbers for the 8-core model have appeared yet.) But trying to feed all of that hardware with the Intel platform's existing frontside bus architecture would be folly. So, just as importantly, Nehalem also sounds the long-overdue death knell for Intel's positively geriatric frontside bus architecture.

The radical change in Intel's system bandwidth situation that Intel's new QuickPath Interconnect (QPI) represents is perhaps the largest single factor that shaped Nehalem's design. Between QuickPath and Nehalem's integrated memory controller, a Nehalem processor will have access to an unprecedented amount of aggregate bandwidth, especially in two- and four-socket implementations.

AMD moved the memory controller into the processor earlier and used Hypertransport.

Home

The maximum cores a CPU will contains?