How Many Processor Cores Are Enough?
|
From: Felger Carbon on 28 Sep 2006 13:59 "Jon Forrest" <forrest(a)ce.berkeley.edu> wrote in message news:efep6h$vbl$1(a)agate.berkeley.edu... > Today I read that we're going to get quad-core processors > in 2007, and 80-core processors in 5 years. This has > got me to wondering where the point of diminishing returns > is for processor cores. A very few power users - say, 3 to 5 in the world - will be able to use lots and lots of cores. The vast majority of the public will not run more than one task at a time, which at this time means only one core. In the distant future, applications that are in common use long enough to be called "legacy programs" may have been written to use several cores, so at that time even the general public will need several cores. But this is a long, long way off. In between, some workstations and their users can probably use a few cores, as soon as the software is rewritten for multicores.
From: Rick Jones on 28 Sep 2006 14:18 Joe Seigh <jseigh_01(a)xemaps.com> wrote: > Why would B be doing something else if you have an infinite number > of threads on hand to do that something else? This is just a "what > if" exercise. > Ok, let me pose this question then. What are the limits to how many > cores one can imagine using? Are there fundimental laws of logic > here, or are we the next generation of punch card mentality? Would the existing Internet be an approximation? It has what ammounts to a virtually unlimited number of "cores" (systems). rick jones -- web2.0 n, the dot.com reunion tour... these opinions are mine, all mine; HP might not want them anyway... :) feel free to post, OR email to rick.jones2 in hp.com but NOT BOTH...
From: Nick Maclaren on 28 Sep 2006 14:23 In article <2KGdnWmuYvz-m4HYnZ2dnUVZ_tmdnZ2d(a)comcast.com>, Joe Seigh <jseigh_01(a)xemaps.com> writes: |> > |> > Not really. Let's assume that you do have such an infinite number of |> > threads, and thread A wants to prod thread B at a time it is doing something |> > else. That can't be done without some form of asynchronicity. |> |> Why would B be doing something else if you have an infinite number of threads |> on hand to do that something else? This is just a "what if" exercise. Because, if you split the assignments to processors right down to atomic (communication-free) units, you end up with a huge amount of communication between processors. TANSTAAFL again. |> Ok, let me pose this question then. What are the limits to how many cores |> one can imagine using? Are there fundimental laws of logic here, or are we the |> next generation of punch card mentality? There are fundamental laws, but no particular limits. I can imagine using millions of cores, possibly even thousands of millions for big tasks, but the problem is communicating between them. Regards, Nick Maclaren.
From: Eugene Miya on 28 Sep 2006 14:52 In article <efgr7e$6oa$1(a)gemini.csx.cam.ac.uk>, Nick Maclaren <nmm1(a)cus.cam.ac.uk> wrote: >|> PIMs. > >When are we going to see them, then? We? "What do you mean 'we?' white man?" --Tonto I've seen them. I'm under an NDA. >Seriously, they have been talked about as imminent for 20 years, so >either there is a major problem or the IT industry is suffering a >collective failure of nerve. Or both. You have to locate the knowledgeable in your country. --
From: Joe Seigh on 28 Sep 2006 14:55
Rick Jones wrote: > Joe Seigh <jseigh_01(a)xemaps.com> wrote: > >>Ok, let me pose this question then. What are the limits to how many >>cores one can imagine using? Are there fundimental laws of logic >>here, or are we the next generation of punch card mentality? > > > Would the existing Internet be an approximation? It has what ammounts > to a virtually unlimited number of "cores" (systems). > Google probably. Except they and the internet don't have anything like shared memory for communication. -- Joe Seigh When you get lemons, you make lemonade. When you get hardware, you make software. |