How Many Processor Cores Are Enough?
|
From: Nick Maclaren on 18 Oct 2006 06:56 In article <wPmZg.21729$L.8512(a)newsfe4-gui.ntli.net>, "Peter Dickerson" <first{dot}surname(a)tesco.net> writes: |> |> Dennis, calm down please. It doesn't help the image of comp.arch . Yes, Nick |> can be bloody infuriating. He really ought to be citing references for the |> points he makes (=existance proof) - he works (or goes round) in academic |> circles, so he should know the form. For heaven's sake - I GAVE you the damn references! I don't keep all of the details of the areas I know about in my head or even in a convenent form - that is possible only for narrow generalists. If I were writing an academic paper, I would put the effort in to looking them up and listing them properly, but why should I do that for people who are too damn idle to do it for themselves? In any case, this is all standard knowledge for people with experience in the area, and academic tradition is NOT to provide references for such basic information. It isn't a GOOD tradition, because it helps to propagate myths, but it is a common one. As I said, look at those architecture documents: x86, IA64, MIPS, PA-RISC, zArch (probably, but certainly System/370), POWER (if I recall correctly). And the SC22WG1 Web site for the dicussions on parallelism. Anyone capable of understanding the issues is capable of finding those on the net. Regards, Nick Maclaren.
From: Dennis M. O'Connor on 18 Oct 2006 09:43 "Peter Dickerson" <first{dot}surname(a)tesco.net> wrote ... > "Dennis M. O'Connor" <dmoc(a)primenet.com> wrote in >> <rohit.nadig(a)gmail.com> wrote >> [ ... blah blah blah ...] >> > Architect, micro-architect, I could care less. >> >> Then shut the f*ck up. There's enough noise on USENET >> already without ever pissant Gmail user puking up onto >> a thread just to tell everyone they don't care about it. > > Dennis, calm down please. It doesn't help the image of comp.arch . > Yes, Nick can be bloody infuriating. [...] Peter, my post above is NOT a response to Nick's posts, or aimed at Nick. It's to "rohit.nadig", whoever that is. -- Dennis M. O'Connor dmoc(a)primenet.com
From: girish on 18 Oct 2006 10:36 > As I said, look up RC delay. Until and unless someone can get > opto-electronics working for internal chip 'wiring', that will be correct me if i am wrong. but is this referring to -- wire-less chip interconnect or optical chip interconnect? if it is about wireless, then i believe several people are on that path. maximum possible symbols per maximum possible Hz over maximum possible distance.
From: Nick Maclaren on 18 Oct 2006 10:38 In article <1161182202.791510.118410(a)m7g2000cwm.googlegroups.com>, "girish" <girishvg(a)gmail.com> writes: |> |> > As I said, look up RC delay. Until and unless someone can get |> > opto-electronics working for internal chip 'wiring', that will be |> |> correct me if i am wrong. but is this referring to -- wire-less chip |> interconnect or optical chip interconnect? No. As I said, look it up. It will explain many of the replies from other people. Regards, Nick Maclaren.
From: girish on 18 Oct 2006 10:47
On Oct 18, 11:38 pm, n...(a)cus.cam.ac.uk (Nick Maclaren) wrote: > In article <1161182202.791510.118...(a)m7g2000cwm.googlegroups.com>,"girish" <giris...(a)gmail.com> writes:|> > |> > As I said, look up RC delay. Until and unless someone can get > |> > opto-electronics working for internal chip 'wiring', that will be > |> > |> correct me if i am wrong. but is this referring to -- wire-less chip > |> interconnect or optical chip interconnect? > > No. As I said, look it up. It will explain many of the replies from > other people. thanks. let me understand this. (been some time i studied this). are we talking about - R -------------wwwwww-------------------------------- | C | ======= ======= | | ------------------------------------------------------------ lpf (?) hmm. i completely forgot... |