Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Introducing "No-Moore's Law"

Author: Robert Hyatt

Date: 17:17:14 03/01/03

Go up one level in this thread


On March 01, 2003 at 11:48:50, Jeremiah Penery wrote:

>On March 01, 2003 at 10:11:13, Robert Hyatt wrote:
>
>>On March 01, 2003 at 01:53:11, Jeremiah Penery wrote:
>>
>>>Please go read this:
>>>
>>>http://www.realworldtech.com/forums/index.cfm?action=detail&PostNum=1022&Thread=34&roomID=11&entryID=11503
>>>
>>>I'm not going to try arguing the economic points anymore.  The post above may
>>>help you understand what I may have failed to explain well.
>>
>>That is not exactly a place I would cite in a technical paper, any more than
>>I would cite a post here. :)
>
>Lucky for me, I'm not writing a technical paper.  Neither are you.  I'd give
>that source as much credit as "a couple of engineer friends I have" and some
>random engineer that happens to read _this_ message board.

Your choice.  I _know_ the engineers I talk to from time to time.  I know their
background, education, and reputation.

>
>>>On March 01, 2003 at 00:07:01, Robert Hyatt wrote:
>>>
>>>>On February 28, 2003 at 20:41:59, Jeremiah Penery wrote:
>>>>
>>>>Sparc isn't selling "so well".  IN fact, if you talk to Sun insiders, it is
>>>>doomed and they are moving to the PC world quickly.  They already use a PC
>>>>type chassis with IDE disks and the like.  Care to guess why?  Processor sucks.
>>>>Everybody knows it sucks.  Only the "sun loyalty" keeps a few coming back.  We
>>>>used to be 100% sun, for example.  We now have 5 out of 250 computers here.
>>>>The rest are mostly PCs with a few others (SGI, etc) thrown in for good measure.
>>>
>>>http://biz.yahoo.com/ibd/030127/tech1_1.html and
>>>http://www.realworldtech.com/forums/index.cfm?action=detail&PostNum=1181&Thread=1&roomID=11&entryID=14061
>>>
>>>---
>>>"In 2002, Sun was No. 1 in sales of non-Intel servers.
>>>It had 37% of all non-Intel server revenue, according
>>>to researcher International Data Corp.
>>
>>So?  37% of 5% is what?  PCs dominate the computer market, reaching near
>>95% of all computers.  So Sun is fighting to compete for some fraction of
>>5%?  And they are going down the hole.  Sparc is doomed, and sun has already
>>said this.  They will be X86-based within two years...  although it might be
>>Intel or AMD of course...
>
>5% in terms of sales volume - much more in terms of revenue.  Most machines sold
>in that segment are multi-million dollar ones, so it doesn't matter that they're
>low volume.  Just like Cray, for instance.


Sun doesn't sell more than a single million-dollar computer a year.  They
are hopeless in that market, because that is SGI Challenge territory and the
SGI eats the sparc in any benchmark ever created...  As will the big
itanium boxes.  Hell, even a multi-xeon will eat any sparc on a cpu for cpu
basis without even using SMT.  :)




>
>>>Hewlett-Packard was No. 2, with 31% of those sales.
>>>IBM Corp. came in No. 3 with 21%. And Fujitsu was No.
>>>4, with just 2.6%"
>>>
>>>So by revenue, RISC server market share breakdown is
>>>approximately:
>>>
>>>40% SPARC
>>>31% PA-RISC + Alpha
>>>21% Power/PowerPC
>>>
>>>The 31% HP share is likely about two thirds PA-RISC
>>>and one third Alpha. SGI probably takes a good chunk
>>>of the 8% unaccounted for.
>>
>>
>>But that entire segment is 5% or less of the total sales.  Probably less as
>>mainframes are in that 5% category as well...
>
>If you sell 5 systems for $5m each, or 500 systems for $1000 each, which is
>making more money, despite being only 1% of the total volume?

The problem is, it is 5 for $5m, or 5M for $1000.  The math is _simple_
then.



>
>>>>The alpha was too expensive for the desktop.  256 bit bus was a killer.  But
>>>
>>>http://news.com.com/2100-1001-278032.html?tag=rn
>>>
>>>They planned to release it for the desktop.  It wasn't all that expensive,
>>>either.  With FX!32, they could even run native Intel binaries, so software
>>>compatibility shouldn't have been a barrier.
>>
>>There were some cheapo versions released.  Polywell was one example.  But it
>>was a dog because it used the PC 64 bit bus so it could use the PC memory and
>>PCI cards.  And it was a flop.
>
>I said they planned to release it for the desktop - the DEC machines, not the
>Polywell ones - not that they ever actually did so.  I visited New Mexico Tech
>in 1997 or so, and they had 533MHz Alpha desktop machines there.  It seemed to
>me that they were trying to make that kind of machine standard equipment for
>students and such.

I have one in my lab (an alphastation from dec.)  But it was never near the
PC price point, which left it for the "number crunchers" where it was the best
around.



>
>>>So why did _YOU_ bring up the heat/power argument?
>>
>>I didn't.  I responded to it.
>
>No.  You said, and I quote _again_, "But reducing the die size has other
>advantages, including lower voltage and lower heat, at the same clock frequency,
>so there is a reason for going there.."  That was before I _ever_ mentioned
>anything about thermal characteristics.
>
>>>>I'm only "harping" on how engineering works.  It is _not_ as haphazard as you
>>>>and others would suggest.  The engineers know very well what a particular fab
>>>
>>>Please give me one example of someone saying anything remotely implying
>>>something like, "engineering is haphazard."
>>
>>Just read thru this thread.  The discussion about "max speed".  I claim they
>>know before the first chip rolls off the fab.  Others claim that they don't know
>>until they test.
>
>Please show me where anyone claimed anything of the sort.
>
>I'll save you some time - it never happened.
>
>>>>IE Cray _never_ played these games, _ever_.
>>>
>>>If we were talking about the high-performance, server-oriented RISC market, or
>>>supercomputer market, your comments about marketing may well be correct.  We're
>>>talking about the commodity x86 market, however, which is completely different.
>>
>>I believe it is different _only_ in the volume of sales..
>
>That's a gigantic difference, don't you think?  Do you really believe it costs
>5x as much to manufacture an Itanium chip as it does a P4?  Itanium chip is
>lower volume, and therefore higher priced.  It's very simple economy of scale.

I don't disagree at all...


>
>>>>Once again, I do not _care_ about the intentionally slowed down processors
>>>>and whether they will overclock or not.  I care about the front-line fastest
>>>>chips being produced _only_.  All my comments are addressed to that specific
>>>>segment of the chip market.  Not the low-head (mobile) processors.  Not the
>>>
>>>You were the one who brought up the laptop processors.  I only tried to respond
>>>to the point.
>>
>>Once again I did _not_ bring up the laptop processors.  I responded to
>
>Wrong again.  You said, "IE a laptop processor can't run as hot as a desktop
>processor, because there can't be a 6" tall heat sink to help keep it from
>frying."  That was before I ever mentioned one word about laptops.


That was in response to the heat discussion, and an explanation of why it might
be reasonable to clock a chip well below its max, but only because there is
_another_ constraint that must be met, namely power consumption or heat
dissipation.  When those two don't count, then full-speed ahead...

Which was _the_ point to start with.  Overclocking the chips on the _front_ of
the power curve, not those on the back side.



This page took 0.02 seconds to execute

Last modified: Thu, 07 Jul 11 08:48:38 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.