Intel acquiring Pallas

[Joel Jaeggli]

The cost of the os, either of a blessed one, or a roll your own one hasn't 
been a significant factor in our reluctance to use Itanium II.

The lack of commodity mainboards.

The steep price of the cpu's.

and lack of a clear view into intels product lifecycle for itaniumII.

have been issues.

Itanium II 1.3ghz 3mb cpu's have only recently arrived at ~$1400ea. 
opteron 244s are less than half that and that's before we put the rest of 
the system around it.

we have some off-the-shelf compaq itanium boxes to evaluate but at around 
$8000 ea that sort of a non-starter.

joelja

On Thu, 28 Aug 2003, Robert G. Brown wrote:

> On Thu, 28 Aug 2003, Stephen Gaudet wrote:
> 
> > With Itanium2 this is not the case.  Both Red Hat and SuSe have a fixed 
> > cost of about $400.00, plus or minus a few dollars per system.  
> > Therefore, due to this fixed cost, MOST people looking at a cluster 
> > won't touch Itanium2. 
> 
> Steve,
> 
> Are you suggesting RH has put together a package that is NOT GPL in any
> way that would significantly affect the 64 bit market?  The kernel, the
> compiler, and damn near every package is GPL, much of it from Gnu
> itself.  Am I crazy here?
> 
> So I'm having a hard time seeing why one would HAVE to pay them
> $400/system for anything except perhaps proprietary non-GPL "advanced
> server" packages that almost certainly wouldn't be important to HPC
> cluster builders (and which they would have had to damn near develop in
> a sealed room to avoid incorporating GPL stuff in it anywhere).
> 
> > Some white box resellers are looking at taking RH Advanced Server and 
> > stripping it down and offering on their ia64 clusters.  However, if 
> > their not working with code lawyers, and paying very close attention to 
> > copy right laws, they could end up with law suits down the road.
> 
> If Red Hat isn't careful and not working very carefully with code
> lawyers, I think the reverse is a lot more likely, as Richard Stallman
> is known to take the Gnu Public License (free as in air at the source
> level, with inheritance) pretty seriously.  Red Hat (or SuSE) doesn't
> "own" a hell of a lot of code in what they sell; the bulk of what they
> HAVE written is GPL derived and hence GPL by inheritance alone.  The
> Open Source community would stomp anything out of line with hobnailed
> boots and club it until it stopped twitching...
> 
> So although many a business may cheerfully pay $400/seat for advanced
> server because it is a cost and support model they are comfortable with,
> I don't see what there is to stop anyone from taking an advanced server
> copy (which necessarily either comes with src rpm's or makes them
> publically available somewhere), doing an rpmbuild on all the src rpm's
> (as if anyone would care that you went through an independent rebuild vs
> just used the distribution rpm's) and putting it on 1000 systems, or
> giving the sources to a friend, or even reselling a repackaging of the
> whole thing (as long as they don't call them Red Hat and as long as they
> omit any really proprietary non-GPL work).
> 
> I even thought there were some people on the list who were using at
> least some 64 bit stuff already, both for AMD's and Intels.  Maybe I'm
> wrong...:-(
> 
>   rgb
> 
> Robert G. Brown	                       http://www.phy.duke.edu/~rgb/
> Duke University Dept. of Physics, Box 90305
> Durham, N.C. 27708-0305
> Phone: 1-919-660-2567  Fax: 919-660-2525     email:rgb at phy.duke.edu
> 
> 
> 
> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org
> To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
> 

-- 
-------------------------------------------------------------------------- 
Joel Jaeggli  	       Unix Consulting 	       joelja at darkwing.uoregon.edu    
GPG Key Fingerprint:     5C6E 0104 BAF0 40B0 5BD3 C38B F000 35AB B67F 56B2


_______________________________________________
Beowulf mailing list, Beowulf at beowulf.org
To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf