Fred Kleinsorge wrote:

> Bill Todd wrote in message ...
>
>>"Rob Young" <[log in to unmask]> wrote in message
>>news:lGELmlXAGUYz@eisner.encompasserve.org...
>>
>>>In article <[log in to unmask]>, "Bill
>>>
>>Todd" <[log in to unmask]> writes:
>>
>>...
>>
>>
>>>>Sorry - UltraSPARC III.  You know, the processor line Rob always
>>>>
>>denigrates
>>
>>>>for being such a pig that Itanic will quickly usurp Sun's entire
>>>>
>>customer
>>
>>>>base as its start on conquering the world.  That's why it would be so
>>>>
>>funny
>>
>>>>if McKinley turned out to be slower after all.
>>>>
>>>>
>>>Is that an "official" prognostication, or a wish?
>>>
>>I made a quantitive prediction (based on publicly-available information
>>which I described) some time ago that McKinley would weigh in at 600 - 700
>>SPECint2K (and most likely in the middle of that range), and I stand by it
>>(unless it gets delayed so long that Intel can skip the first release
>>entirely and go directly to what would have been the first major
>>post-release process tweak - which is looking increasingly possible).  The
>>best USIII SPECint2K currently is 610, but since such values do tend to
>>
> rise
>
>>as new configurations appear I'd say there's a distinct possibility, though
>>perhaps not a better-than-even chance, that if McKinley doesn't in fact
>>
> wait
>
>>for a process-tweak before releasing it will at introduction have a hard
>>time equalling USIII's SPECint2K speed.
>>
>>
>
> So there you go.  Assuming your predictions are right, McKinley will beat
> USIII (and even your outside estimate of USIII getting faster doesn't take
> into account the tricked up compiler that caused the temportary "upgrade" of
> USIII speed).
>


There you go again posting about something you don't understand.

1. The optimisation used by Sun only effected SPECfp note that Bill
is talking about SPECint. Even you should be aware of the differences.

2, It wasn't a trick and if you think it was perhaps you could back up
your claim with evidence other than suppostion on your part.



> So IA64 systems will at minimum be performance competetive with USIII, and
> from what I understand will be priced much lower.
>


This would have been an interesting point had your previous ones been
correct since they were not it isn't :):)

Regards
Andrew Harrison

* To join/leave the list, search archives, change list settings, *
* etc., please visit http://raven.utc.edu/archives/hp3000-l.html *