Author: Vincent Diepeveen
Date: 08:09:53 08/30/03
Go up one level in this thread
On August 29, 2003 at 23:35:53, Eugene Nalimov wrote:
>On August 29, 2003 at 22:58:10, Jay Urbanski wrote:
>
>>On August 29, 2003 at 16:05:32, Eugene Nalimov wrote:
>>
>>>Ok, so if we are talking about what is available *right now*, not about some
>>>future products:
>>>
>>>* Itanium2 has absoulute best FP performance, as well as absolut best SpecFP
>>>rate.
>>>* Xeon has very competive price / FP performance for the uniprocessor system. I
>>>am not sure if Xeon or Opteron is better this week, because all depends on exact
>>>prices and discounts.
>>>* Opteron and Itanium2 probably have comparable price / FP performance for the
>>>multi-CPU systems (SPEC FP rate for the single-CPU Itanium2 is the same as for
>>>the dual-CPU Opteron, so single-CPU Itanium2 system can be 2x more expensive
>>>than dual Opteron system).
>>
>>Yeah it could, except that it's 4X more expensive. The list price for our 2 X
>>2.0Ghz Opteron system is around $6000. For the two-way 1.5Ghz Madison system
>>that gets 30 SPEC FP rate it's $26,000.
>
>Here is dual Itanium2/1.5GHz/6Mb L3 for ~$15k:
that one is not delivered with the HP compiler is it?
it says: compaq.
that's intel and the intel compiler sucks at the itanium2, we already know that.
i can daily compile with it:
DESCRIPTION
Intel(R) C++ Compiler Options. This compiler is designed
to preprocess, compile, assemble, and link C and C++ pro
grams on Itanium(R)-based systems.
>http://www.smb.compaq.com/MiddleFrame.asp?page=config&ProductLineId=433&FamilyId=1431&BaseId=9443&oi=E9CED&BEID=19701&SBLID=&AirTime=False
>
>And I believe exactly such system (zx6000 with dual Itanium2/1.5GHz/6Mb L3) has
>Spec FP rate of 42:
>http://www.spec.org/cpu2000/results/res2003q3/cpu2000-20030630-02327.html
WRONG LINK. you are referring to the HP dual itanium2. NOT to the compaq
itanium2.
So you're selling us a trabant for $15000 referring to the speed of a mercedes
for it. If we buy that trabant for $15000 we won't run even *close* to the speed
of a dual opteron.
>Thanks,
>Eugene
>
>>>For integer performance story is different, but that thread was about FP
>>>performance, right? :-)
>>>
>>>Thanks,
>>>Eugene
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.