Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Pentium IV mobile processors have very good results ...

Author: Anthony Cozzie

Date: 09:27:14 01/23/04

Go up one level in this thread


On January 23, 2004 at 12:02:42, Thomas Mayer wrote:

>Hi Frank,
>
>>>> I am wonder about the power from the new Pentium IV Mobile processors. If I
>>>> compare the power is the Mobile faster.
>>>>
>>>> Athlon optimated bench results from Axon Bench Test:
>>>>
>>>> Maxdata (4200x) Pentium IV Mobile 2.67 with HT Notebook = 7.015
>>>> Maxdata (3100x) Pentium IV 2.67 without HT Notebook = ~ 6.300
>>>> Xeon 2.8 GHz with HT = 7.670
>>>>
>>>> Hyper-Threading is not important for this test!
>>>>
>>>> Athlon proecessors are a little bit faster but after my information is
>>>> this test optimize for Athlon processors.
>
>>> Not sure how to take the results.. but.. my Athlon XP 2.5GHz gets 8.721
>
>> yes this must be right!
>> The test is better for Athlon programs because Axon is Athlon optimated.
>> Try this test with an Intel processor!
>
>you write that nonsense all the time -> maybe you READ your forum ? The
>programmer of Axon told it SEVERAL times, that it is NOT optimized for Athlon at
>all, the Athlons are simply better for chess. E.g. my XP2700+ with internal
>2.166 GHz performs like a 3.4 GHz PIV - which we can not buy right now...
>clockwise Athlons are WAY better...
>
>But don't forget the best: Opterons are BEASTs for computerchess, they beat
>everything else in performance even when you use only the 32 bit mode...
>Yesterday the Zappa programmer reports me, that his Operon 1.8 GHz is of about
>double the speed for his program then an Athlon XP2700+/2.166 GHz in 64bit mode.
>Unbelieveable - even with lower clockspeed it is 2 times as fast... AMD rules...
>:)
>
>Greets, Thomas

approximate numbers for Zappa:

AMD Athlon XP 1.5G:  400 knps
Intel P4 2.4G:       470 knps
AMD Opteron 1.8G-32: 580 knps
AMD Opteron 1.8G-64: 920 knps

Zappa basically ends up being about 1/2 as fast as crafty in all situations.  I
don't do lazy eval, I keep extra rotated bitboards, I do a (somewhat) slower
kingsafety, and in general am less optimized.

anthony



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.