Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Some Crafty 16.19 results on my XP 2.44GHz

Author: Matt Taylor

Date: 22:14:13 02/18/03

Go up one level in this thread


On February 19, 2003 at 01:11:17, Aaron Gordon wrote:

>On February 19, 2003 at 01:06:24, Matt Taylor wrote:
>
>>On February 19, 2003 at 00:52:09, enrico carrisco wrote:
>>
>>>On February 19, 2003 at 00:19:41, Robert Hyatt wrote:
>>>
>>>>On February 19, 2003 at 00:11:08, Aaron Gordon wrote:
>>>>
>>>>>I just downloaded Crafty 16.19 and ran a bench for you guys. No single cpu Intel
>>>>>box could ever touch this without sub-zero cooling. Just plain not going to
>>>>>happen.
>>>>>
>>>>>Crafty v16.19
>>>>>
>>>>>White(1): bench
>>>>>Running benchmark. . .
>>>>>......
>>>>>Total nodes: 67136136
>>>>>Raw nodes per second: 1766740
>>>>>Total elapsed time: 38
>>>>>SMP time-to-ply measurement: 16.842105
>>>>
>>>>
>>>>This is not a great test since that is a very old version.  I'm not sure how
>>>>1.7M compares to version 19.3 in nps...
>>>>
>>>>However, while on the question, what is an XP 2.44ghz machine, since I am not
>>>>an AMD expert.  Overclocked?  If so, I consider that a worthless number, because
>>>>of obvious reasons...
>>>
>>>
>>>If done properly and tested for reliability -- what reasons do you speak of?
>>>Most CPUs are purposely locked from higher than marked performance from the
>>>manufacturer for marketing and other reasons -- both Intel and AMD.  This, in no
>>>way, means the CPU is incapable of such performance.
>>
>>Propigation delays do. Intel and AMD release chips at a given speed for a
>>reason. Yes, much of it is about money. It is very profittable to allow
>>consumers to upgrade through every iteration of a chip. Not always. Intel
>>delayed the 1.13 GHz Pentium 3 for a while. I've heard that they could not mass
>>produce them reliably at the time.
>>
>>>In the case of AMD, chips with the same stepping are identical no matter what
>>>they're marked. So if a 1500+ AthlonXP has an AIUHB 0301 core and an AthlonXP
>>>2800+ has an AIUHB 0301 then they'll be able to run identical speeds.
>>>(Obviously there are slight variations in peak performance, if you're going for
>>>higher than XP3000+ level.)
>>>
>>>Are you suggesting that "unlocking" performance that is already included in the
>>>core simply because the marking on the top of the cpu says otherwise makes such
>>>results worthless?
>>
>>No, he is suggesting that comparing unguaranteed performance is worthless and
>>silly. You might stick a peltier on your chip, tweak the voltage, and manage to
>>run 2.8 GHz or something similarly fast. That doesn't mean I can. That doesn't
>>mean anyone else can.
>>
>>>Wouldn't that be the same as saying stronger results I may find with Crafty if I
>>>modified the settings are completely worthless if you did not include the
>>>settings in your official release?
>>
>>Modifying Crafty compile settings doesn't cause it to crash all of a sudden.
>>Furthermore, anyone can apply those same settings and get the same results.
>>
>>-Matt
>
>Thats what he was saying about the chip. Anyone can slap an air-cooler on an
>AIUHB chip and get at least 2.3ghz (up to 2.6ghz). If you can compile crafty,
>you can surely push a few keys to raise your bus and voltage. Even my fiance
>overclocks her computer (and did it by herself). I'm not magical, you can get
>the same hardware and run the same settings I do. :)

AMD doesn't guarantee 2.3 GHz out of any of their chips. As I recall, you had a
particularly bad one recently...

Anyway, if AMD doesn't define the limit of stability, who does? Some P4s
overclock to 4 GHz now, don't they?

-Matt



This page took 0.01 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.