Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Intel Hyperthreading and Ponder (Permanent Brain)

Author: Robert Hyatt

Date: 14:42:29 01/02/04

Go up one level in this thread


On January 02, 2004 at 15:56:36, Juergen Wolf wrote:

>On January 02, 2004 at 13:30:09, Robert Hyatt wrote:
>
>>On January 02, 2004 at 09:57:38, Jasmine Baer wrote:
>>
>>>I've seen it written that under the following conditions:
>>>
>>>1.  Engine vs. Engine match or tournament
>>>2.  Held on a single computer with a single processor
>>>
>>>having ponder=ON(or Permanent Brain in the Fritz GUI) will impact the play of
>>>the engines since the each individual engine would not have full access to the
>>>processor during its own turn.
>>>
>>>First, is this true?
>>
>>yes.  Since both engines are running, each should get about 1/2 the
>>computational cycles.
>
>usually yes, if the priority-level is controlled by the GUI and not
>overwritten by the engine. i just want to mention this as i have seen
>one (weaker) engine resetting the priority-level.
>

Not a problem in Unix.  You can set your priority down, but never up.  So
you can give the advantage to your opponent, but you can't "take it".

>
>>
>>>
>>>Second, is this issue, if it actually is an issue, something that is eliminated
>>>by running a two-processor system?
>>
>>Partially.  What about engines that can use _both_ processors?  :)
>>
>>
>>
>>>
>>>And, finally, does anyone have any solid insight on how ponder=off/on or
>>>Permanent Brain works on a Pentium 4 with Hyperthreading?
>>>
>>>Thanks.
>>
>>
>>Same way.  PIV with SMT on looks like two slower processors...



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.