Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Good luck

Author: Charles Worthington

Date: 21:02:41 02/18/03

Go up one level in this thread


On February 18, 2003 at 23:52:33, Aaron Gordon wrote:

>On February 18, 2003 at 23:44:18, Charles Worthington wrote:
>
>>On February 18, 2003 at 23:39:18, Aaron Gordon wrote:
>>
>>>Hyatts box benchmarks a little over 2 million nodes/sec in the crafty benchmark.
>>>Hyatt, I know you say you get 2.5 million but in all the games you've played
>>>online where you've kibbed your nodes/sec you've ALWAYS been just over 2 million
>>>(2050-2150kn/s most of the time). Also, about a dual P4-3.06 + HT getting 3
>>>million nodes/sec. Not going to happen (Possible in the endgame with almost no
>>>pieces). My AthlonXP 2100+ overclocked to 2.44GHz gets a little over 1.5 million
>>>nodes/sec in crafty and I've seen over 2 million in end-games. Enricos 2400+ @
>>>2.52GHz gets almost 1.6 million in crafty.
>>>
>>>There are *NO* P4 chips available that can match this, including a P4-3.06 Xeon
>>>+ HT. Those get around 1.3 million WITH HT in crafty. If you do a 1.3 million *
>>>1.8 you come out to 2.34 million nodes/sec. Far cry from 3 million nodes/sec.
>>>
>>>How much did MY box cost? $97 for the chip, $80 for the board. $75 for the ram,
>>>etc. Not much at all.
>>
>>
>>Once again you are trying to compare overclocked Athlons to factory xeons and
>>still not accounting for the hyperthreading multiple of 1.33. Lets overclock the
>>Xeon too if you want a fair test. And also people can we please stop  pretending
>>that the hyperthreading multiple does not exist?
>
>I am talking about hyperthreading. P4-3.06GHz only gets a little over 1.1
>million nodes/sec without hyperthreading. around 1.3 million WITH
>hyperthreading. Hyatt states 33%, this isn't for a single cpu. This is roughtly
>16% *PER CPU*. Which means you'll see around a 16% increase in performance in
>crafty with hyperthreading on one chip. Hyatt has a dual. 16 * 2 is what? 32..
>pretty close to "33%" :)
>
>As I said before, the dual P4-3.06GHz Xeon *WITH HYPERTHREADING* will not get
>much more than 2.3 million nodes/second. I'll go over the math again with you.
>
>P4-3.06GHz gets a little over 1.1 million nodes/sec on average without
>hyperthreading. 1.1mn/s * 1.16(16% boost from HT) comes out to the benchmark
>results I saw, around 1.3 million. Now, 1.3 million multiplied by 1.8 is what?
>2.34 million. This includes 16% x 2 boost for HT.
>
>Also, I highly doubt Xeon boards can be overclocked. They're not made to do such
>a thing. AMD systems however, can. Get an iWill MPX2 motherboard and two MP
>2400+ or 2600+'s and overclock to 2.3-2.5GHz per cpu. No Dual Intel box would be
>able to touch such a system. Even non-overclocked I bet it'd still be faster..
>and with the price you'd have to pay to even come close with an Intel box you
>could buy multiple AMD systems.


My apologies I was not aware that you had included hyperthreading figures. But
in regards to overclocking yes there are Xeon boards (non intel) that can be
overclocked.



This page took 0.06 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.