Author: Robert Hyatt
Date: 18:10:00 12/01/01
Go up one level in this thread
On December 01, 2001 at 06:54:42, Slater Wold wrote: >On November 30, 2001 at 23:32:40, Robert Hyatt wrote: > >>On November 30, 2001 at 12:18:20, Slater Wold wrote: >> >>>On November 30, 2001 at 11:59:01, Robert Hyatt wrote: >>> >>>>On November 30, 2001 at 02:31:18, Slater Wold wrote: >>>> >>>>>On November 29, 2001 at 21:21:33, K. Burcham wrote: >>>>> >>>>>> >>>>>> >>>>>>Mr Hyatt. i have read the posts here about deep fritz and its kns increase with >>>>>>two processors. >>>>>> >>>>>>from the info i have seen with my dual machine, i have become curious about >>>>>>something. below are the examples with difference in hardware. >>>>>> >>>>>>program A on single processor 1500 mhz 1400 kns >>>>>>program A on dual processor 3000 mhz 2000 kns >>>>>> >>>>>>program B on single processor 1500 mhz 1400 kns >>>>>>program B on dual processor 3000 mhz 1400 to 1500 kns >>>>>> >>>>>> >>>>>>my question is only about the chess software. not the hardware. not the ram. >>>>>>not the hash. >>>>>> >>>>>>is it possible with these smp programs that something else going on in the chess >>>>>>software, that you can comment on. in other words if this kns is accurate and a >>>>>>true value (that deep fritz is giving us), then is it possible the program is >>>>>>doing something else with this second processor that will not show a kns >>>>>>increase but will add to its strength. the reason for this question is that when >>>>>>i run task manager in windows 2000, it shows that the program is using the >>>>>>second processor with deep fritz as much as my other smp programs (90 to 100%) >>>>>>but it shows no increase in kns. >>>>>> >>>>>>kburcham >>>>> >>>>>No. Because it's not solving the problem any quicker either. >>>> >>>> >>>>For the record, if you run crafty, you will _always_ see both cpus running >>>>at 100%. But it is possible that one thread is in a spin-lock waiting on >>>>the other to release something, or that one is spinning waiting on work. >>>> >>>>IE just because a cpu is busy doesn't mean it is busy doing something >>>>_useful_. :) >>> >>>Speaking of which, did you know Crafty reports the wrong CPU usage time in >>>Windows? It always says that I am using like 90% when task manager (along with >>>other utilities) say it's using 100%. >>> >> >>I have seen this, but since I don't run windows here, I have never been able >>to track it down. If you are interested, I can tell you how the timing stuff >>works and perhaps get it right... > >Sure. Send me an e-mail. I'd do whatever I can. > >> >> >> >> >>>I also checked the memory paging in Crafty between 3xxMB ram and 7xxMB RAM. I >>>am guessing Crafty does the global lock, because it did extremly well. Better >>>than any others tested. >> >> >>Not sure what you mean by "global lock"... > >Locking the memory. I've seen a lot of SMP programs swap over a MB a sec >because the memory is not being locked. Almost a must in Windows 2000. > >Anyone who's interested, can run an SMP program on a Windows 2000 machine, and >press ALT+TAB to go to another running program. See how much memory Windows >2000 swaps in order to do this. At times it can be > 3MB/sec. perfmon will >report this. I don't lock anything in my code, I simply malloc() a large chunk of memory for the hash tables and go with it...
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.