Author: Paul
Date: 05:09:17 01/22/01
Go up one level in this thread
On January 21, 2001 at 21:02:38, Larry Griffiths wrote: >On January 21, 2001 at 17:20:11, Paul wrote: > >>Hmmm ... I didn't know BCB had alignment problems. I use int64's for hashing. >>Haven't noticed a big speed penalty for that, is it only a problem in >>combination with MMX or is it more general if I understand you right? > >MMX instructions take performance hits when the data is not aligned on a >quadword boundry. Using int64's without MMX should be ok. >>But in return you've got a lot more registers too play with right? But if >>you can't test on conditions their use must be very limited? Just And/Or etc? > >Correct Paul. Their are 8 MMX registers. They are the floating point registers >in another mode. An EMMS instruction must be done before doing any floating >point and can take up to 50 clock cycles to execute. > >>I looked at the way TSCP communicates with WinBoard, and that's through the >>use of printf/fgets on stdout/in, but am not sure if that works from a >>GUI exe; will just have to try I guess, or do you know? > >I am using the VCL and communicating with Winboard at the same time. Ok, will have to try it later this week then, thanks ... Paul
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.