Re: Vulcano Test

The calibration is quite simple. It is substantially nothing but, as it has always been, the kerneel/user space latency example that comes with RTAI. The only difference with respect to the previous self version is that it avoids iterating in the hope of a better precision. 
As remarked by someone the previous version was not apt to cross development. Thus the decision of carrying it out at the first schedule installation, using a shorter calibration time, settable by the user.
The use of shorter times has been tested on different machines and  has been verified already also by Felix (Frey).
So a user has just to give the period of calibration, discussed on this list already, and the time to calibrate (to become the number of calibration cycles).
The results of the calibration are saved on a file, in the installation dir, and are available for subsequent uses, without recalibrating.
That's all, but I'm working on an improvement (hopefully), though it will not change the results very much.

About its explanation, if If you have a better editing of the Kconfig help I'll be glad to merge it with mine.

Paolo.

________________________________________
From: Rtai [[email protected]] on behalf of Alec Ari [[email protected]]
Sent: Friday, April 1, 2016 5:20 PM
To: RTAI Mailing List
Subject: Re: [Rtai] Vulcano Test

>I hope to have some feedback more from RTAI users.

>Paolo

(accidentally emailed directly)

Sure! I can test with an AMD APU! This new latency calibration setup is awfully confusing though, can I have some tips on the values and what they mean?

Alec Ari
_______________________________________________
Rtai mailing list
[email protected]
https://mail.rtai.org/cgi-bin/mailman/listinfo/rtai
_______________________________________________
Rtai mailing list
[email protected]
https://mail.rtai.org/cgi-bin/mailman/listinfo/rtai