Re: Mcsec in Timestamp, is it possible?

["Leif Svalgaard" <leif@xxxxxxxx>]

thanks, Bruce, but why even have the 8-microsecond
limit? The timebase clock in the Power-PC runs much faster
than that. Playing with the MFTB instruction seems to indicate
a granularity (on a 150) of about 1 tick per machine cycle.

----- Original Message -----
From: <bvining@vnet.ibm.com>
To: <MIDRANGE-L@midrange.com>
Sent: Wednesday, February 14, 2001 9:16 AM
Subject: Mcsec in Timestamp, is it possible?


> In V4R3 the MI architecture was updated to reflect a 8-microsecond
> granularity for time resolution.  From an implementation point of view
> one might find it is 8-microsecond on earlier RISC releases also.
> CISC is 1024-microseconds.
>
> Bruce
>
> >
> >According to the MI-manual, the timestamp counter increments once
> >every 1024 microseconds, so it may be hard to get the microseconds.
> >
>
>
> +---
> | This is the Midrange System Mailing List!
> | To submit a new message, send your mail to MIDRANGE-L@midrange.com.
> | To subscribe to this list send email to MIDRANGE-L-SUB@midrange.com.
> | To unsubscribe from this list send email to
MIDRANGE-L-UNSUB@midrange.com.
> | Questions should be directed to the list owner/operator:
david@midrange.com
> +---

+---
| This is the Midrange System Mailing List!
| To submit a new message, send your mail to MIDRANGE-L@midrange.com.
| To subscribe to this list send email to MIDRANGE-L-SUB@midrange.com.
| To unsubscribe from this list send email to MIDRANGE-L-UNSUB@midrange.com.
| Questions should be directed to the list owner/operator: david@midrange.com
+---