Re: Clock rate on SGI's

New Message Reply Date view Thread view Subject view Author view

panisset++at++discreet.qc.ca
Wed, 3 Jul 1996 13:03:48 -0400

> The clock period determined by pfInitClock() on 250MHz IMPACT
> systems is apparently inconsistent with the true clock period. It
> seems that the actual clock period is that of a 200MHz system.
> Consequently, pfGetTime() will return a time that is .8 (200/250)
> that of the true time.

Turns out that this is a bug in IRIX 5.3 All Impact when running on certain
models of the 250MHz R4400 CPU module. More specificaly, if your CPU module
revision is:

030-0808-001 RevE

the cycle counter time will be reported as 32000 ps, whereas it should be 40000
ps. This has been fixed under IRIX 6.2, which reports 40000. If your CPU module
revision is:

030-0937-001 RevA

both 5.3 All Impact and 6.2 will report a cycle interval of 48000 ps, which
appears to be correct.

Found this out the hard way...

JF

-- 


Jean-Francois Panisset                                panisset++at++discreet.qc.ca
Software Engineer
Discreet Logic 


=======================================================================
List Archives, FAQ, FTP:  http://www.sgi.com/Technology/Performer/   <--new!
            Submissions:  info-performer++at++sgi.com
        Admin. requests:  info-performer-request++at++sgi.com

New Message Reply Date view Thread view Subject view Author view

This archive was generated by hypermail 2.0b2 on Mon Aug 10 1998 - 17:53:08 PDT

This message has been cleansed for anti-spam protection. Replace '++at++' in any mail addresses with the '@' symbol.