Re: Clock rate on SGI's

New Message Reply Date view Thread view Subject view Author view

John W. Barrus (barrus++at++merl.com)
Wed, 3 Jul 96 12:03:48 EDT

I found the following Q&A in the Performer FAQ.

Is this the same clock as that used in the syssgi(SGI_QUERY_CYCLECNTR) call?
If so, this must be the same problem.

Is the cycle rate returned by that call built into hardware, or is compiled
in somewhere as a constant? If it is compiled in, it seems like a patch
would solve the problem.

Any thoughts or suggestions?

John B.

==========

Subject: + -56- 2.0 Bug pfInitClock() and Video Rate on 250MHz IMPACT
Date: 12 Dec 95 00:00:01 EST

  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.

  Among other things, this invalidates the calculations done by
  Performer to determine the current video rate.

  As a workaround, you can specify an alternate clock period with the
  PFCLOCKPERIOD environment variable. If set, PFCLOCKPERIOD
  specifies the clock period, in picoseconds, to be used by
  pfInitClock(). For proper behavior on 250MHz IMPACT systems, use
  40000 for the period.

=======================================================================
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.