FW: [Simh] SimH vax.exe cpu usage on Windows.

[Carl Lowenstein]

> Date: Tue, 18 May 2004 23:24:01 +0200 (CEST)
> From: Andreas Davour <ante at update.uu.se>
> To: "Bishop, Lewis" <lewis.bishop at eds.com>
> Subject: Re: FW: [Simh] SimH vax.exe cpu usage on Windows.
> Cc: "'simh at trailing-edge.com'" <simh at trailing-edge.com>
> 
> On Wed, 19 May 2004, Bishop, Lewis wrote:
> 
> > Thanks for the responses so far...
> [snip]
> > I have set the priority down to low and to be honest it doesn't
> > seem to make any difference to the overall sysstem performance. I've
> > tried some of the PC slow utilities but these have not reduced the
> > CPU usage (didn't think they would). If it cannot be done within
> > SimH then maybe some form of resource manager would  be good?
>
> Well, the problem here is that when the simulated CPU does nothing the
> simulator is still running 100%. That means simh has to be patched to
> "idle" on the host system as soon as the simulated CPU is "idle". You
> can't solve the problem from Windows, as far as I know.

This is the classic hardware problem of optimizing the idle loop, where
the CPU spends most of its time.  If VAX/VMS always executes the same
pattern of instructions when the system is idle, then the SIMH simulator
could be tuned to recognize this, and run at a less intensive rate,
perhaps based on timer interrupts.

But that would make SIMH/VAX/VMS different from SIMH/VAX/BSD and so on.

    carl
-- 
    carl lowenstein         marine physical lab     u.c. san diego
                                                 clowenst at ucsd.edu