RE: Re: MPC555 speed versus PentiumMMX

We run two models (approx. 4500 blocks in size all total), which are extremely computational intensive, on an MPC565
running at 56Mhz.  We have found the performance to be very good.  One thing you should keep in mind, your performance
may vary based on your development tool set (all compilers are not created equal).  We found some of the open source
tools do not make efficient use of the chip architecture, thus resulting in lower throughput.
-Ronnie  

-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of mworksjjf
Sent: Thursday, August 04, 2005 3:53 AM
To: [email protected]
Subject: [MPC500] Re: MPC555 speed versus PentiumMMX

Hi Seth,

--- In [email protected], "surgevw" <surgevw@y...> wrote:
> When I got the sales pitch from Mathworks of Natick, they didn't 
know.
> At that point they didn't understand what I was trying to do (nor 
did
> I, exactly). When I get the model done, I will get an eval version 
and
> try it. 

Ok, sounds good.

> I can tell you right now that the integral term in a PID
> controller eats clock cycles on the Pentium, and I am not sure why. 

Is your model running with discrete or continuous time?   Continuous 
time imposes significant overhead on the real-time system.

Thanks,

Jon.

> I
> am curious to see how a 56MHz MPC565 compares with the more
> conventional Simulink model and the SimMechanics inverse kinematics 
model.
> 
> Thanks,
> 
> Seth
> 
> 
> --- In [email protected], "mworksjjf" <jfielder@m...> wrote:
> > Hi Seth,
> > 
> > > I trying to get a handle on the relative
> > > performance of a MPC 555 or 565 
> > 
> > You should be able to clock the MPC565 faster than the MPC555 - 
up to 
> > 56 MHz.
> > 
> > > with respect to an early Pentium,
> > > specifically a 266 MMX unit with 66MHz FSB. 
> > 
> > We're not sure exactly how these will compare for your 
application.
> > 
> > Please contact your local MathWorks office and request an 
evaluation 
> > of the Embedded Target for Motorola MPC555.   It is a straight 
> > forward process to re-target your model from xPC to MPC555.
> > 
> > If required, your local MathWorks office will be able to get in 
touch 
> > with the development team to determine if any further 
optimisations 
> > can be applied.
> > 
> > Best regards,
> > 
> > Jon Fielder
> > Embedded Targets Development
> > The MathWorks Ltd.





-----------------------------------------------------------
To learn more about Freescale Microcontrollers, please visit
http://www.freescale.com/mcu


 
Yahoo! Groups Links



 



------------------------ Yahoo! Groups Sponsor --------------------~--> 
<font face=arial size=-1><a href="http://us.ard.yahoo.com/SIG=12h1d6uh0/M=362131.6882499.7825260.1510227/D=groups/S=1706554205:TM/Y=YAHOO/EXP=1123167105/A=2889191/R=0/SIG=10r90krvo/*http://www.thebeehive.org
">Get Bzzzy! (real tools to help you find a job) Welcome to the Sweet Life - brought to you by One Economy</a>.</font>
--------------------------------------------------------------------~-> 

-----------------------------------------------------------
To learn more about Freescale Microcontrollers, please visit
http://www.freescale.com/mcu


 
Yahoo! Groups Links

<*> To visit your group on the web, go to:
    http://groups.yahoo.com/group/MPC500/

<*> To unsubscribe from this group, send an email to:
    [email protected]

<*> Your use of Yahoo! Groups is subject to:
    http://docs.yahoo.com/info/terms/