Experimental Physics and
Industrial Control System

Kate Feng <[email protected]> · Thu, 18 Mar 2004 14:30:19 -0500

Andrew Johnson wrote:

> Kate Feng wrote:
> >
> > Measured 60x bus bandwidth (MPC7450 + GT64260) :
> >     Pipelining  disabled : 177 MBytes/sec
> >     Pipelining  enabled :  589 MBytes/sec
> >
> > Thus, theoretically, one should be able to disable  the
> > address pipelining  of the mvme5500 (MPC7455 + GT64260).
>
> There's no way of getting 589MB/s through a regular VMEbus.
>

Perhaps I forgot to mention that the paper was based on work done
on  an  evaluation board without  the VME bus.   However, I did not
say one can get that 589 MB/s through a regular VME bus.
It is just a reference number to describe the possibility of
disabling the  address pipelining on the mvme5500.

>
> Address pipelining on the VMEbus (which was causing the problems with the
> VME-MXI-1 modules) is not related to address pipelining by the CPU on its
> local bus, which is presumably what the Motorola paper is quoting.

I did not say it was quoted by Motorola.  I said it was brought up by
someone in the tech-talk discussion.   Now I looked  back  at the archiver.
Oh, it was quoted by  someone  from APS  submitted to tech-talk
on  Fri, 14 Nov 2003 10:52:45 -060.

> The
> VMEbus cycle timings are completely controlled by the Tundra Universe-2
> chip on Motorola PowerPC boards, and VMEbus address pipelining cannot be
> disabled.
>

This is yet to be verified.   However, in the previous tech-talk   it was
quoted :

>  The APS has a rather large number of these modules. The flaw in the
VME-MXI-1
> has not caused problems because the modules have been used only
> with MVME167 CPU modules which do not perform address pipelining. We now
> want to upgrade some of these MVME167 IOCs to more modern CPU
> modules, but we've run into a problem. CPU modules with a UNIVERSE-II VME
interface
> chip (all Motorola 2100, 5100 and 5500 series) do perform
> address pipelining which results in erratic data transfer from VME-MXI-1
modules.
> My guess is that it is likely that any modern CPU is going to cause the
same problem.

Now you are telling me a different story.

Thanks,
Kate

Experimental Physics and Industrial Control System

Experimental Physics and
Industrial Control System