Re: mvme5500 (was National Instruments VME-MXI-1 modules vs. modernVMECPUmodules)

[Eric Bjorklund <bjorklund@lanl.gov>]

Umm... I may be completely missing the boat here, but didn't the 
VME-MXI-1 problem mostly involve bad data returned because of  "address 
rot" during the READ cycles? (c.f. Eric Norum's clarification post from 
14 Nov. 2003).

We've seen a similar problem with one of our boards here at LANSCE.  In 
our case, the "pipelined" address was not generated by the executing 
code.  I don't think it was from a PPC or PCI bus "pre-fetch" either, 
as there was no read cycle generated for the new address.   So unless 
there is some real cleverness going on between the Universe and the PCI 
controllers, it looks like the Universe chip is just trying to 
anticipate the next address I am going to want and putting out on the 
bus early (the new address was the logical successor to the addresses I 
had previously requested).  I am not aware of any cure for this  -- 
except that in our case it is our own board, so we can fix the problem 
at that level.

-Eric Bj.

On Mar 26, 2004, at 11:38 AM, Kate Feng wrote:

> Kate Feng wrote:
>
> > I agree with you  that one should enable the posted write by default.
> > However, it could be disabled, which means the address
> > pipelining on the  UniverseII could be disabled as well on the 
> > Mvme5500.
> > I thought the origianl issue is "to disable the  address pipelinig".
> > It  looks like you have a reason to disable the posted write
> > for the NI VME-MXI-1.   The trad off is to sacrifice the bandwidth
> > of the VME bus.  However, I do not know if  the decrease is
> > significant for your application.   I hope this helps.
>
> I  ran a   short test, which  showed  a decrease of  33% in
> performance for the posted-write disabled mode.  It might not be worse
> than the VMEchip2 that was used on the MVME167, which is in
> your existing system.   I do not have  the datasheet for the
> VMEchip2.  I guess it does not provide address pipeling,
> which explained why it worked fine with the  MXI-1.
>
>
> Again,  hoping this helps.   -- Kate


<><><><><><><><><><><><><><><><><><><><><><><><><><><><>
Eric Bjorklund
Los Alamos Neutron Scattering Center (LANSCE)

phone: 505-667-6031                                                     
email:  bjo@lanl.gov
<><><><><><><><><><><><><><><><><><><><><><><><><><><><>