Hal Murray wrote:

> 
> > The '*Local* Communication bandwidths' numbers don't looks rigth compared
> > to Simon's results for a ds20/OSF1. I can't believe NetBSD is that bad :)
> 
> The EV6 can have 2 memory operations in progress at the same time.  
> The performance gain is dramatic when you can take advantage of that. 
> 
> Are the local communication numbers testing the compiler or bcopy 
> and friends?  Have either been tuned to know about EV6?

Lmbench doesn't appear to use any host-specific tuning options.  It
looks like lmbench uses gcc if it's in your path - I honestly can't
remember if said machine had gcc or not (I don't have access to the DS20
anymore)...

Simon.