> >I.e., i'm wondering about:
> >	(1) PCI load caused by script instruction fetches?
> >	    (fixed in some newer SIOP variants)
> 
> This would have caused the NCR controller to be slower in every
> situation, wouldn't it? It seems that the NCR driver is slower only
> with specific drives.

That really depends on the PCI implementation of the host, the host
and PCI bus loading, the structure of the SIOP scripts, etc.


cgd