Booting Imac G5

[J. Mayer]

On Tue, 2004-11-23 at 13:35, Segher Boessenkool wrote:
> > They may use the SPU interface to access the RAM.  But, in fact, 
> > looking
> > at the OF SMU driver, I should have been warned about the cache issue:
> > this routine is quite clear:
> > : clr-cache-lines
> >    cmd-buf ^dcbf ^sync  ;
> 
> Well yes, but Apple OF tends to use very heavy hammers for no
> reason at all, all of the time ;-)

I've seen that Darwin does not seem to be the best example for an
optimisation lesson ;-)

> I'd really like to _understand_ the issue -- although that's
> not necessary at all for programming the driver, of course,
> monkey-see, monkey-do worked fine for all the other Mac
> drivers ;-P

I'd like to understand what the hardware does too !
It seems logical too me that it would use the SPU interface to access
the memory. If the SPU interface is really like a JTAG interface as it
seems to be, then it can entirelly control the CPU, so it could also
invalidate the caches when needed.  Only getting (and understanding !)
the SPU firmware may tell us what it really does....

-- 
J. Mayer <l_indien at magic.fr>
Never organized