[ECOS] structure size

Grant Edwards grante@visi.com
Mon Jan 5 22:43:00 GMT 2004


> > > Also, when the compiler inserts padding it usually does so for
> > > a good reason: manipulating packed structures can involve a
> > > significant performance penalty.
> >
> > Not only that, on many systems (ARM, SPARC, H8, ...)
> > manipulating packed structures can cause bus faults (if you're
> > lucky) or silently produce incorrect results.
> 
> You'd better believe it. ARM in particular seems to just
> quietly rotate data when you make non-aligned accesses,

That's certainly what an ARM7 does.  I don't remember for sure
what XScale does, but I have vague memories that it's
different.  I know A SPARC generates a bus fault.  I haven't
found out what an H8 does yet, but I imagine I'll find out the
hard way in the next few months.

> which is one very effective way to go insane.

The trick is to figure it out faster the next it happens. ;)

Porting x86 code (which allows unaligned accesses) to other
processors always seems to wake up alignment bugs.

-- 
Grant Edwards
grante@visi.com

-- 
Before posting, please read the FAQ: http://sources.redhat.com/fom/ecos
and search the list archive: http://sources.redhat.com/ml/ecos-discuss



More information about the Ecos-discuss mailing list