Re: AVL trees vs. Red-Black trees

Jamie Lokier (lkd@tantalophile.demon.co.uk)
Mon, 29 Nov 1999 21:46:53 +0100


Andrea Arcangeli wrote:
> On Mon, 29 Nov 1999, Ingo Molnar wrote:
> >guarantees the 'Program Order' shared memory model, which makes
>
> Unfortunately the empirical test tells that something must be going wrong.
> I have to possible diagnoses:

It could also be a processor bug. Maybe they're meant to guarantee
Program Order but get it wrong. This stuff is complex; I heard they use
formal verification techniques to get the cache coherency protocols
right. Yet they change it from stepping to stepping (why else wouldn't
different steppings be compatible). Even formal techniques can have
bugs :-)

-- Jamie

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/