Re: [patch] Re: spin_unlock optimization(i386)

Ingo Molnar (mingo@chiara.csoma.elte.hu)
Sun, 21 Nov 1999 17:57:42 +0100 (CET)


On Sun, 21 Nov 1999, Alan Cox wrote:

> Unfortunately it then goes on to say "Intel does not guarantee that
> future processors will support this model"

yes, but it will definitely be told wether a model supports this or not.
It's a really noticeable performance and cache footprint win, and there is
no problem at all to reintroduce a (saner) write-barrier later on if a
more advanced model is added. On 550MHz PIII Xeons there is no problem so
far with this.

-- mingo

-
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/