[
Lists Home |
Date Index |
Thread Index
]
What kind of application would seriously benefit from this sort of
fine-grained intra-task parallelism? Server apps typically runs many
tasks concurrently, and so embarrasing parallelism is found naturally
at more coarse grained levels, which is more cost effective. Plus,
given that the algorithm is deviating from pure sequential access it
might not even speed things up at all.
Wolfgang.
On Mar 31, 2006, at 11:22 PM, Sean McGrath wrote:
> I have sketched out an algorithm for fast XML WF parsing utilising
> two threads that each start at opposite ends of the octet-stream
> and meet in the middle. The algorithm hinges on the fact that
> start- and end-tags are balanced. i.e. as one thread reads forward
> looking for foo start-tag, the other thread is reading backwards
> looking for foo end-tag.
>
> This also has the nice side effect of giving you accurate error
> messages quickly. i.e. as soon as a mismatched tag is found, it can
> be reported. This is particularly useful with recursive element types.
>
> Modern machines (even desktop boxes) will increasingly have multi-
> core CPUs as standard and I think it behooves us to find ways of
> exploiting that in the XML world.
>
> But to get the most out of the algorithm, you really need a
> filesystem that supports reading byte-streams backwards.
>
> Does anyone know of such a filesystem?
>
> thanks,
> Sean
>
>
> -----------------------------------------------------------------
> The xml-dev list is sponsored by XML.org <http://www.xml.org>, an
> initiative of OASIS <http://www.oasis-open.org>
>
> The list archives are at http://lists.xml.org/archives/xml-dev/
>
> To subscribe or unsubscribe from this list use the subscription
> manager: <http://www.oasis-open.org/mlmanage/index.php>
>
|
