> Do people agree that something like this is required?
I'm not sure. I think for processors which permit this much staleness,
it's almost a prerequisite to have a working pool (for each processor?)
of ``fresh'' memory which is guaranteed to not be in cache on other
processors. Such memory could be allocated at each garbage collection.
Combined with knowledge of cache line width, it's probably reasonable to
use fresh memory and write-once techniques for JITed code and the like.
On the other hand, aggressive pre-fetching might defeat such techniques.
I can't quite see how yet, but I'm sure somebody else will.
--p
-------------------------------
This is the JavaMemoryModel mailing list, managed by Majordomo 1.94.4.
To send a message to the list, email JavaMemoryModel@cs.umd.edu
To send a request to the list, email majordomo@cs.umd.edu and put
your request in the body of the message (use the request "help" for help).
For more information, visit http://www.cs.umd.edu/~pugh/java/memoryModel
This archive was generated by hypermail 2b29 : Thu Oct 13 2005 - 07:00:16 EDT