[Beowulf] Moores Law is dying
coutinho at dcc.ufmg.br
Wed Apr 15 14:04:13 PDT 2009
2009/4/14 Joe Landman <landman at scalableinformatics.com>
> Jon Forrest wrote:
> But this wouldn't happen in the scenarios you describe
>> because text is read-only. There would be no updaters or writers
>> or any kind of contention. The text pages would have to get filled
> Ok, lets assume you have a table in the text, that every thread is using to
> dereference. Sure it can go in the data section, but some compilers (old
> SGI) could leave it in the text area for faster access.
I believe that today it can't be done. In most architectures (except for our
lovely x86 :) ) text pages are read only so data placed here must be read
> Same thing with contention. Read contention is harder to diagnose than
> write contention, as you don't get the cache line update from the writes
> triggering the associated counters, so this is a bit more subtle. But the
> effect is there.
This can be relived with broadcast hardware, but this can make hardware
complexity grow too fast.
> I know you might postulate that 32 bit text is effectively the CS
>>> equivalent of "C" in physics ... you may approach it asymptotically, but
>>> never actually get there ... but unlike in physics, there isn't really an
>>> underlying reason why you might not get there.
>> The underlying reason in this case is complexity.
> So you are posulating that complexity scales as Nbytes of text?
> Joseph Landman, Ph.D
> Founder and CEO
> Scalable Informatics LLC,
> email: landman at scalableinformatics.com
> web : http://www.scalableinformatics.com
> phone: +1 734 786 8423 x121
> fax : +1 866 888 3112
> cell : +1 734 612 4615
> Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin Computing
> To change your subscription (digest mode or unsubscribe) visit
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Beowulf