News for hackers. Stuff that matters.
Re:Lockfree algorithms by reitzensteinm on Wednesday June 13, 2012 @01:31AM (#4104469)
Rumor has it that Haswell-EP is going to bring 16 core, 32 threads CPUs (up from the current 10 core, 20 thread chips), allowing for 128 threads on a 4 socket systems.

Which is to say, we're actually not that far way from the title of this site becoming quaint, like Teradata does today - assuming Moore's law holds for a while.

Interestingly, and not coincidentally, Haswell is also the first chip that will support hardware transactional memory, which should speed efforts like PyPy's STM, which enables you to write code without manually locking anything.

http://morepypy.blogspot.co.nz/2012/06/stm-with-threads.html

Great submission though - bookmarked!

Re:Lockfree algorithms by 4ad on Wednesday June 13, 2012 @04:00AM (#4104821)
Please note that you could already have had 512 threads per 4 socket server since two years ago:

http://en.wikipedia.org/wiki/SPARC_T3

Re:Lockfree algorithms by dmpk2k on Wednesday June 13, 2012 @05:49AM (#4105099)
Considering the problems that Sun ran into with Rock, and the opinion that Cliff Click has for Azul's own HTM implementation, I wouldn't get excited yet.
Re:Lockfree algorithms by eternalban on Wednesday June 13, 2012 @09:22AM (#4105732)
>Considering ... Azul ...

I would like to consider: what did he say and when/where?

Re:Lockfree algorithms by bmm6o on Wednesday June 13, 2012 @10:59AM (#4106251)
Re:Lockfree algorithms by jwbaker on Wednesday June 13, 2012 @03:26AM (#4104728)
These docs can retain their usefulness even when their titles are long since obsolete. "The C10K Problem" comes to mind.