On Mon, Jan 16, 2012 at 04:10:53PM -0800, David Barbour wrote:
> I disagree with this assertion: "we will need to embrace a style of
> programming without any synchronization whatsoever."
> 
> Rather, synchronization will just shift from the physical domain (e.g.
> compare-and-swap, data races on the network or bus) to the logical domain
>  (e.g. temporal semantics, consistency through commutativity and logical
> monotonicity). This essentially means trading memory for parallelism and
> performance.

Biology also synchronizes locally coupled oscillators (with positive
and negative feedback loops) which are made from asynchronous components.

A nice, albeit a little shallow book on synchronization is
http://www.amazon.com/Sync-Order-Emerges-Universe-Nature/dp/0786887214/

Notice that Chuck Moore has a history of making clockless/asynchronous
chips, his latest being 144-core GA144 http://www.greenarraychips.com/

So you can go clockless at die level, as long as complexity is low.

> Berkeley's Order of Magnitude project (BOOM) and my own work on RDP are
> examples of effectively supporting logical synchronization. But there are a
> lot of precedents, e.g. regarding various `synchronous programming` models.
> 
> * http://lambda-the-ultimate.org/node/4162
> * http://awelonblue.wordpress.com/2011/10/06/vat-model-for-rdp/
> 
> I also expect we'll shift latency into the logical domain.
_______________________________________________
fonc mailing list
[email protected]
http://vpri.org/mailman/listinfo/fonc

Reply via email to