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
