Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Strategies & Market Trends : 2026 TeoTwawKi ... 2032 Darkest Interregnum -- Ignore unavailable to you. Want to Upgrade?

To: yard_man who wrote (63884)	5/26/2010 5:52:45 PM
From: benwood	Read Replies (1) \| Respond to of 217543

Propagation delays abound; those from travel times of electrons through gold/silver/copper are fixed (at ~80% of speed of light) and as processing speeds increase and as gate delays decrease (in gate arrays, CPUs, etc.), the propagation delay caused solely by the length of the wire (again, a fixed amount for a given length) become proportionally larger in relation to the overall delay. Some of this has been mitigated by design, e.g. a billion transistors in a few square centimeters, so many signals do not travel far. But in a cluster, they travel several feet at times (between processing nodes), and in cloud computing, they can travel many miles through all sorts of delaying routers. Generally, the processing load required by cluster computing would be large compared to the data transfer time, but with no transit time at all (the hope from quantum teleportation or some variation thereof), the possibilities not only open up dramatically about the nature of cloud computing (i.e. even mundane tasks) but the performance would increase greatly through optimal algorithm design and even optimal software design (that is, software developed more quickly and which is more reliable). Just my off the top of the head thoughts.