sjn wrote:While typically slower when used as fixed general purporse processoring devices, they come into their own when you need to perform anticipated algorithyms. Some models can be reprogrammed very quickly indeed and it is possible to reconfigure the device optimally for any given task; this way it easily out performs fixed funcion general purpose CPUs.
Correct .. we are using them to speed up random number generation for stochastic simulations of cells. There was a publication in
Nature Biotechnology a few months ago which featured the implementation of the Gillespie algorithm on a chip. It is is up to hybrid sw/hw engineers to come-up with a system design (not a new technology platform) to start simulations in those babies. Once we do that ... it is going to be a new era for bio-engineering, material science etc.
I'm following developments just for the heck of it ...
"Nuclear power has long been to the Left what embryonic-stem-cell research is to the Right--irredeemably wrong and a signifier of moral weakness."Esquire Magazine,12/05
The genetic code is commaless and so are my posts.