freeCycles is a VC solution and thus, its ultimate goal is
to aggregate as many volunteer resources as possible to perform
general purpose computation. As that being, our solution
must be capable of scaling up with the number of volunteers
and collecting volunteers’ resources such as CPU cycles
and network bandwidth in an efficient way. We also believe
that being able to tolerate volunteer faults and unreliable network
connections is an important requirement for our solution
since volunteer node churn is very high in large scale
networks (as the Internet). freeCycles must be capable of supporting
new parallel programming paradigms, in particular
MapReduce, given its relevance for a large number of applications.
Finally, as MapReduce applications depend on large
amounts of information to run, freeCycles must be capable
of distributing large amounts of data (namely input, intermediate
and output data) efficiently without compromising its
scalability.
freeCycles is a VC solution and thus, its ultimate goal is
to aggregate as many volunteer resources as possible to perform
general purpose computation. As that being, our solution
must be capable of scaling up with the number of volunteers
and collecting volunteers’ resources such as CPU cycles
and network bandwidth in an efficient way. We also believe
that being able to tolerate volunteer faults and unreliable network
connections is an important requirement for our solution
since volunteer node churn is very high in large scale
networks (as the Internet). freeCycles must be capable of supporting
new parallel programming paradigms, in particular
MapReduce, given its relevance for a large number of applications.
Finally, as MapReduce applications depend on large
amounts of information to run, freeCycles must be capable
of distributing large amounts of data (namely input, intermediate
and output data) efficiently without compromising its
scalability.
การแปล กรุณารอสักครู่..
