Sun and Ni's Law

The Sun and Ni's Law is a generalization of Amdahl's Law as well as Gustafson's Law. The fundamental idea underlying the Sun and Ni's Law is to find the solution to a problem with a maximum size along with limited requirement of memory.  Now-a-days, there are a lot of applications which are bounded by the memory in contrast to the processing speed.

In a multiprocessor based parallel computer, every processor has an independent small memory.  In order to solve a problem, normally the problem is separated into sub-problems and distributed to a variety of processors. It may be noted that the size of the sub-problem should be in proportion with the size of the independent local memory available with the processor. Now, for a given problem, when large set of processors is culminated together, in that case the overall memory capacity of the system enhancing proportionately. Thus, instead of following Gustafson's Law i.e., fixing the implementation time, the size of the problem can be increased further such that the memory could be utilized. The above technique assists in generating more correct solution as the problem size has been increased.