In this communication, we would like to test the feasibility of a parallel tempering based study of dissociation in dicationic noble gas clusters, namely, Ar(n)(2+), Kr(n)(2+), and Xe(n)(2+), where "n" is the size of the cluster units. We would like to find out the correct limit for sizes of each of these systems, above which the clusters stay intact as a single unit and does not dissociate into fragments by the process of Coulomb explosion. Moreover, we would also like to, for a specific case, i.e., Ar(n)(2+), study in detail the fragmentation patterns and point out the switchover from the non-fission way to the fission mechanism of dissociation. In all these calculations, we would like to analyse, how close we are in our predictions with that of experimental results. As a further check on the dissociating patterns found out by parallel tempering, we also conduct basin hopping based study on representative sizes of the clusters and find that parallel tempering, as used for this present work as an optimizer, is able to predict correct features when compared with other celebrated methods like the basin hopping algorithm.