Indeed there is an hybrid algo using both i.e( parallel Merge sort) there are various parallel programming models/API/Languages (OPENMP,MPI,Cilk) you can test it. U can divide the array in to half and give it to 2 processeor and do the job which may be efficent than sequential merge sort
also there is no exact way to tell how to split the array if there are p processors n/p may be a good choice Also see wiki page for Parallel Computing <http://en.wikipedia.org/wiki/Parallel_computing> dividing array will come under data-level parallelism. On Mon, May 25, 2009 at 4:16 AM, OK <[email protected]> wrote: > > HI everybody, > > I'm wondering what will be more efficient. > Let's say I have p processors (so i can use p processes working > parallel). > I need to create a merge sort so I got two options: > 1) Divide the array to half each time and give each process a half > when it's possible. > 2) Divide the array to n/p sections when every process need to sort > each section. > > > -- Potential is not what U have, its what U think U have!!! --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "Algorithm Geeks" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/algogeeks -~----------~----~----~----~------~----~------~--~---
