To obtain sorting algorithms that scale to the largest available machines, conventional parallel sorting algorithms cannot be used since they either have prohibitive communication volume or prohibitive critical path length for computation. We outline ideas how to combine a number of basic algorithmic techniques which overcome these bottlenecks.
Practical Massively Parallel Sorting -- Basic Algorithmic Ideas
Michael Axtmann, Timo Bingmann, Peter Sanders, and Christian Schulz
Technial Report October 2014, arXiv:1410.6754