Master/Slave Assignment Optimization for High Performance Computing in an EC2 Cloud Using MPI
For high performance computing, cloud services offer highly scalable infrastructures on demand. Without requiring a great deal of maintenance and financial resources, which a datacenter would need, it is possible to obtain a huge set of computing instances from, e.g., the Amazon Elastic Computing Cloud (Amazon EC2). The downsides of cloud computing are that the set of computing instances is arbitrary and that communication speed varies greatly and affects the running time of algorithms. The authors present a master/slave selection algorithm for the EC2 cloud service based on a benchmark to counteract this disadvantage.