@inproceedings{70134a0c21c5457fbf62629b39fdc4fb,
title = "BDMPI: Conquering BigData with small clusters using MPI",
abstract = "The problem of processing massive amounts of data on clusters with finite amount of memory has become an important problem facing the parallel/distributed computing community. While MapReduce-style technologies provide an effective means for addressing various problems that fit within the MapReduce paradigm, there are many classes of problems for which this paradigm is ill-suited. In this paper we present a runtime system for traditional MPI programs that enables the efficient and transparent disk-based execution of distributed-memory parallel programs. This system, called BDMPI, leverages the semantics of MPI's API to orchestrate the execution of a large number of MPI processes on much fewer compute nodes, so that the running processes maximize the amount of computation that they perform with the data fetched from the disk. BDMPI enables the development of efficient parallel distributed memory disk-based codes without the high engineering and algorithmic complexities associated with multiple levels of blocking. BDMPI achieves significantly better performance than existing technologies on a single node (GraphChi) as well as on a small cluster (Hadoop).",
keywords = "Bigdata, MPI, Out-of-core, Parallel processing",
author = "{La Salle}, Dominique and George Karypis",
year = "2013",
month = nov,
day = "18",
doi = "10.1145/2534645.2534652",
language = "English (US)",
series = "Proceedings of DISCS 2013: The 2013 International Workshop on Data-Intensive Scalable Computing Systems, Held in conjunction with SC 2013: The International Conference for High Performance Computing, Networking, Storage and Analysis",
publisher = "Association for Computing Machinery, Inc",
pages = "19--24",
booktitle = "Proceedings of DISCS 2013",
note = "2013 International Workshop on Data-Intensive Scalable Computing Systems, DISCS 2013 ; Conference date: 18-11-2013",
}