News & Events

  • CREST of IU receives Grant from NSF for Collaborative Research Proposal: "ParalleX Based Transformative I/O System for Big Data"

    Date: 08/22/2014

    The National Science Foundation awarded a grant of $300,000 to CREST of Indiana University for support of the project described below. This award started September 1, 2014 and will end on August 31, 2016. Maciej Brodowicz is lead PI.

    Abstract of the Proposal:

    Big Data problems include extremely large amounts of data that must be processed coupled with complex computational requirements. Neither entirely compute bound, nor entirely I/O bound, Big Data applications typically involve the collection and integration of large data sets with computational models with problematic data organization and management issues. Post processing analytics and visualization further complicate them.

    In this proposal we will demonstrate that an extension of new, highly innovative parallel execution model ParalleX will allow researchers to develop highly efficient data management, discovery, and analysis codes for Big Data applications covering a wide range of fields that both favor large scale computation and efficient large data set handling. We intend to do this by implementing a Map/Reduce application framework on a combination of HPX, an implementation of ParalleX based on C++, and PXFS, a high performance parallel file system based on OrangeFS currently being co-designed with HPX. This approach ensures a wide applicability of the results delivered by the proposed work.