Applying MDA to Generate Hadoop Based Scientific Computing Applications

The paper presents an attempt to develop and deploy a functioning MDA (Model-Driven Architecture) model of a distributed scientific application. The main focus is a problem of modeling high performance computing processes in a visual notation and automatic generation of an executable code using the resulting diagrams. The article describes the efforts to create a platform independent model of process execution, transformation it into a platform specific model and, finally, automatic generation an application code. The research novelty includes a platform independent model of the classic hydrodynamics problem, equivalent Hadoop based platform specific model and the testing results that confirm feasibility of the research.

[1]  David Frankel,et al.  Model Driven Architecture: Applying MDA to Enterprise Computing , 2003 .

[2]  Benoît Combemale,et al.  MDE in Practice for Computational Science , 2015, ICCS.

[3]  Ileana Ober,et al.  Improving scalability and maintenance of software for high-performance scientific computing by combining MDE and frameworks , 2011, MODELS'11.

[4]  Andrzej Daniluk,et al.  Visual modeling for scientific software architecture design. A practical approach , 2012, Comput. Phys. Commun..

[5]  Ileana Ober,et al.  HPCML: a modeling language dedicated to high-performance scientific computing , 2012, MDHPCL '12.

[6]  Ileana Ober,et al.  MDE4HPC: An Approach for Using Model-Driven Engineering in High-Performance Computing , 2011, SDL Forum.

[7]  Mark C. Miller,et al.  Enabling Interoperation of High Performance, Scientific Computing Applications: Modeling Scientific Data with the Sets & Fields (SAF) Modeling System , 2001, International Conference on Computational Science.

[8]  David Lugato.  Model-driven engineering for high-performance computing applications , 2008 .

[9]  Kyoungho An,et al.  A Model-driven Approach for Price/Performance Tradeoffs in Cloud-based MapReduce Application Deployment , 2013, MDHPCL@MoDELS.

[10]  Bolatzhan Kumalakov,et al.  Distributed parallel algorithm for numerical solving of 3D problem of fluid dynamics in anisotropic elastic porous medium using MapReduce and MPI technologies , 2015, 2014 9th International Conference on Software Engineering and Applications (ICSOFT-EA).

[11]  Anatolij Zubow,et al.  Map/reduce on EMF models , 2012, MDHPCL '12.

[12]  Bedir Tekinerdogan,et al.  Domain Specific Language for Deployment of Parallel Applications on Parallel Computing Platforms , 2014, ECSAW '14.

[13]  Richard J. Sadus,et al.  A suite of domain-specific visual languages for scientific software application modelling , 2013, 2013 IEEE Symposium on Visual Languages and Human Centric Computing.

[14]  Manuel Barata,et al.  Development High Performance Scientific Computing Application Using Model-Driven Architecture , 2013 .

[15]  Jean-Luc Dekeyser,et al.  A Model-Driven Design Framework for Massively Parallel Embedded Systems , 2011, TECS.

[16]  Bedir Tekinerdogan,et al.  Architecture Framework for Mapping Parallel Algorithms to Parallel Computing Platforms , 2013, MDHPCL@MoDELS.