A Building Blocks Approach towards Domain Specific Workflow Systems?

This paper makes the case for a fresh perspective on workflow-systems and, in doing so, argues for a building blocks approach to the design of workflow-systems. We outline a description of the building block approach and define their properties. We discuss RADICAL-Cybertools as an implementation of the building block concept, showing how they have been designed and developed in accordance to the building blocks method. Two use cases describe how \rct building blocks have been used to develop and integrate scientific workflow systems illustrating the applicability and potential of software building blocks. In doing so we have begun an investigation of an alternative and conceptual approach to thinking the design and implementation of scientific workflow-systems.

[1]  Shantenu Jha,et al.  SAGA: A standardized access layer to heterogeneous Distributed Computing Infrastructure , 2015 .

[2]  David Garlan,et al.  Architectural Mismatch or Why it's hard to build systems out of existing parts , 1995, 1995 17th International Conference on Software Engineering.

[3]  Judith Segal,et al.  Developing Scientific Software , 2008, IEEE Software.

[4]  Grant M. Rotskoff,et al.  Molecular simulation workflows as parallel algorithms: the execution engine of Copernicus, a distributed high-performance computing platform. , 2015, Journal of chemical theory and computation.

[5]  Shantenu Jha,et al.  ExTASY: Scalable and flexible coupling of MD simulations and advanced sampling techniques , 2016, 2016 IEEE 12th International Conference on e-Science (e-Science).

[6]  Feng Liu,et al.  Integrating Abstractions to Enhance the Execution of Distributed Applications , 2015, 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS).

[7]  Daniel S. Katz,et al.  Evaluating Distributed Execution of Workloads , 2016, 2017 IEEE 13th International Conference on e-Science (e-Science).

[8]  Edward A. Lee,et al.  Scientific workflow management and the Kepler system , 2006, Concurr. Comput. Pract. Exp..

[9]  Shantenu Jha,et al.  RepEx: A Flexible Framework for Scalable Replica Exchange Molecular Dynamics Simulations , 2016, 2016 45th International Conference on Parallel Processing (ICPP).

[10]  Shantenu Jha,et al.  Ensemble Toolkit: Scalable and Flexible Execution of Ensembles of Tasks , 2016, 2016 45th International Conference on Parallel Processing (ICPP).

[11]  Gregor von Laszewski,et al.  Swift: Fast, Reliable, Loosely Coupled Parallel Computation , 2007, 2007 IEEE Congress on Services (Services 2007).

[12]  Shantenu Jha,et al.  Synapse: Synthetic Application Profiler and Emulator , 2016, 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).

[13]  Don S. Batory,et al.  The design and implementation of hierarchical software systems with reusable components , 1992, TSEM.

[14]  Daniel S. Katz,et al.  Application skeletons: Construction and use in eScience , 2016, Future Gener. Comput. Syst..

[15]  Peter V. Coveney,et al.  Automated Molecular Simulation Based Binding Affinity Calculator for Ligand-Bound HIV-1 Proteases , 2008, J. Chem. Inf. Model..

[16]  Jacquelyn S. Fetrow,et al.  Scientific Software Development Is Not an Oxymoron , 2006, PLoS Comput. Biol..

[17]  Shantenu Jha,et al.  P∗: A model of pilot-abstractions , 2012, 2012 IEEE 8th International Conference on E-Science.

[18]  Daniel S. Katz,et al.  Pegasus: A framework for mapping complex scientific workflows onto distributed systems , 2005, Sci. Program..

[19]  Shantenu Jha,et al.  Executing dynamic heterogeneous workloads on Blue Waters with RADICAL-Pilot , 2016 .

[20]  Justin M. Wozniak,et al.  Coasters: Uniform Resource Provisioning and Access for Clouds and Grids , 2011, 2011 Fourth IEEE International Conference on Utility and Cloud Computing.