The SciTech research team wishes you a wonderful 2017! In 2016, we had a great year and several accomplishments. Among them, we highlight the LIGO’s discovery early this year and how the Pegasus team has contributed to LIGO’s software infrastructure.
Research Grants from the National Science Foundation: We have been awarded with 4 research grants to address cybersecurity controls in Pegasus (Indiana University, USC, and RENCI); to develop a portfolio of computational modeling and simulation software for earthquake, wind, and multi-hazard engineering research and education; to develop a simulation workbench for scientific workflows (UHM and USC); and to enhance user productivity and broadening participation of the Computational and Data-enabled Science and Engineering (CDS&E) community (XSEDE2).
Research Seminars: We have hosted 4 research seminars presented by top research leaders from the HPC, scientific workflows, science gateways, and distributed systems communities: Dr. Gesing presented enhancements of workflow systems to address the usability of workflows and optimizations of their efficiency; Dr. Filgueira presented a review of existing research infrastructures used by the scientific community to conduct a top-level research in their field; Dr. Klimeck discussed some of the myths and perceptions of what is possible and impossible to achieve scientific knowledge transfer; and Dr. Prodan presented a multi-objective scheduling and enactment approach for makespan, cost, energy efficiency and fault tolerance using provenance information on distributed cloud and manycore parallel infrastructures.
Publications in Peer-Reviewed Journals: We have published 6 journal articles about the Pegasus software, applications, and research in scientific workflows:
Workflow Optimization:
- Dynamic and Fault-Tolerant Clustering for Scientific Workflows, IEEE Transactions on Cloud Computing
Workflow Reproducibility:
- Enhancing reproducibility for computational methods, Science
- Reproducibility of Execution Environments in Computational Science Using Semantics and Clouds, Future Generation Computer Systems
Pegasus Software:
- Pegasus in the Cloud: Science Automation through Workflow Technologies, IEEE Internet Computing
Pegasus Applications:
- PGen: large-scale genomic variations analysis workflow and browser in SoyKB, BMC Bioinformatics
- OSG-GEM: Gene Expression Matrix Construction Using the Open Science Grid, Bioinformatics and Biology Insights
Publications in Peer-Reviewed Conferences: We have also published 13 conference papers discussing Pegasus software and applications, workflow optimizations and fault-tolerance, and data analyses:
Fault-tolerance:
- Using Simple PID Controllers to Prevent and Mitigate Faults in Scientific Workflows, 11th Workflows in Support of Large-Scale Science (WORKS’16)
- Anomaly Detection for Scientific Workflow Applications on Networked Clouds, IEEE 2016 International Conference on High Performance Computing & Simulation (HPCS’16)
Data Analytics and Modeling:
- Workflow Performance Profiles: Development and Analysis, Euro-Par 2016: Parallel Processing Workshops
- Consecutive Job Submission Behavior at Mira Supercomputer, 25th ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC)
- Analyzing Users in Parallel Computing: A User-Oriented Study, 14th International Conference on High Performance Computing & Simulation (HPCS’16)
- Understanding User Behavior: from HPC to HTC, International Conference on Computational Science (ICCS’16)
Cloud Computing:
- Performance Analysis of an I/O-Intensive Workflow executing on Google Cloud and Amazon Web Services, 18th Workshop on Advances in Parallel and Distributed Computational Models (APDCM)
Scheduling:
- Increasing Waiting Time Satisfaction in Parallel Job Scheduling via a Flexible MILP Approach, 14th International Conference on High Performance Computing & Simulation (HPCS’16)
Pegasus (software, applications, integration):
- Automating Environmental Computing Applications with Scientific Workflows, Environmental Computing Workshop (ECW’16)
- Asterism: Pegasus and dispel4py hybrid workflows for data-intensive science, 7th International Workshop on Data-Intensive Computing in the Clouds (DataCloud’16)
- Science Automation in Practice: Performance Data Farming in Workflows, 21st IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)
- Toward and End-to-end Framework for Modeling, Monitoring, and Anomaly Detection for Scientific Workflows, Workshop on Large-Scale Parallel Processing (LSPP 2016)
In addition, we have hosted 3 visiting researchers (Dr. Rosa Filgueira, Dr. Frédéric Suter, and Prof. Martin Quinson), 2 graduate students (Stephan Schlagkamp and Saloni Pryia), and 2 summer internships (Guilherme Gribeler and Samrat Jha).
Additional Pointers:
753 views