Title: Introduction to Hadoop, Spark, and Beyond
Speaker: Saliya Ekanayake
Abstract: With the introduction of MapReduce by Google in 2004, academia and industry have contributed a vast number of open source software to facilitate Big Data use cases. Hadoop and Spark being the prominent and widely adopted in the industry, it is interesting to understand whether these can be used in scientific applications and what advantageous or limitations they would bring to the table. Also interesting are the questions; if Big Data software can replace the de facto MPI+X model used in High Performance Computing (HPC) or can there be a convergence between these two domains for the greater good? In this regard, I'll introduce Hadoop, Spark, and their libraries and discuss some of the pros and cons of these systems when developing scientific applications. Specifically, I'll go through experience of implementation of a graph algorithm in Spark and Giraph. The talk will also introduce some of the recent developments to combine Big Data software with HPC.
Title: Espresso: Modeling, simulation, and analysis of complex dynamics over synthetic population
Speaker: Sandeep Gupta
Abstract: Espresso is a framework to model and study complex dynamics coupled with contagion spread within a synthetic population. Example of such dynamics include, strategic placement of hospitals, interventions (school closure,vaccination) based on geographical and epidemic attributes and so on. I will primarily focus on how to configure/program the framework to express novel dynamics. The talk will assume familiarity with basic simulation science and epidemiological concepts.
In addition to this, I will also touch upon the role of complex systems and collaborative research as it applies to broader computational epidemiology research.
Meeting number: 643 164 789
Host key: 749673
+1-855-749-4750 US TOLL FREE
+1-415-655-0001 US TOLL
Show toll-free dialing restrictions
Access code: 643 164 789