Data Intensive Computing

This course deals with various topics in data-intensive computing to address challenges in managing large-scale data and methods for extracting values from big data. Specifically, we explore state-of-the-art techniques to build parallel systems and applications for scalable data analysis on a massive and complex dataset, those from scientific and engineering problems. Topics include: 1) Storage requirements of big data; 2) parallel and distributed computing systems in both high-performance computing (HPC) and commercial domains; 3) Data-parallel frameworks such as MapReduce/Hadoop/Spark; 4) parallel file systems such as HDFS/Lustre; 5) NoSQL data models such as Dynamo/BigTable/Cassandra; and 6) time-series data models such as InfluxDB/Prometheus.