The University of Michigan(U-M), in partnership with Marvell, has built a Data Analytics cluster with ThunderX processors based on the Hadoop and Spark family of tools. We present information on the deployment and use of the cluster, which uses software packaged by the Linaro Big Data teams. We also present feedback to the Big Data on ARM community and future plans for development for Big Data on ARM at U-M as well.
Research Computing Manager (University of Michigan)
Jeremy Hallum is the manager responsible for Storage, Private Cloud, and Data Science Operations teams at ARC-TS at the University of Michigan. His teams are responsible for the deployment of the storage systems, Yottabyte Research Cloud, and Marvell data science Cluster.
Jeremy earned his undergraduate degree from Minnesota State University in Astronomy and Mathematics in 1996, and a Masters degree from Boston University in 1999 in Astronomy. His interests lie in developing usability for advanced computing resources, user training and secure use of advanced computing resources.