New Cornell Virtual HPC, Data Science, Machine Learning Workshops at XSEDE

Print Friendly, PDF & Email

ITHACA, NY – Cornell University announced today that four new Cornell Virtual Workshop training topics are available at the Extreme Science and Engineering Discovery Environment (XSEDE) User Portal:

  • Getting Started on Frontera
  • Introduction to Advanced Cluster Architectures
  • Using the Jetstream APIs
  • Python for Data Science: Part 2 – Data Modeling and Machine Learning

Cornell Virtual Workshop topics are freely available at all times to the entire scientific community – researchers, HPC practitioners, students, and educators – at XSEDE Online Training.

“Getting Started on Frontera” is a quick-start guide for the Texas Advanced Computing Center’s (TACC) Frontera supercomputer. Upon completion of Frontera training, you’ll be able to log in, store and move data, configure your shell environment, use the available compilers, select the correct queue for your job, and submit a job to Slurm.

“Introduction to Advanced Cluster Architectures” describes how to effectively use advanced clusters that are powered by large numbers of multi-core processors, abundant memory and cache, and fast interconnects. Scale up, scale out, and scale deep exercises are available with this training, as well as exercises on tuning codes.

“Using the Jetstream APIs” describes the different programmatic and user interfaces available with Jetstream/Jetstream 2, which to choose, and how to perform typical operations through the interfaces. Jetstream 2 is a cloud-based, on-demand computing and data analysis resource that builds upon the success of Indiana University Pervasive Technology Institute’s (PTI) Jetstream.

“Python for Data Science: Part 2: Data Modeling and Machine Learning” provides training on how to use Python and its libraries and packages to compute statistics on data sets, develop statistical models and visualizations, conduct parameter estimations using SciPy, analyze network models using NetworkX, carry out machine learning analyses using scikit-learn, and access XSEDE resources for data science.

In addition to these training opportunities, Cornell announced major updates to current virtual workshops, including Python for High Performance, Vectorization, Data Transfer, MATLAB Programming, and Hybrid Programming with OpenMP and MPI.

“We’re excited to be developing training materials for NSF-funded CI resources,” said Susan Mehringer, associate director for consulting at the Cornell Center for Advanced Computing. “Helping end-users to make best use of these architectures is very rewarding.” New training topics currently under development at Cornell include Jetstream 2 and Terraform, containers and Singularity, using Jupyter with HPC systems, GPU hardware, and deep learning.

The Cornell University Center for Advanced Computing (CAC) is a leader in the design and development of virtual workshops, webinars, and in-person training that enhances the computational skills of researchers and accelerates the adoption of new and emerging technologies. Over 250,000 unique users have accessed Cornell Virtual Workshop training modules.

The Extreme Science and Engineering Discovery Environment (XSEDE) is an NSF-funded virtual organization that integrates and coordinates the sharing of advanced digital services – including supercomputers and high-end visualization and data analysis resources – with researchers nationally to support science.