Skip to end of metadata
Go to start of metadata

Our Resources

We provide Rice-affiliated researchers with a number of computing services and resources to facilitate research goals.

Computational Resources

Our primary role is the administration and maintenance of Rice’s Shared Computing Clusters and infrastructure.

If a researcher’s computational needs exceed that available from the shared clusters, there are two paths available. For those needing an environment similar to the core, we support a research condominium model where we attach researcher-purchased equipment into the infrastructure maintained for the shared systems. For those whose jobs can scale beyond the size of any of our systems, we offer assistance in transitioning to running on highly scaled national resources like XSEDE.

Data Management

Research data is the core of most computational research. The challenges our researchers face in managing this data have grown in recent years. In order to accommodate the increasing flow of scientific data between Rice and its collaborators across the globe, we provide a data transfer node connected to Globus Online in the model of the Energy Science Network’s Faster Data guidelines.

In addition, we provide guidelines and management plans of our own to researchers seeking grants from agencies that are increasingly paying close attention to how grant-related data is handled and curated through and beyond the life of the grant.

To help our researchers store large data sets in a collaborative environment, we provide the Research Data Facility - a combination of on-premises network storage and cloud based data storage. 

Visualization

In addition to our computational and data management resources, we recognize the importance of post-processing (and sometimes concurrent processing) and visualization of data sets used in  the computational clusters. Our Visualization Lab provides access to a high-resolution 200 inch 3D display wall, and the Visualization Portal allows users with laptops and low-end workstations lacking expensive 3D hardware to take advantage of the DAVinCI cluster’s 16 GPU nodes for visualization applications.

  • No labels