The SMPH Research Computing Infrastructure is a new School of Medicine and Public Health initiative aimed at advancing researchers’ capabilities in computational research. Over the next couple of years, the SMPH will embark on a series of concerted efforts to accomplish the overarching goal of having a seamless data storage and computing system for high-throughput and specialized computational research.
As a first step toward the seamless data storage and computing system for research, the SMPH has provided the funding for an expansion of the Social Sciences Computing Cooperative (SSCC) computing environment in terms of both computing capacity at SSCC and storage (hosted at the DoIT data center). This expansion is specifically for use in data intensive -omics and other computationally intensive research. Silo has the capacity to store large data files and the potential to streamline computational pipelines. Researchers are encouraged to investigate and utilize these capabilities. Users’ feedback is critical for assessing current capacity limitations in order to facilitate our continuous evaluation and improvement process.
- 816 total cores at launch, including from 3 Interactive Linux, 2 High-Performance Linux, 9 HTCondor, and 4 Windows servers
- The data storage component from DoIT, with 400TB at launch
- Numerous common software available, such as R/RStudio with multiple packages, Python 2.7 & 3.7, SAS, Stata, and many more