SciDAS will provide advanced cyberinfrastructure to support the creation of distributed compute infrastructure for the efficient injection of data and workflows into the compute environment. SciDAS is supported by rule based data discovery and retention policies with iRODs and the SciDASH dashboard for monitoring and interacting with a high scale computational experiment.
SciDAS is for researchers who need to process terabytes to exabytes of data. Computer scientists & engineers build amazing systems, but domain scientists are having problems scaling up their data-intensive scientific applications: nodes break, storage/RAM/CPUs are finite, total compute time is uncertain. SciDAS provides the solution to this problem.
Read the Clemson media release here.