Helping Scientists Create and Use Very Large Volumes of Data in ECP Activities

Rob Ross is a senior computer scientist at Argonne National Laboratory and a senior fellow in the Northwestern Argonne Institute for Science and Engineering. He is also an adjunct assistant professor in the Department of Electrical and Computer Engineering at Clemson University. In addition, Ross is principal investigator for a research effort called Datalib: Data Libraries and Services Enabling Exascale Science, which is funded by the US Department of Energy’s (DOE) Exascale Computing Project (ECP) under its Software Technology research focus area. ECP is a joint collaboration of two DOE sponsoring organizations, the Office of Science (DOE-SC) and the National Nuclear Security Administration (NNSA).

The Datalib project aims to develop software that helps scientists create and use very large volumes of scientific data as part of their ECP activities. It approaches the effort in three ways: (1) by supporting and extending packages scientists can use to access and share data across all the different platforms on which they work; (2) by employing tools that reveal how scientists are using their data, thus providing information to troubleshoot problems at facilities and to better configure future systems; and (3) by bringing to bear research from other DOE Advanced Scientific Computing Research (ASCR) programs that enable the Datalib team to build entirely new specialized data services to replace tools that are either too hard to use or are too slow.

Chat Notes

What the Datalib project is about [1:40]

Recent project successes [3:23]

The composition of the Datalib team [4:31]

The intangible benefits of being a part of ECP [6:06]

What is on the horizon for the Datalib project [7:36]