Hardware and Integration

Training and Productivity

Productivity

Principal Investigators:

Mike Heroux (Sandia National Laboratory)

Lois Curfman McInnes (Argonne National Laboratory)

Advances in next-generation computational science require the development of applications that can fully exploit emerging exascale architectures for optimal performance and provide high-fidelity multiphysics and multiscale capabilities. To help address overwhelming complexity, the members of the IDEAS-ECP project are collaborating with the ECP community to improve scientific productivity by qualitatively improving developer productivity (positively impacting product quality, development time, and staffing resources) and software sustainability (reducing the cost of maintaining, sustaining, and evolving software capabilities in the future).

Key aspects of work are as follows:

  • Working with individual ECP application development and software technology teams to understand productivity bottlenecks and improve software development practices through the Productivity and Sustainability Improvement Plan (PSIP) methodology.
  • Customizing and curating methodologies for productive and sustainable software development.
  • Establishing and providing editorial support for the Better Scientific Software portal (BSSw.io), a community-driven hub for sharing information on practices, techniques, experiences, tools, and other resources to improve developer productivity and software sustainability (Contributors welcome!).
  • Partnering with DOE leadership computing facilities to jointly develop training content, work with their delivery mechanisms, and address challenges in ECP software deployment.