Scalable System Software for Performance and Productivity

PI Name: 
Ewing Lusk
PI Email:
Argonne National Laboratory
Allocation Program: 
Allocation Hours at ALCF: 
Research Domain: 
Computer Science

As hardware complexity skyrockets in high-end computing systems, it is not easy for applications to take complete advantage of the available system resources and avoid potential bottlenecks. The purpose of this project is to improve the performance and productivity of key system software components on these leadership-class platforms. Researchers are studying four different classes of system software: Message Passing Libraries, Parallel I/O, Data Visualization, and Operating Systems. They are using time on the platforms to understand and solve problems that occur at scale. The project team is leveraging their connections with software development groups in SciDAC, exascale codesign centers, and the larger community to most effectively address these challenges. Through rigorous experimentation, analysis, and design cycles, this project will dramatically improve the capabilities of not only systems being deployed in the near term, but of all systems pushing scalability limits in the near future.