A collaborative project involving Virginia Tech, Stony Brook, and ICL/UTK, the Ecosystem for Programming and Executing eXtreme Applications (EPEXA), aims to create a software framework that implements high-performance methods for irregular and dynamic computations that are poorly supported by current programming paradigms. Employing science-driven codesign, the EPEXA team will harden a successful research prototype into an accessible, production-quality programming model that will leverage domain-specific languages (DSLs) to improve accessibility and accelerate the adoption of high-performance tools for computer scientists and domain scientists.
The project bridges the so-called "valley of death" between a successful proof of concept and an implementation with enough quality, performance, and community support to motivate application scientists and other researchers to adopt it and invest their own effort into pushing for community use. Specifically, the new powerful data-flow programming model and associated parallel runtime directly address multiple challenges faced by scientists as they attempt to employ rapidly changing computer technologies—including current, massively parallel, hybrid, and many-core systems. Both data-intensive and compute-intensive applications are enabled in part by the general programming model and through the ability to target multiple backends or runtime systems.
In Collaboration With
- Stony Brook University
- Virginia Tech