Argonne National Laboratory said today it has established a March 1 deadline to apply for an opportunity to learn the tools and techniques needed to carry out research on the world’s most powerful supercomputers.
Applications are now being accepted for ATPESC 2021 — a two-week training program designed to teach the skills, approaches and tools to design, implement and execute computational science and engineering (CSE) applications on current leadership-class supercomputers and next-generation exascale machines. Launched in 2013, ATPESC has hosted more than 500 participants since its inception.
The call for applications is now open, and interested doctoral students, postdocs and computational scientists are encouraged to apply here.
The architecture and software environments of today’s most powerful supercomputers are complex, Argonne said in its announcement, posing significant challenges to researchers interested in using them to advance scientific discoveries. To meet these challenges and facilitate breakthrough science and engineering on these amazing resources, the annual ATPESC — hosted by Argonne — provides specialized, in-depth training to doctoral students, postdocs and computational scientists.
“ATPESC provides an intense, broad and deep introduction to many aspects of high-performance computing, not just one or two,” said William Gropp, director and chief scientist, National Center for Supercomputing Applications and ATPESC lecturer. “Having direct access to some of the leaders in the field is great for asking questions, getting opinions and talking about careers. The participants also benefit from being part of the ATPESC community with their fellow students.”
The program will be held this year from Aug. 1-13 and is designed to address gaps in the training that computational scientists typically receive through formal education or other shorter courses.
“Many researchers start out with fairly ad hoc exposure to solving problems computationally. The ATPESC curriculum covers a broad set of topics, filling in gaps and providing a solid basis to support their future work,” said Ray Loy, ATPESC program director and lead for training, debugging and math libraries at the Argonne Leadership Computing Facility (ALCF), a DOE Office of Science User Facility.
More than 70 participants will attend lectures and hands-on training sessions provided by renowned computer scientists and HPC experts from U.S. national laboratories, universities and industry. The core curriculum will address:
- Computer architectures and predicted evolution.
- Numerical algorithms and mathematical software.
- Approaches to building community codes for HPC systems.
- Data analysis, visualization, I/O, and methodologies and tools for big data applications.
- Performance measurement and debugging tools.
- Machine learning and data science.
Qualified applicants will have
- Substantial experience in MPI and/or OpenMP programming.
- Experience in applying at least one HPC system to address a complex problem.
- Plans to conduct CSE research on large-scale computers.
There are no fees to participate, and domestic airfare, meals and lodging are provided to selected applicants. The event is currently planned to be in-person, as usual; if in-person meeting restrictions prevent that, ATPESC will be virtual.
ATPESC is organized by the ALCF and funded by the Exascale Computing Project (ECP), a collaborative effort of the DOE Office of Science’s Advanced Scientific Computing Research Program and the National Nuclear Security Administration. The training program is structured to align with the ECP’s mission to develop a capable computing ecosystem for future exascale supercomputers, including Aurora at Argonne and Frontier at Oak Ridge National Laboratory.
