The architecture and software environments of today’s most powerful systems, including those at the Argonne Leadership Computing Facility and at the Oak Ridge Leadership Computing Facility pose new and unique challenges to their users. Technology trends indicate that the next generation of systems, circa 2017, and the exascale systems projected for 2022 will feature far greater parallelism and complexity of architectures. The Argonne Training Program on Extreme-Scale Computing will focus on the key skills, approaches, and tools necessary to design, implement, and execute CS&E applications on current high-end systems and the Leadership-Class systems expected to be available in 2017 and beyond.
The Argonne Training Program on Extreme-Scale Computing will cover the key topics that computational science and engineering researchers must master to develop and use leading-edge applications. The program fills a gap in the training that most computational scientists receive; hence it will provide a more comprehensive program than typical short courses. Individuals with expertise and leadership responsibilities in each of these key topic areas will serve as the respective lecturers and the hands-on laboratory session guides.
The core of the program will focus on programming methodologies that are effective across a variety of supercomputers and that are expected to be applicable to exascale systems. Multiple approaches will be covered but the emphasis will be on unifying concepts and levels of abstraction that provide migration paths and performance portability among current and future architectures. Additional topics to be covered include computer architectures, mathematical models and numerical algorithms, approaches to building community codes for HPC systems, and methodologies and tools relevant for Big Data applications.