GLCPC - Great Lakes Consortium for Petascale Computation

Virtual School of Computational Science and Engineering

Summer School: Accelerators for Science and Engineering Applications: GPUs and Multicores

• Are you a chemistry graduate student who wants to run in one day the computational studies that take a whole year for your peers?
• Are you a computer engineering graduate student who would like to develop video games with authentic physics effects that can only be faked in current offerings?
• Are you a bioengineering graduate student whose medical imaging algorithms are too computationally intensive for current systems?

If so, then this summer school is for you.

High-performance computing is entering a new era with the emergence of petascale systems that will enable researchers to solve a new class of complex problems. To ensure these capabilities are available, researchers must develop new programming paradigms and advanced code development tools for science, engineering, digital arts and humanities, and a variety of interdisciplinary applications.

Furthermore, virtually all semiconductor product domains—including PCs, game consoles, mobile handsets, servers, supercomputers, and networks—are converging to parallel processors. Processors from NVIDIA, AMD, Intel, and IBM either are or soon will be massively parallel. Programming these processors will require in-depth knowledge about parallel programming principles, as well as the parallelism models, communication models, and resource limitations of these processors.

The target audience for this Virtual School summer school event includes graduate and doctoral students from all disciplines who want to use these processors for new and exciting applications projects, as well as those who want to develop programming tools and future designs of these processors. The goal is to provide students with knowledge and hands-on experience in developing applications software for processors with massively parallel computing resources. Students will learn about how to accelerate science and engineering applications using graphics processing units (GPUs) and multicore processors.

The summer school will include tutorials, hands-on programming assistance, lectures by experts, and a multidisciplinary panel discussion.

By end of the summer school participants will:

• Understand algorithm styles that are suitable for accelerators.
• Understand the most important architectural performance considerations to developing applications.
• Be exposed to computational thinking skills for accelerating applications in science and engineering.
• Gain ability to engage computing accelerators on science and engineering breakthroughs.

Because hands-on instruction is integral to the summer school, participation will be limited to 40 people. Please complete the online application form to be considered for a spot in the summer school.

There is no fee to participate, and all breakfasts and lunches will be provided for summer school participants. Attendees are responsible for their own travel and hotel arrangements (see Local Info), but are encouraged to seek support from their home institutions. Attendees are expected to bring their own laptops.

Prerequisite: C, C++, Java, or equivalent programming knowledge

Instructors: Wen-mei Hwu, Sanders-AMD Endowed Chair in Electrical and Computer Engineering, University of Illinois at Urbana-Champaign and David B. Kirk, chief scientist, NVIDIA Corporation

Footer

The Great Lakes Consortium for Petascale Computation (GLCPC) facilitates the widespread and effective use of petascale computing to address frontier research questions in science, technology, engineering, and mathematics at research, educational, and industrial organizations across the United States. The National Center for Supercomputing Applications, on behalf of the University of Illinois at Urbana-Champaign, is the lead institution for organizing and managing the GLCPC. © 2008 Board of Trustees University of Illinois.