Graduate students from all disciplines and institutions across the country can learn more about scaling applications for emerging petascale computing systems and using many-core graphics processors to accelerate applications during two FREE summer school courses offered by the Virtual School of Computational Science and Engineering.
The Scaling to Petascale course will be Aug. 3-7, 2009. High-definition streaming video of the course will enable students to participate from multiple locations, including the University of Illinois' National Center for Supercomputing Applications (NCSA), the National Institute for Computational Sciences (NICS) in Oak Ridge, Tennessee, the University of Michigan, and Louisiana State University.
Participating students will have access to high-performance computing systems at NCSA, NICS, and the Texas Advanced Computing Center.
Prerequisites for the course are: Fortran, C, C++, Java, or equivalent scientific programming knowledge, experience developing and running scientific codes on a cluster or grid computing environment, and experience working in a Unix environment. Preference will be given to students with parallel programming experience.
For full information on the course and to apply, see: http://www.greatlakesconsortium.org/events/scaling/. Applications will be accepted online until May 18. Applicants will be notified by June 15.
A second course on Many-Core Programming for Science and Engineering Applications will be Aug. 10-14, 2009. Instructors Wen-mei Hwu (University of Illinois) and David B. Kirk (NVIDIA) will provide students with knowledge and hands-on experience in developing applications software for many-core processors, such as general purpose graphics processing units (GP-GPUs).
High-definition streaming video of the course will enable students to participate from multiple locations, including the University of Illinois' National Center for Supercomputing Applications (NCSA), the University of Michigan, Ohio State University and the University of Illinois, Chicago.
Participating students will have access to NCSA's 32-node cluster of GP-GPUs, and will learn to use CUDA to write programs for the cluster.
Prerequisites for the course are: C, C++, Java, or equivalent programming knowledge. Some knowledge of parallel programming will be helpful. An optional tutorial on GPU architecture will be offered on the first day of the summer school.
For full information on the course and to apply, see: http://www.greatlakesconsortium.org/events/manycore/. Applications will be accepted online until May 18. Applicants will be notified by June 15.
There is no fee for the summer school courses and lunches will be provided, but participants are responsible for their own travel and lodging costs.
The Virtual School of Computational Science and Engineering leads the graduate education effort for the National Science Foundation-funded Blue Waters project. NCSA is collaborating with IBM and the Great Lakes Consortium for Petascale Computation to build and deploy Blue Waters, a supercomputer that will deliver sustained performance of one petaflop on a range of science and engineering applications when it comes online in 2011. The Virtual School helps prepare the next generation of computational researchers so they can take full advantage of Blue Waters and other emerging petascale resources.
Questions about the summer school courses can be sent to: firstname.lastname@example.org.
story posted 04.28.09