Graduate students can gain computational skills at two summer schools
 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, and
select university campuses in the Midwest.
 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, at NCSA. 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, and 
several other
 university campuses in the Midwest.
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 for 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: 
[log in to unmask]