Monday, 29 July, 2013
Graduate students, post-docs and professionals from academia, government and industry are invited to enroll in a summer school course on Proven Algorithmic Techniques for Many-core Processors offered by the Virtual School of Computational Science and Engineering and presented at UT Knoxville and other sites across the country July 29 through Aug. 2. The course is free at UT, with the stipulation that attendees register two weeks in advance of the course. This virtual course will be delivered to sites nationwide using high-definition videoconferencing technologies. The location for the course at UT Knoxville will be the virtual classrooms on the lower level of the Communications and University Extension building from 10 a.m to 6 p.m.
The Proven Algorithmic Techniques for Many-core Processors Summer School will present students with the seven most common and crucial algorithm and data-optimization techniques to support successful use of GPUs for scientific computing.
By studying many current GPU computing applications, the course instructors have learned that the limits of an application's scalability are often related to some combination of memory bandwidth saturation, memory contention, imbalanced data distribution or data-structure/algorithm interactions.
Successful GPU application developers often adjust their data structure and problem formulation specifically for massive threading and execute their threads leveraging shared on-chip memory resources for bigger impact.
The techniques presented in the course can improve performance of applicable kernels by 2 to 10X in current processors while enhancing future scalability.
In addition to UT Knoxville, other participating sites for the Proven Algorithmic Techniques for Many-core Processors summer school are Clemson University, Louisiana State University, Marshall University, Michigan State University, Princeton University, Purdue University, University of California Los Angeles, University of Delaware, the National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign, University of Texas at Brownsville, University of Texas at El Paso and University of Utah.
Registration is accomplished by visiting the user portal for the eXtreme Science and Engineering Discovery Environment (XSEDE). First-time users of the XSEDE portal must follow the guidelines to create a free portal account before being able to sign up for the Virtual School courses. Upon creating an XSEDE portal account, users can sign up for Virtual School courses through the XSEDE course calendar.
More information about the Virtual School can be viewed here. Questions about the summer school can be sent to firstname.lastname@example.org.