Deliver Your News to the World

NVIDIA Names University of Tennessee a CUDA Center of Excellence


WEBWIRE

Leading University and Research Institution Joins Network of Seven Other Institutions Focused on Parallel Computing.

SANTA CLARA, Calif.— NVIDIA Corp. today recognized the University of Tennessee, Knoxville’s (UTK’s) Innovative Computing Laboratory (ICL) as a CUDA Center of Excellence, noting its adoption of the CUDA programming model in its curriculum, as well as its pioneering research into the development of linear algebra libraries for the high-performance computing community.

UTK joins a select group of seven universities and research organizations in the U.S. and abroad, including Harvard University, Cambridge University and National Taiwan University, that are designated as a CUDA Center of Excellence. More than 200 universities worldwide teach the CUDA programming model within their curriculum.

CUDA is NVIDIA’s computing architecture that enables its GPUs to be programmed using industry standard programming languages and APIs, opening up their massive parallel processing power to a broad range of applications beyond graphics.

“This award of a CUDA Center of Excellence underscores ICL’s commitment to continue our work at the forefront of high performance, scientific computing, ” said Jack Dongarra, ICL’s director. “We are very proud of this award and excited by the opportunity it affords to pursue our research on NVIDIA’s ground breaking platform"

Mathematical algorithms are an essential component used by computers to perform linear algebra computations, and ICL’s years of experience in developing open source, mathematical software packages and systems such as LAPACK, ScaLAPACK, ATLAS, and PLASMA will be extended by the establishment of this new center. In particular, ICL’s work on Matrix Algebra for GPU and Multicore Architectures (MAGMA), whose goal is to create a new generation of linear algebra libraries that dramatically cut processing times using hybrid GPU-CPU co-processing systems, will be an area of focus.

"NVIDIA technologies are now well established in the forefront of general purpose, parallel computing. Our work on the development of Linear Algebra Libraries for CUDA-based Hybrid Architectures will further enable and expand these technologies in the general area of high-performance scientific computing. MAGMA, a subset of LAPACK for CUDA-based Hybrid Architectures, is only a first step in this direction,” added Dongarra.

The potential size of the communities impacted by the success of this new CUDA Center of Excellence is significant. A partial listing of the peta-scale ready applications that rely on the kind of dense and sparse linear algebra that the MAGMA libraries will encode includes: quantum chemistry, multi-physics supernova simulation, nano-materials, geophysics, computational mechanics, electronic structure of matter and fluid dynamics.



WebWireID107120





This news content was configured by WebWire editorial staff. Linking is permitted.

News Release Distribution and Press Release Distribution Services Provided by WebWire.