Come for Table discussions, Member Self-Intro, What's New, Application Showcase, and Advanced Application Development Techniques! Exchange ideas, meet experts, share code... all HPC & GPU, all practical, all cutting-edge.
Refreshments generously sponsored by Colfax.
Presentation: CUDA Linear Algebra Libraries: cuBLAS and cuSPARSE
Speaker: Philippe Vandermersch
A few words about Philippe:
“I've been software manager of the cuBLAS and cuSPARSE CUDA libraries at NVIDIA since 2009. Previously I was a video architect at NVIDIA for 4 years. Prior to NVIDIA, I worked at Equator Technologies, Siemens ICN and Sercel Inc. I am the inventor of two patents in VOIP conference technology and hold an engineering degree from the Institut National Des Telecommunications in France.”
The cuBLAS (CUDA Basic Linear Algebra Subroutines) library is a GPU-accelerated version of the complete standard BLAS library. The cuSPARSE (CUDA Sparse Matrix) library provides a collection of basic linear algebra subroutines used for sparse matrices.
Carnegie Mellon Silicon Valley;
NASA Research Park Bldg 23;
Mountain View, CA 94043;
Directions to Carnegie Mellon Silicon Valley;
Google Map showing parking, check point, and building entrance;
NOTE: You will need a government issued ID (e.g. Driver's License) to enter NASA Research Park