[LA-SiGMA] HPC Training: Numerical Libraries

[Alexander Pacheco]

Dear All,

The next HPC training will be held on Wednesday, Mar. 19 at 10:00 AM CDT 
in 307 Frey and broadcast through Adobe Connect for remote users.

Wednesday, Mar. 19, 2014: Numerical Libraries
Schedule:
Training Lecture: 10AM - 12:30 PM
Hands-On and Consultation: 1:30PM - 4PM
This training will cover serial and parallel libraries for better 
performance. Topics will include numerical, I/O and other useful 
libraries such as lapack (netlib, mkl), fftw, petsc, hdf5/netcdf. Some 
optimizations for mpi libraries and compilers will also be covered.
*Prerequisites*: /A LONI or LSU HPC account is required. Training 
accounts will be provided to in-class participants.//
/
Next HPC Training:
Wednesday, Mar. 26, 2014: Introduction to OpenACC
Schedule:
Training Lecture: 10AM - 12:30 PM
Hands-On and Consultation: 1:30PM - 4PM
OpenACC is a programming standard for parallel computing developed by 
Cray, CAPS, Nvidia and PGI. The standard is designed to simplify 
parallel programming of heterogeneous CPU/GPU systems. OpenACC is a 
directive based programming model to annotate C, C++ and Fortran source 
code similar to OpenMP Programming Model. This tutorial provides an 
introduction to the OpenACC programming model.
*Prerequisites*: /A LSU HPC account is required. Training accounts will 
be provided to in-class participants. *LONI users who are not eligible 
for LSU HPC resources will need to have access to a computer with GPU 
(Nvidia preferred) card and PGI compiler with OpenACC support*. 
Programming background in C/C++ or Fortran is required. Experience with 
OpenMP programming model is preferred but not required./

Wednesday, April. 2, 2014: CUDA Programming
Schedule:
Training Lecture: 10AM - 12:30 PM
Hands-On and Consultation: 1:30PM - 4PM
This tutorial is a basic introduction to programming GPUs using Nvidia's 
programming environment. Basics of the GPU architecture and CUDA C 
programming language will be covered. Some simple examples demonstrating 
basic techniques for getting greater performance out of GPUs will also 
be discussed.
*Prerequisites*: /A LSU HPC account is required. Training accounts will 
be provided to in-class participants. *LONI users who are not eligible 
for LSU HPC resources will need to have access to a computer with GPU 
(Nvidia preferred) card and CUDA compiler*. Programming background in 
C/C++ (preferred) or Fortran is required. No prior experience with GPU 
is required./

Please visit http://www.hpc.lsu.edu/training/tutorials.php for more 
details and register using the link provided.

Please see the system requirements for Adobe Connect at 
http://connect.grok.lsu.edu/Categories.aspx?parentCategoryId=1519.

Please distribute to faculty, staff and students that might be 
interested in these trainings.

Thanks,
Alex

-- 
Alexander Pacheco, Ph. D.
IT Analyst 3
LSU - HPC & LONI
Louisiana State University
Baton Rouge, LA 70803
http://www.cct.lsu.edu/~apacheco

-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mail.loni.org/mailman/private/lasigma/attachments/20140317/ea80ce5c/attachment.html