[LA-SiGMA-TESC] TESC (Technologies for Extreme Scale Computing) seminar on Thursday (9/10)

[Wei P Feinstein]

Dear all,


Technologies for Extreme Scale Computing (TESC) bi-weekly seminar will start this Thursday (9/10) at 12:00pm-1:00pm in 1034 Digital Media Center. TESC seminars are intended to provide a platform  for exchanging ideas and establishing collaborations, especially in code development using HPC.  As in previous seminars, students and researchers from different disciplines have come together working on various projects. We are grateful for the support of the High Performance Computing, Computational Biology, LA_SiGMA, Center for Computation and Technology, and Louisiana Optical Network Initiative.


David Koppelman, an associate professor at Division of Electrical and Computer Engineering, will give a presentation. The title is "Model-Driven Kernel Fission: One Step Closer to Robot Takeover".


Abstract:

Chemora is a system for generating accelerated computing cluster code simulating systems that are described by differential equations written in Chemora's Equation Description Language (EDL). Chemora build-time components generate a set of calculations from the EDL. Calculations update array elements based on nearby array elements, what's called a stencil pattern. A challenge for Chemora is generating GPU code for these calculations. Mapping an entire calculation to one CUDA kernel would leave little storage for array buffering, and so performance potential would be unrealized in these high re-use, memory intensive codes. Splitting calculation based on some convenient but oblivious criterion might provide plenty of buffering storage but would result in a large number of kernels and with them a large kernel-launch overhead. In the talk the representation of a calculation will be discussed, as will the performance model, optimization, and PTX code generation.


PIZZA AND DRINK WILL BE PROVIDED.

Presentation time: 12:00PM~1:00PM CST
Location: 1034 Digital Media Center

The meeting will be shared through adobe connect at http://connect.lsu.edu/gpu/


Best,

Wei


Wei Feinstein, Ph.D.
High Performance Computing
Louisiana State University
337 Frey Computing Services Center
Baton Rouge, LA  70803
Office 225-578-0582 | Mobile 251-599-3814
wfeinstein at lsu.edu<mailto:wfeinstein at lsu.edu> | lsu.edu<http://lsu.edu> | hpc.lsu.edu<http://hpc.lsu.edu>

LASiGMA-gpu mailing list
LASiGMA-gpu at loni.org<mailto:LASiGMA-gpu at loni.org>
https://mail.loni.org/mailman/listinfo/lasigma-gpu
wiki: https://wiki.cct.lsu.edu/la-sigma/
http://www.institute.loni.org/lasigma/lasigma-gpu.php

-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mail.loni.org/mailman/private/lasigma-gpu/attachments/20150908/b8b03a4b/attachment.html