CS6596 High-Performance Parallel Computing

GIAN course
Instructors: P. Sadayappan and Rupesh Nasre.
TA: Jyothi Krishna V S
Dates: June 20 -- July 1, 2016
Venue: MSB 360, IIT Madras

Home | Evaluation | Lectures

The course is intended to be of interest to both computer scientists as well as computational scientists who use high-performance computing in their work. It will cover parallel programming for shared-memory multiprocessors and GPUs, as well as the fundamental performance issues with these systems. It would help the attendees learn the issues involved in creating high-performance parallel software.

Topics:

  • Caches and locality, Loop transformations, Data dependence analysis, Performance modeling
  • OpenMP review, OpenMP performance optimization, OpenMP case studies
  • GPU programming, GPU performance issues, GPU case studies
  • Irregular algorithms, Vectorization, Intel Xeon Phi case studies

Course Registration:
click here for GIAN registration portal. The registration requires Rs.500 for the GIAN portal (to be paid online) and then additional following fees for the course to be paid by demand draft.

  • Student Participants: Rs.2000
  • Faculty Participants: Rs.5000
  • Government Research Organization Participants: Rs.5000
  • Industry Participants: Rs.10000
The above fee is towards participation in the course, the course material, computer use for tutorials and assignments, and laboratory equipment usage charges. Follow these steps towards the payment.
  1. Get a demand draft from your bank of the correct amount in favor of Registrar, IIT Madras.
  2. Hand over or post the demand draft to Rupesh Nasre, CSB 11, CSE Department, IIT Madras, Chennai -- 600036.
  3. Email rupesh0508@gmail.com mentioning about handing over / posting the demand draft.

Accommodation
The student and faculty participants from other institutes who want accommodation will be provided the hostel accommodation on payment basis. These participants have to apply for the hostel accommodation through the link: http://hosteldine.iitm.ac.in/iitmhostel. The lodging and boarding charges are to be paid by the participants. The course registration fee does not include the boarding and lodging charges.

Acknowledgment
We thank Prof. C Chandra Sekhar for coordinating the course for GIAN from IIT Madras.

Instructors
Prof. Sadayappan is a Professor in the Department of Computer Science and Engineering at The Ohio State University. His primary research interests center around performance optimization and compiler/runtime systems for high-performance computing, with special emphasis on high-performance frameworks that enable high productivity for application developers in scientific computing. Two recent projects include a polyhedral framework for automatic parallelization and data locality optimization, and the Tensor Contraction Engine – a domain-specific compiler/runtime system to automatically transform high-level specifications into efficient parallel programs, for a class of high accuracy ab initio models in quantum chemistry.
Rupesh Nasre is a faculty member at the Department of Computer Science and Engineering at IIT Madras. His primary research interests are in compilers and parallelization. In particular, he has been exploring parallelization of graph algorithms on multi-core as well as GPUs. Towards improving productivity of end-users, he has developed a domain-specific language for graph algorithms, in collaboration with other researchers. He is a recipient of NVIDIA Special Prize, has won Yahoo! HackU Award, and holds five US patents.