High Performance Computing with Accelerators

Sri Sathya Sai Institute of Higher Learning, Prashanthi Nilayam, Puttaparthi

SSSIHL Website

Home | Schedule | Piazza | Student Work

Attention

This course was highly successful resulting in 9 student papers, more than one third of the total papers, accepted for Student Research Symposium, at HiPC 2012. And also, 3 out of the 4 awards constituted for Best Presentation and Best Poster were secured by the students of this course.

Description

This course examines an important trend in high-performance computing, the use of special-purpose hardware originally designed for graphics and games to solve general-purpose computing problems. Such graphics processing units (GPUs) have enormous peak performance for arithmetically-intensive computations, and at relatively low cost as compared to their general-purpose counterparts with similar performance levels. Technology trends are driving all microprocessors towards multiple core designs, and therefore, techniques for parallel programming represent a rich area of recent study. Students in the course will learn how to develop scalable parallel programs targeting the unique requirements for obtaining high performance on GPUs and multi-cores. We will compare and contrast parallel programming for GPUs and conventional multi-core microprocessors.

Prerequisites

• Programming for Performance
• MATH 704 : Introduction to Computer Architecture.
• Strong C Skills

Instructor

Prof. Pallav Kumar Baruah ,pkbaruah@sssihl.edu.in
Office: DMACS

Sudheer Kumar , cdsudheerkumar@sssihl.edu.in
Office: AI Lab

Ajith Padyana , ajithpadyana@sssihl.edu.in
Office: AI Lab
Office Hours: Monday - Friday, 3:00-4:00 pm

Meeting

Online

• Google Group: techsuns, techsuns@googlegroups.com
  
• GitHub Organization: dmacssite

Books

• Programming Massively Parallel Processors, 2010, David Kirk and Wen-mei Hwu. Old draft pdfs are on the website for ECE 498 AL at UIUC.

Grading

• Homeworks: 30%
• Student Presentation: 20%
• Final Project: 40%
• Final: 10%

Lab Resources

• Access to nVIDIA S2050 blade provided by nVIDIA under the aegis of nVIDIA Professor Partnership program
• Materials from GTC
• XSEDE
  1. Forge Supercomputing system
  2. Gordon Supercomputing system
  3. Trestles Supercomputing system

Important Conferences in HPC

• SuperComputing Conference (SC)
• International Parallel and Distributed Processing Symposium (IPDPS)
• High Performance Computing Conference (HiPC)
• GTC Conference