PUMPS

PUMPS 2011

  • The 2011 attendees say hi and would like you consider coming to next PUMPS

PUMPS Summer School, July 18-22, 2011

PUMPS in a Nutshell

- Dates:
Applications due: May 31
Summer school: July 18-22, 2011
- Instructors:
Wen-mei Hwu, University of Illinois
David B. Kirk, NVIDIA Corporation
- Audience:
Parallel tracks specially designed for beginners and advanced profiles
- Programming Languages:
CUDA, MPI, OmpSs, OpenCL
- Hands-on Labs:
Afternoon labs with teaching assistants for each audience/level
- Poster session:
Share your research results and get feedback at a poster session
- Programming contest:
Compete and win the Best Achievement Award
- Spread the news: PUMPS Flyer

Textbook discount for attendees!

The Programming and Tuning Massively Parallel Systems Summer School (PUMPS) is aimed at enriching the skills of researchers, graduate students and teachers with cutting-edge technique and hands-on experience in developing applications for many-core processors with massively parallel computing resources like GPU accelerators.

  • Location: Barcelona Supercomputing Center, Computer Architecture Dept. at Universitat Politecnica de Catalunya, Barcelona, Spain

The summer school is organized into two main tracks according to the attendees' knowledge, expertise and interest levels:

  • Tracks:
    • Beginners Track: The Beginners Track starts off with introductory lectures to multiprocessor programming and CUDA, covering topics such as the CUDA threading model and CUDA memory model.
    • Advanced Track: The Advanced Track continues the topics from the Beginner's track and focuses on optimizations and tuning of scientific and engineering applications; CUDA Performance Considerations; Debugging and Profiling CUDA Code; CUDA Algorithm Patterns, etc.
    • Separated hands-on lab sessions will be arranged for both tracks, adjusting the examples to the level of knowledge of each group.
  • Topics:
    • The full list of topics covered during the course is:
      • Many-core & Memory Organization
      • Introduction to CUDA
      • Threading and Memory Model
      • Performance Considerations
      • Hands-on Lab: CUDA examples
      • CUDA Algorithm Patterns
      • Debugging and Profiling CUDA Code
      • Hands-on Lab: Advanced Exercises
      • New Hardware and Software/SDK/Tool Features
      • GMAC Runtime
      • Multi-GPU Execution
      • Hands-on Lab: GMAC and Multi-GPU
      • CUDA with MPI / OmpSs for HPC Applications
      • Algorithmic Optimization Strategies
      • Hands-on Lab: Algorithmic Optimization
  • Summer School Co-Directors: Mateo Valero (BSC and UPC) and Wen-mei Hwu (University of Illinois at Urbana-Champaign)
  • Local Organizer: Nacho Navarro (BSC and UPC)
  • Organized by:
    • Barcelona Supercomputing Center (BSC)
    • University of Illinois at Urbana-Champaign (University of Illinois)
    • Universitat Politecnica de Catalunya (UPC)
    • HiPEAC Network of Excellence (HiPEAC)
    • Distinguished Teachers: Wen-mei Hwu (Sanders III-Advanced Micro Devices Endowed Chair in Electrical and Computer Engineering in the Coordinated Science Laboratory of the University of Illinois at Urbana-Champaign) and David Kirk (NVIDIA Fellow, former Chief Scientist, NVIDIA Corporation )
    • UIUC and BSC: Isaac Gelado
    • BSC and UPC: Rosa M. Badia, Alex Duran, Xavier Martorell, Nacho Navarro
    • Teaching Assistants: Javier Cabezas, Marc Jorda, Judit Planas, Diego Caballero
  • Dissemination: PUMPS Flyer


471x110.swf

Overview

  • Instructors Wen-mei Hwu (University of Illinois) and David B. Kirk (NVIDIA), co-authors of “Programming Massively Parallel Processors, A Hands-on Approach”, will provide students with knowledge and hands-on experience in developing applications software for many-core processors, such as general purpose graphics processing units (GPUs).
  • Prerequisites for the course are: C, C++, Java, or equivalent programming knowledge. Some knowledge of parallel programming will be helpful. An optional tutorial on GPU architecture will be offered on the first day of the summer school.
  • By the end of the summer school, participants will:
    • Understand algorithm styles that are suitable for accelerators.
    • Understand the most important architectural performance considerations for developing applications.
    • Be exposed to computational thinking skills for accelerating applications in science and engineering.
    • Engage computing accelerators on science and engineering breakthroughs.
  • Participating students will have access to a multinode cluster of GPUs, and will learn to use CUDA to write programs for the cluster.
  • Participants are expected to bring their own laptops to access the servers with GPU accelerators.
  • The afternoon lab sessions will provide hands-on experience with various languages and tools covered in the lectures and will comprise a brief introduction to the programming assignments, followed by independent work periods. Teaching assistants will be available in person and on the web to help with assignments.
  • Dates:
    • Applications due: May 31, 2011
    • Notification of acceptance: June 15, 2011
    • Summer school: July 18-22, 2011
  • Location: BSC/UPC, Campus Diagonal Nord, Building C6 (Computer Architecture Department), Barcelona, Spain
  • Programming Languages: CUDA, MPI, OmpSs, OpenCL
  • Hands-on Labs: Afternoon labs with teaching assistants for each audience/level
  • Application: Please apply to the summer school by submitting the application form
start.txt · Last modified: 2014/05/29 14:38 by admin