School of Computer Science - IPM School of Computer Science - IPM Institute for Studies in Theoretical Physics and Mathematics (IPM)
   
Search SCS
About us
People
Research
Getting a Grant
Publications
Useful Links
Events and News
Search
IPM Home Page
Contact us
 
 
 
» HOME»IPM workshop on GPU programming
 

IPM One day Workshop on

GPU programming

Introduction

Parallel algorithms executing on clusters can be ported to GPUs and reap massive performance gains. The availability of global shared memory on GPU chipsets makes it also possible to leverage on complex parallel designs with high intern-node communication to execute tasks such as matrix multiplication in CUBLAS. CUDA is NVIDIA's revolutionary parallel computing architecture that is built up on a unified Computing architecture and multiple software components. The architecture consists of an ISA and hardware compute engine. The available software tools include a C compiler and NVIDIA drivers for developers to build applications using C for CUDA, as well as useful libraries for high-performance computing (BLAS, FFT, etc.).

On Thursday, Khordad 6th, 1389 (Thursday, May 27, 2010) the IPM School of Computer Science will host One-day workshop on GPGPU programming. It will provide an introduction to the CUDA architecture, programming model, and the programming environment of C for CUDA, as well as an overview of the NVIDIA GPU (Geforce) )architecture, a live programming demo, and strategies for optimizing CUDA applications for the GPU. The workshop will also include a brief presentation of some of the projects using CUDA within the IPM School of computer sciences, and of the hardware requirements for getting started with CUDA.

Registration (closed)

Total number of attendees is limited to 60. If there are more registrants, we will select 60 persons according to their background and field of study.

Registration fee:

1) IPM members (must be registered by IPM email) - 100,000 Rials

2) University students (must be registered by university emails)- 200,000 Rials

3) others - 1000,000 Rials

Account Information:

Account No: 217-214-900-1-004 (بانك ملي - سيبا)

Account Holder: Institute for Research in Fundamental Sciences (پژوهشگاه دانشهاي بنيادي)

*** Attention: The grant is finsihed.

 

Organizing Committee

  • Dr. Hamid Sarbazi-Azad (IPM School of Computer Science and Sharif University of Technology)
  • Dr. Ahmad Khonsari (IPM School of Computer Science and University of Tehran)
  • Dr. Abbas Nayebi (IPM School of Computer Science)
  • Hassan Eslami (IPM School of Computer Science and Sharif University of Technology)
  • Seyed Farhad Kazemi (IPM School of Computer Science and University of Tehran)
  • Sina Keshtkar Jafari (IPM School of Computer Science and Sharif University of Technology)
  • Mohammad Hasan Khabbazian (IPM School of Computer Science and Sharif University of Technology)
  • Ahmadreza Khadem(IPM School of Computer Science and Sharif University of Technology)
  • Masoud Rahimi Ghazi Kalayeh (IPM School of Computer Science and University of Tehran)
  • Mehdi Rezaei (IPM School of Computer Science)
  • Hamid Reza Shahrabi (IPM School of Computer Science)
  • Amirhesam Shahvarani (School of Computer Science and University of Tehran)
  • Amir Shaikhha (IPM School of Computer Science and Sharif University of Technology)
  • Ali Shirvani (IPM School of Computer Science and University of Tehran)
  • Arash Tavakkol (IPM School of Computer Science)
  • Ehsan Totoni (IPM School of Computer Science and Sharif University of Technology)

 

Prerequisites

  • Attendees need to be familiar with:
    • either C or C++ programming
    • Linux/Shell
    • (Recommended) Matlab

Workshop Requirements

  • Each attendee, or at most two, need to bring their laptop with a wireless modem and a installed version of a SSH Client program (You can download Putty for Windows XP/Vista/7 here)

Date & Venue

Date: Thursday, 1389/03/06 (Thursday, May 27th, 2010)
Time: 8:30 - 18:00
Address: Hall 1, Institute for Research in Fundamental Sciences, Shahid Bahonar (Niavaran) Sq., Niavaran, Tehran, Iran

Contact

Email: khadem (- at -) ipm .ir
Tel: +98 912 554 3560


Time Table


8:30 - 9:00 Registration & Technical Checking
9:00 - 9:15 Dr. Abbas Nayebi Workshop Opening Talk
9:15 - 10:30

Arash Tavakol ,

Masoud Rahimi Ghazi Kalayeh

Introduction to GPU & installation
  • HPC technologies
  • Intoruction to GPU hardware
  • Introduction to CUDA
  • Set-up a GPU system
  • installing toolkit & driver
10:30 - 11:00 Break
11:00 - 12:40

Ehsan Totoni,

Sina Keshtkar Jafari

intoroction to programming GPU in c
  • Introduction to CUDA programming model
  • Compile Simple CUDA program
  • Some basic programs for CUDA and compare results
12:40 - 14:00 Lunch
14:00 - 15:30 Amir Hesam Shahvarani, Ehsan Totoni Architecture
  • GPU hardware and programming model
  • Memory hierarchy and optimization
15:30 - 16:00 Break
16:00 - 17:40

Ahmadreza Khadem,

Seyed Farhad Kazemi

MATLAB and CUDA
  • Introduction to MATLAB applications in science
  • Acceleration MATLAB with CUDA mex
  • Example on Nvidia CUDA mex - advanced example on CUBLAS, CUFFT
  • Introduction to JACKET
  • intorduction to GPUMAT
  • Wrap-up
 

 



 IPM HOMEPAGE | IPM LIBRARY

© Copyright 2000-2009 
Institute for Research in Fundamental Sciences (IPM)
All rights reserved.
  Please submit your comments or questions here, or contact Webmaster.