L1 - CSCI 503 Parallel Programming Lecture 1 Introduction...

Info iconThis preview shows pages 1–13. Sign up to view the full content.

View Full Document Right Arrow Icon
CSCI 503 Parallel Programming Lecture 1: Introduction Bob Lucas and Jacque Chame {rflucas,jchame}@isi.edu TAs: Manaschai Kunaseth and Nam Ma [email protected] & [email protected]
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Course Organization When: Mondays, 3:30 – 6:20 PM, THH208 Office hours: Mondays, 2:00 – 3:15 PM TA office hours: negotiable Course Objective: Learn how to think in parallel. Issues impacting safety and profitability of parallelism Discuss future of parallel computing and its impact Hands-on programming exercises Guest Lectures Experts when they are available Coverage when Jacque and I are not
Background image of page 2
Tentative Outline That Will Change! Introduction to parallel machines and programming models Locality and uniprocessor performance Threads and shared memory Global address space languages Message passing (MPI) MapReduce Parallel algorithms (2) Parallel I/O Data Parallelism (CUDA) Debugging and performance tools Heterogeneous systems Project presentations (2)
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Grading Class Participation Homework Late homework will be penalized Final Project Fractions To Be Determined
Background image of page 4
Assignments This is a class on parallel programming! Therefore, assignments will be to write parallel programs. Submissions will be in the form of source code and a makefile so the TAs can compile and run it. All submissions must also include a brief report discussing what you did, and any interesting things you learned in doing so. This will be true, even if we forget to explicitly mention it.
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Resources Your laptop USC’s HPC system Workstations with Nvidia GPUs
Background image of page 6
Today’s Lecture Topic: Introduction Motivation Reading: Textbook: Grama, A. Gupta, G. Karypis, and V. Kumar, Introduction to Parallel Computing , 2 nd Ed., Addison-Wesley, 2003 Read Chapter 1
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Sources of Material Jack Dongarra, Tennessee, CS 594 Vivek Sarkar, Rice, COMP 4 Kathy Yelick, UC Berkeley, CS 267 Mary Hall, USC, CS 503 Mark Horowitz, Stanford, CANDE talk
Background image of page 8
01/15/2008 CS503-Lecture 1 5 Format of Lectures • 2 hours and 50 minutes is a long time! -For me you • After roughly 75 minutes, a short break • Following the break, some “light” technical discussion - Current parallel computing events - Go over current assignment • And then back to work for another hour
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
01/15/2008 CS503-Lecture 1 6 Discussion and Assessment 1. Have you ever written a parallel program? What language or programming model did you use? 2. Why are you interested in parallel programming? 3. What parallel applications are of interest to you? 4. What makes parallel programming challenging?
Background image of page 10
01/15/2008 CS503-Lecture 1 7 Outline • Introduction • Large important problems require powerful computers (see text) - Computational Power -Memory/D isk Speed - Data Communication • Why powerful computers must be parallel processors - Including your laptop • A new direction for parallel applications • Why writing (fast) parallel programs is hard • Principles of parallel computing performance Thanks to Kathy Yelick and Jim Demmel (UC Berkeley) for many of today’s slides.
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
01/15/2008 CS503-Lecture 1 8 Parallel and Distributed Computing • Limited to supercomputers?
Background image of page 12
Image of page 13
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 86

L1 - CSCI 503 Parallel Programming Lecture 1 Introduction...

This preview shows document pages 1 - 13. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online