NOTE: the most recent web site for COMP 322 is located here

 

COMP 322: Fundamentals of Parallel Programming (Spring 2011)

Instructor:

Prof. Vivek Sarkar, DH 3131

Graduate TA:

Sanjay Chatterjee 

 

Please send all emails to comp322-staff at rice dot edu

Graduate TA:

Raghavan Raman

 

 

Undergrad TA:

Christopher Nunu

Assistant:

Amanda Nokleby, akn3@rice.edu, DH 3137

Undergrad TA:

Max Grossman

 

 

Research Programmer:

Vincent Cave

Lectures:

Duncan Hall (DH) 1042

Time:

MWF 1:00-01:50pm

Labs:

Ryon 102

Times:

Tuesday 2:30-3:50pm (Sec 1), Wednesday 3:30-4:50pm (Sec 2)

Introduction

The goal of COMP 322 is to introduce you to the fundamentals of parallel programming and parallel algorithms, using a pedagogical approach that exposes you to the intellectual challenges in parallel software without enmeshing you in low-level details of different parallel systems.  To that end, the main pre-requisite course requirement is COMP 211 or equivalent.  This course should be accessible to anyone familiar with the foundations of sequential algorithms and data structures, and with basic Java programming.  COMP 221 is also recommended as a co-requisite.

The pedagogical approach will introduce you to the following foundations of parallel programming:

  • Primitive constructs for task creation & termination, collective & point-to-point synchronization, task and data distribution, and data parallelism
  • Abstract models of parallel computations and computation graphs
  • Parallel algorithms and data structures including lists, strings, trees, graphs, matrices
  • Common parallel programming patterns including task parallelism, undirected and directed synchronization, data parallelism, divide-and-conquer parallelism, map-reduce, concurrent event processing including graphical user interfaces. 

Laboratory assignments will explore these topics through a simple parallel extension to the Java language called Habanero-Java (HJ), developed in the Habanero Multicore Software Research project at Rice University.  The use of Java will be confined to a subset of the Java 1.4 language that should also be accessible to C programmers --- no advanced Java features (e.g., generics) will be used.  An abstract performance model for HJ programs will be available to aid you in complexity analysis of parallel programs before you embark on performance evaluations on real parallel machines.  We will conclude the course by introducing you to some real-world parallel programming models including the Java Concurrency Utilities, Google's MapReduce, CUDA and MPI.  The foundations gained in this course will prepare you for advanced courses on Parallel Computing offered at Rice (COMP 422, COMP 522). 
 
Since the aim of the course is for you to gain both theoretical and practical knowledge of the foundations of parallel programming, the weightage for course work will be balanced across written assignments, programming assignments, and exams.  Students interested in taking COMP 322 in Spring 2012 can find summary information here\.

Textbooks

There are no required textbooks for the class. You will be expected to read each lecture handout before coming to the lecture.  We will also provide a number of references in the slides and handouts.

However, there are a few optional textbooks that we will draw from quite heavily.  You are encouraged to get copies of any or all of these books.  They will serve as useful references both during and after this course:

Lecture Schedule

 

Day

Date (2011)

Topic

Handouts

Slides

Homework Assigned

Homework Due

1

Mon

Jan 10

Lecture 1: The What and Why of Parallel Programming

lec1-handout

lec1-slides

HW1 (Written Assignment)

 

2

Wed

Jan 12

Lecture 2: Task Creation & Termination using Async & Finish

lec2-handout

lec2-slides

 

 

3

Fri

Jan 14

Lecture 3: Computation Graphs, Abstract Performance Metrics

lec3-handout
(rev 1/14/2011)

lec3-slides

HW2 (Written Assignment)

HW1

-

Mon

Jan 17

School Holiday

 

 

 

 

4

Wed

Jan 19

Lecture 4: Futures --- Tasks with Return Values

lec4-handout

lec4-slides

 

 

5

Fri

Jan 21

Lecture 5: Parallel Array Sum and Array Reductions

lec5-handout

lec5-slides

 

HW2

6

Mon

Jan 24

Lecture 6: Data Races and How to Avoid Them

lec6-handout

lec6-slides

HW3 (Programming Assignment)

 

7

Wed

Jan 26

Lecture 7: Parallel Prefix Sum, Forall parallel loops

lec7-handout

lec7-slides

 

 

8

Fri

Jan 28

Lecture 8: Parallel Quicksort

lec8-handout
(rev 1/28/2011)

lec8-slides

 

 

9

Mon

Jan 31

Lecture 9: PRAM model, Amdahl's Law

lec9-handout

lec9-slides

 

 

10

Wed

Feb 02

Lecture 10: Critical sections and the Isolated statement

lec10-handout
(rev 2/3/2011)

lec10-slides

 

 

-

Fri

Feb 04

No Lecture, School closed due to inclement weather

 

 

 

 

11

Mon

Feb 07

Lecture 11: Abstract vs Real Performance, Work-sharing & Work-stealing schedulers

lec11-handout

lec11-slides

 

HW3

12

Wed

Feb 09

Lecture 12: Barrier Synchronization in Forall Loops

lec12and13-handout

lec12-slides

HW4 (Written Assignment)

 

13

Fri

Feb 11

Lecture 13: Barrier Synchronization in Forall Loops (contd)

lec12and13-handout

lec13-slides

 

 

14

Mon

Feb 14

Lecture 14: Point-to-point Synchronization and Phasers

lec14and15-handout

lec14-slides

 

 

15

Wed

Feb 16

Lecture 15: Point-to-point Synchronization and Phasers (contd)

lec14and15-handout

lec15-slides

 

HW4

16

Fri

Feb 18

Lecture 16: Guest Lecture on Bitonic Sort (John Mellor-Crummey)

 

lec16-slides

 

 

17

Mon

Feb 21

Lecture 17: Advanced Phaser topics

lec17-handout

lec17-slides

 

 

18

Wed

Feb 23

Lecture 18: Midterm Summary

 

lec18-slides

Midterm Exam (Take-home)

 

-

Fri

Feb 25

No lecture, Midterm Exam due today

 

 

 

Midterm Exam (Take-home)

-

M-F

Feb 28 - Mar 04

Spring Break

 

 

 

 

19

Mon

Mar 07

Lecture 19: Java Atomic Variables

lec19-handout

lec19-slides

 

 

20

Wed

Mar 09

Lecture 20: Java Concurrent Collections

lec20-handout

lec20-slides

 

 

21

Fri

Mar 11

Lecture 21: Linearizability of Concurrent Objects

lec21-handout

lec21-slides

HW5 (Written Assignment)

 

22

Mon

Mar 14

Lecture 22: Task Affinity with Places

lec22-handout

lec22-slides

 

 

23

Wed

Mar 16

Lecture 23: Task Affinity with Places, contd.

lec23-handout

lec23-slides

 

 

24

Fri

Mar 18

Lecture 24: Map Reduce

lec24-handout

lec24-slides

 

 

25

Mon

Mar 21

Lecture 25: Dataflow Programming and Data-Driven Futures

lec25-handout

lec25-slides

 

HW5

26

Wed

Mar 23

Lecture 26: Dataflow Programming with Intel Concurrent Collections

lec26-handout

lec26-slides

HW6 (Programming Assignment)

 

-

Fri

Mar 25

Midterm Recess

 

 

 

 

27

Mon

Mar 28

Lecture 27: Java Threads

lec27-handout

lec27-slides

 

 

28

Wed

Mar 30

Lecture 28: Java Threads (contd), synchronized statement

 

lec28-slides

 

 

29

Fri

Apr 01

Lecture 29: Java synchronized statement with wait/notify

 

lec29-slides

 

 

30

Mon

Apr 04

Lecture 30: Advanced locking in Java

 

lec30-slides

 

 

31

Wed

Apr 06

Lecture 31: Java Executors and Synchronizers

 

lec31-slides

 

HW6

32

Fri

Apr 08

Lecture 32: Volatile Variables and Java Memory Model

 

lec32-slides

HW7 (Programming Assignment)

 

33

Mon

Apr 11

Lecture 33: GPGPU programming with CUDA

lec33-handout

lec33-slides

 

 

34

Wed

Apr 13

Lecture 34: CUDA contd.

 

lec34-slides

 

 

35

Fri

Apr 15

Lecture 35: Liveness and Progress Guarantees

 

lec35-slides

 

 

36

Mon

Apr 18

Lecture 36: Introduction to MPI

 

lec36-slides

 

 

37

Wed

Apr 20

Lecture 37: Introduction to MPI (contd)

 

lec37-slides

 

 

38

Fri

Apr 22

Lecture 38: Course Summary

 

lec38-slides

Final Exam (Take-home)

HW7

-

Fri

Apr 29

 

 

 

 

Final Exam (Take-home)

Lab Schedule ||

Lab #

Date (2011)

Topic

Handouts

1

Jan 11, 12

Infrastructure setup

lab1-handout

2

Jan 18, 19

Abstract performance metrics with async & finish

lab2-handout

3

Jan 25, 26

Data race detection

lab3-handout

4

Feb 01, 02

Points, regions, forall loops

lab4-handout

5

Feb 08, 09

Abstract vs Real Performance, Work-sharing & Work-stealing schedulers

lab5-handout

6

Feb 15, 16

Barriers and Phasers

lab6-handout

-

Feb 22, 23

No lab (midterm week)

 

7

Mar 08, 09

Atomic Variables

lab7-handout

8

Mar 15, 16

Places

lab8-handout

9

Mar 22, 23

Data Driven Tasks

lab9-handout

10

Mar 29, 30

Java Concurrency I

lab10-handout

11

Apr 05, 06

Java Concurrency II

lab11-handout

12

Apr 12, 13

CUDA

lab12-handout

13

Apr 19, 20

MPI

lab13-handout

Grading, Honor Code Policy, Processes and Procedures

Grading will be based on your performance on homeworks (worth 50%) and exams (20% for first exam, and 30% for the second exam).

The purpose of the homeworks is to train you to solve problems and to help deepen your understanding of concepts introduced in class. Homeworks and programming assignments are due on the dates and times specified in the course schedule. Please turn in all your homeworks using the CLEAR turn-in system. Homework is worth full credit when turned in on time. A 10% penalty per day will be levied on late homeworks, up to a maximum of 6 days. No submissions will be accepted more than 6 days after the due date.

You will be expected to follow the Honor Code in all homeworks and exams.  All submitted homeworks are expected to be the result of your individual effort. You are free to discuss course material and approaches to problems with your other classmates, the teaching assistants and the professor, but you should never misrepresent someone else’s work as your own. If you use any material from external sources, you must provide proper attribution.  Take-home exams, which are pledged under the Honor Code, test your individual understanding and knowledge of the material. Collaboration on exams is strictly forbidden.  Finally, it is also your responsibility to protect your homeworks and exams from unauthorized access. 

The work you submit for this class is expected to be the result of your own work and that of your homework partner. You are free to discuss course material and approaches to problems with your other classmates, the teaching assistants and the professor, but you should never misrepresent someone else’s work as your own. If you use any material from online sources, you must provide proper attribution (as shown here) in your homework/programming assignment turnins. A tutorial on how and when to cite sources is here. You should explain what value you have added to work taken from online sources. Finally, it is also your responsibility to protect your work from unauthorized access. I will expect you to follow the Honor Code in this course.

Graded homeworks will be returned to you via email, and exams as marked-up hardcopies. If you believe we have made an error in grading your homework or exam, please bring the matter to our attention within one week.

Accommodations for Students with Special Needs

Students with disabilities are encouraged to contact me during the first two weeks of class regarding any special needs. Students with disabilities should also contact Disabled Student Services in the Ley Student Center and the Rice Disability Support Services.

  • No labels