CSS 434: Parallel and Distributed Computing - Spring 2011

CSS 434: Parallel and Distributed Computing
Spring 2011
TTh 330-535pm at UW1-041
Prof. Munehiro Fukuda

Professor:

Munehiro Fukuda <mfukuda@u.washington.edu>, room UW1-331, phone 352-3459, office hours: TTh 220-320pm

Course Description:

This course introduces the concepts and design of distributed computing systems. Topics covered include message passing, remote procedure calls, process management, migration, mobile agents, distributed coordination, distributed shared memory, distributed file systems, fault tolerance, and grid computing.

The first five weeks focus on the basic mechanism and the Java programming techniques for message passing, process management, and migration. We will use Java sockets, MPI: Message Passing Interface, Java RMI, and UWAgent: a Java-based mobile agent system the professor and his former CSS students have designed. The last five weeks discuss advanced topics, where the instructor will overview each topic; each student will review a topic-related research paper; and all of us will be involved in group discussions on those papers.

Four programming assignments are given: (1) A chat server design with Java sockets, (2) A parallel-computing application programming with MPI Java, (3) A functional/performance comaprison between Java RMI and UWAgent, and (4) A distributed file system implementation using Java RMI. A lab session is planned for each of the first three assignments to get familiar with sockets, MPI, and mobile agents.

Prerequisites:

CSS343.

Work Load and Grading:

Course Work Percentage Achievements Approximately Corresponding Numeric Grade
Program 1 7% 90s 3.5 - 4.0
Program 2 11% 80s 2.5 - 3.4
Program 3 7% 70s 1.5 - 2.4
Program 4 15% 60s 0.7 - 1.4
Paper Review 12%
Midterm Exam 20%
Final Exam 20%
Discussions 5%
Lab. Work 3%

Textbooks:

75% of the lecture covers the following textbook, while the rest focuses on some advanced topics such as MPI, mobile agents, and some research-oriented topics. To help your understanding, I recommend you should buy this textbook.
  1. Distributed Systems: Concepts and Design,, 4th Edition, George Coulouris, Jean Dollimore and Tim Kindberg, Addison-Wesley Publishers, 2005

References:

Some Programming Textbooks:

The following books and manuals are useful for system, network, and MPI programming.

Policies:

All programming assignments except program 4 and a paper review are to be done independently. Any collaboration of work will result in severe penalty. You may discuss the problem statement and any clarification with each other, but any actual work to be turned in, must be done without collaboration.
  1. Paper review: must be done by a team of two students.
  2. Program 4: may be done by a team of two students. If you work with a classmate, you must turn in a confidential evaluation of your partner. If you work independently, you will be awarded +5 extra credits.

Any homework is due at the beginning of class on the due date. The submission may be postponed only in emergencies such as accidents, sickness, sudden business trips, and family emergencies, in which case you may turn in yor homework late with a written proof. No make-up exams will be given except under exceptional circumstances. Barring emergencies, I must be informed before the exam.

To request academic accommodations due to a disability, please contact Disability Resources for Stuents (DRS) in UW1-175, (email: drs@uwb.edu, TDD: 425-352-5303, and FAX: 425-352-3581). If you have a documented disability on file with the DSS office, please have your DSS counselor contact me and we can discuss accommodations.

Course Goals:

The overall goal of CSS 434, "Parallel and Distributed Computing" includes: To strengthen your understanding of fundamental concepts, you are recommended to solve the problems that are given on the final page of each lecture slide, (while some of them will be solved in class discussions.). To review research papers, you must visit the library, search for them, and get prepared for presenting your paper review with the power point. Finally, you need to work in the Linux laboratory, (UW1-320) for testing and evaluating the performance of your distributed program. Therefore, as with most technical courses, besides ability and motivation, it takes time to learn and master the subject. Expect to spend an additional 10 to 15 hours a week outside of class time on the average.

Assignments:

This is a research-flavored course. Each assignment specificaiton only gives you a topic and a guideline in order to work on the assignment. The answer and the quality of assignment work just depend on your enthusiuasm for assignment work. Therefore, there are no specific key answers.
  1. Program 1 (pdf, word): learns how to use Java-based TCP communication through a design of chat client and server program.
  2. Program 2 (pdf, word): exercises how to write a parallel-computing application using MPI Java.
  3. Program 3 (pdf, word): compares RMI and mobile agenets in terms of programmability and performance. Click here to download the UWAgent manual.
  4. Program 4 (pdf, word): designs and implements a very simple distributed file system.
  5. Paper review:requires each student to review a notable research project and to present his/her understanding in the class.
Please read assignment.html to understand the environment you use for assignments and the submission/grading procedures.

Laboratory Work:

We have three laboratory assignments in that we will understand the usage of and programming with Java sockets, MPI, and mobile agents. They are intended to mitigate your learning curve of new programming paradigms and ease your programming work. The grading is based on your attendance.
  1. Lab Work 1: is a hands-on exercise for distributed computing with Java sockets. (1% of an entire grade)
  2. Lab Work 2: is a hands-on exercise for MPI programming. (1% of an entire grade)
  3. Lab Work 3: is a hands-on exercise for distributed computing with RMI and mobile agents. (1% of an entire grade)

Group Discussions:

We are planning to have five group discussions where the class will be divided into four groups, each discussing about a given topic and presenting the discussions in the class. Clik here for more detials.

Topics covered and tentative 434 winter schedule:

Note that this is an approximate ordering of topics. Chapters will take about the allotted time and not all sections in all chapters are covered.

Week Date Topics Lab and Discussions Chapters Reading Assignment
1 Mar 29 System Models   2
(2.1 - 2.3.2)		 pp29-57  
  Mar 31 Networking   3
(3.2 - 3.3.4, 3.4.1)		 pp69-81
pp89-94		 Program 1 assigned
2 Apr 5 Interprocess Communication Lab Work 1 (Sockets) 4
(4.1, 4.2, 4.3.2)		 pp131-144
pp148-150		  
  Apr 7 Group Communication and MPI   4.5, 12.4 pp164-168
pp484-498		  
3 Apr 12   Lab Work 2 (MPI)      
  Apr 14 Distributed Objects and Remote Invocation   5 pp177-219 Program 1 due
Program 2 assigned
4 Apr 19 Operating System Support   6 pp221-264  
  Apr 21 Process Migration   6.4.2, 2.2.3 pp231-234
pp37-42		  
5 Apr 26   Lab Work 3 (RMI and Agents)      
  Apr 28 Time and Global States   11 pp433-466 Program 2 due
Program 3 assigned
6 May 3 Midterm exam in class   2 - 6 pp29-57, 37-42, 69-81, 89-94, 131-144, 148-150, 164-168, 177-219, 221-264, and 484-498  
  May 5   Paper Review
Group Discussion 1		   Timewarp
SPEEDES
 Reviewer: Clapp
Reviewer: Kniest, Baker
7 May 10 Distributed Shared Memory   18 pp749-781  
  May 12   Paper Review
Group Discussion 2		   Ivy
Dash
Munin
Linda/JavaSpace
 Reviewer: Fukuda
Reviewer: Ow, Shirdavani
Reviewer: Bartlett-Schneider
Reviewer: Widjaja
8 May 17 Distributed File Systems   8,13
(8.1-8.4,13.5)		 pp323-358
pp545-549		 Program 3 due
Program 4 assigned
  May 19   Paper Review
Group Discussion 3		   Sun NFS
AFS
XFS
PVFS 		Reviewer: Wessels
Reviewer: Girodat, Dhaliwal
Reviewer: Zaretzke
Reviewer: Lentz
9 May 24 Distributed Transactions and Replication   14,15
(14.1-14.3, 15)		 pp565-578
pp603-656		  
  May 26   Paper Review
Group Discussion 4		   Gossip
Coda
GFS
Bayou
 Reviewer: Devara
Reviewer: Simonson
Reviewer: Creighton
Reviewer: Nguyen
10 May 31 Grid Computing
AgentTeamwork at UWB		   No corresponding chapters    
  Jun 2   Paper Review
Group Discussion 5		   NetSolve
Legion
Condor
Globus
CUDA
 Reviewer: Rohrbaugh
Reviewer: Dix
Reviewer: Eakins, Hermes
Reviewer: _____
Reviewer: Shmidt, Locke
11 Jun 7 Final exam in class   8, 11, 13-15, 18 and grid computing pp323-358, 433-466, 545-549, 565-578, 603-656, and 749-781  
  Jun 9 Program 4 Demonstration       Program 4 due (330pm)