• COMP322-Spring-2013
Skip to end of metadata
Go to start of metadata

COMP 322: Fundamentals of Parallel Programming (Spring 2013)

Instructor:

Prof. Vivek Sarkar, DH 3131

Graduate TA:

Kumud Bhandari

 

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

Graduate TA:

Deepak Majeti

Assistant:

Sherry Nassar, sherry.nassar@rice.edu, DH 3137

Graduate TA:

Sriraj Paul

  Graduate TA:Rishi Surendran

 

 

Undergrad TA:

Annirudh Prasad

Cross-listing:

ELEC 323

Undergrad TA:

Yunming Zhang

 

 

HJ consultants:

Vincent Cavé, Max Grossman, Shams Imam

Lectures:

Herzstein Hall 212

Lecture times:

MWF 1:00 - 1:50pm

Labs:

Ryon 102

Lab times:

Tuesday, 4:00 - 5:15pm (Section 3, TAs: Kumud Bhandari, Yunming Zhang)

 

 

 

Wednesday, 3:30 - 4:50pm (Section 2, TAs: Deepak Majeti, Sriraj Paul)

 

 

 

Thursday, 4:00 - 5:15pm (Section 1, TAs: Annirudh Prasad, Rishi Surendran)

Course Objectives

The goal of COMP 322 is to introduce you to the fundamentals of parallel programming and parallel algorithms, using a pedagogic approach that exposes you to the intellectual challenges in parallel software without enmeshing you in the jargon and lower-level details of today's parallel systems.  A strong grasp of the course fundamentals will enable you to quickly pick up any specific parallel programming model that you may encounter in the future, and also prepare you for studying advanced topics related to parallelism and concurrency in more advanced courses such as COMP 422.

To ensure that students get a strong grasp of parallel programming foundations, the classes and homeworks will place equal emphasis on advancing both theoretical and practical knowledge. The programming component of the course work will initially use a simple parallel extension to the Java language called Habanero-Java (HJ), developed in the Habanero Multicore Software Research project at Rice University.  Later in the course, we will introduce you to some real-world parallel programming models including Java Concurrency, .Net Task Parallel Library, MapReduce, CUDA and MPI. The use of Java will be confined to a subset of the Java language that should also be accessible to C programmers --- advanced Java features (e.g., wildcards in generics) will not be used. An important goal is that, at the end of COMP 322, you should feel comfortable programming in any parallel language for which you are familiar with the underlying sequential language; any parallel programming primitives should be easily recognizable based on the primitives studied in COMP 322.

Course Overview 

COMP 322 provides the student with a comprehensive introduction to the building blocks of parallel software, which includes the following concepts:

  • Primitive constructs for task creation & termination, synchronization, task and data distribution
  • Abstract models: parallel computations, computation graphs, Flynn's taxonomy (instruction vs. data parallelism), PRAM model
  • Parallel algorithms for data structures that include arrays, lists, strings, trees, graphs, and key-value pairs
  • Common parallel programming patterns including task parallelism, pipeline parallelism, data parallelism, divide-and-conquer parallelism, map-reduce, concurrent event processing including graphical user interfaces.

These concepts will be introduced in four modules: 

  1. Deterministic Shared-Memory Parallelism: creation and coordination of parallelism (async, finish), abstract performance metrics (work, critical paths), Amdahl's Law, weak vs. strong scaling, data races and determinism, data race avoidance (immutability, futures, accumulators, dataflow), deadlock avoidance, abstract vs. real performance (granularity, scalability), collective & point-to-point synchronization (phasers, barriers), parallel algorithms.
  2. Nondeterministic Shared-Memory Parallelism and Concurrency: critical sections, atomicity, isolation, high level data races, nondeterminism, linearizability, liveness/progress guarantees, actors, request-response parallelism
  3. Distributed-Memory Parallelism and Locality: memory hierarchies, cache affinity, false sharing, message-passing (MPI), communication overheads (bandwidth, latency), MapReduce, systolic arrays, accelerators, GPGPUs.
  4. Current Practice — today's Parallel Programming Models and Challenges: Java Concurrency, locks, condition variables, semaphores, memory consistency models, comparison of parallel programming models (.Net Task Parallel Library, OpenMP, CUDA, OpenCL); energy efficiency, data movement, resilience.

Prerequisite 

The prerequisite course requirement is COMP 215 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.  

Textbooks

There are no required textbooks for the class. Instead, lecture handouts are provided for each module as follows:

  • Module 1 handout (Deterministic Shared-Memory Parallelism)
  • Module 2 handout (Nondeterministic Shared-Memory Parallelism and Concurrency)
  • Module 3 handout (Distributed-Memory Parallelism and Locality)
  • Module 4 handout (Current Practice — today's Parallel Programming Models and Challenges)

You are expected to read the relevant sections in each lecture handout before coming to the lecture.  We will also provide a number of references in the slides and handouts.

There are also 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:

Quiz Schedule

  • Lab quizzes are usually published on Tuesday each week there is a lab, and are due by that Friday night. 
  • Lecture quizzes are usually published on Saturday each week and are due by the following Tuesday night.
    • Exception: combined lecture quiz for Week 5 and Week 6 will be assigned on Thursday, Feb 14, and due by Sunday, Feb 17, night 

Lecture Schedule

Week

Day

Date (2013)

Topic

Reading

Slides

Audio (Panopto)

Code Examples

Homework Assigned

Homework Due

1

Mon

Jan 7

Lecture 1: The What and Why of Parallel Programming

Module 1: Sections1.1, 1.2, 2.1, 2.2

lec1-slides

lec1-audio

ArraySum0.hj

 

 

 

Wed

Jan 9

Lecture 2: Async-Finish Parallel Programming, Data & Control Flow with Async Tasks, Computation Graphs

Module 1: Sections 1.3, 3.1, 3.2

lec2-slides

lec2-audio 

HW1, quicksort.hj

 

 

Fri

Jan 11

Lecture 3: Computation Graphs (contd), Parallel Speedup, Strong Scaling, Abstract Performance Metrics

Module 1: Sections 3.1, 3.2, 3.3lec3-slides ArraySum1.hj 

2

Mon

Jan 14

Lecture 4: Abstract Performance Metrics (contd), Parallel Efficiency, Amdahl's Law, Weak Scaling

Module 1: Sections 3.3, 3.4lec4-slideslec4-audioSearch2.hj  

 

Wed

Jan 16

Lecture 5: Data Races, Determinism, Memory Models

Module 1: Chapter 4lec5-slides    

 

Fri

Jan 18

Lecture 6: Data races (contd), Futures --- Tasks with Return Values

Module 1: Chapter 4, Section 5.1, 5.2lec6-slideslec6-audio   

3

Mon

Jan 21

No lecture, School Holiday (Martin Luther King, Jr. Day)

      

 

Wed

Jan 23

No lecture, Reading Assignment on Futures: Chapter 5 of Module 1 handout

Module 1: Chapter 5   

HW2, GeneralizedReduce.hj,

GeneralizedReduceApp.hj,

SumReduction.hj,

TestSumReduction.hj

HW1 (due by 5pm on Jan 23rd)

 

Fri

Jan 25

Lecture 7: Futures (contd), Parallel Design Patterns, Finish Accumulators

Module 1: Chapter 5, Chapter 6lec7-slides    

4

Mon

Jan 28

Lecture 8: Parallel N-Queens, Parallel Prefix Sum (Array Reductions with Associative Operators)

Module 1: Chapter 7lec8-slideslec8-audio   

 

Wed

Jan 30

Lecture 9: Abstract vs. Real Performance

Module 1: Chapter 9lec9-slideslec9-audio   

 

Fri

Feb 1

Lecture 10: Abstract vs. Real Performance (contd), seq clause

Module 1: Chapter 9lec10-slideslec10-audio   

5

Mon

Feb 04

Lecture 11: Forasync Loops, Forasync Chunking

Module 1: Sections 8.1, 9.4lec11-slides

   

 

Wed

Feb 06

Lecture 12: Forall Loops, Barrier Synchronization

Module 1: Sections 10.1, 10.2, 10.4lec12-slides   HW2 (due by 5pm on Feb 7th)

 

Fri

Feb 08

Lecture 13: Forall and Barriers, Dataflow Computing, Data-Driven Tasks

Module 1: Chapters 10, 11lec13-slideslec13-audio 

HW3, SeqScoring.hj, X.txt,

Y.txt, BigSeq.zip,

UsefulParScoring.hj, SparseParScoring.hj

 

6

Mon

Feb 11

Lecture 14: Recap of HJ constructs, Point-to-point Synchronization, Pipeline Parallelism, Introduction to Phasers

Module 1: Sections 12.1, 12.2lec14-slideslec14-audio   

 

Wed

Feb 13

Lecture 15: Point-to-point Synchronization with Phasers

Module 1: Section 12.3lec15-slides    

 

Fri

Feb 15

Lecture 16: Phaser Accumulators, Bounded Phasers, Summary of Barriers and Phasers

Module 1: Chapter 12lec16-slideslec16-audio   

7

Mon

Feb 18

Lecture 17: Midterm Summary

 lec17-slideslec17-audio   

 

Wed

Feb 20

Lecture 18: Midterm Summary (contd), Take-home Exam 1 distributed

 lec18-slides    

 

F

Feb 22

No Lecture (Exam 1 due by 5pm today)

     HW3 (due by 11:55pm on Feb 24th)

-

M-F

Feb 25- Mar 01

Spring Break

 

 

 

 

 

 

8

Mon

Mar 04

Lecture 19: Critical sections, Isolated statement, Atomic variables

Module 2: Chapters 1, 2, 4, 6lec19-slideslec19-audio  

 

 

Wed

Mar 06

Lecture 20: Parallel Spanning Tree algorithm, Monitors, Java Concurrent Collections

Module 2: Chapters 3, 7lec20-slideslec20-audio HW4, hw_4.zip

 

 

Fri

Mar 08

Lecture 21: Actors

Module 2: Chapter 8lec21-slideslec21-audio  

 

9

Mon

Mar 11

Lecture 22: Actors (contd), Linearizability of Concurrent Objects

Module 2: Chapters 8, 9lec22-slideslec22-audio

 

 

 

 

Wed

Mar 13

Lecture 23: Linearizability of Concurrent Objects (contd)

Module 2: Chapters 9, 10lec23-slideslec23-audio 

 

 

 

Fri

Mar 15

Lecture 24: Safety and Liveness Properties, Intro to Java Threads

Module 2: Chapters 11, 12lec24-slideslec24-audio

 

 

 

10

Mon

Mar 18

Lecture 25: Java Threads (contd), Java synchronized statement

Module 2: Chapters 12, 13, 14lec25-slides 

 

 

 

 

Wed

Mar 20

Lecture 26: Java synchronized statement (contd), advanced locking

Module 2: Chapter 14lec26-slides   

 

 

Fri

Mar 22

Lecture 27: Speculative parallelization of isolated blocks (Guest lecture by Prof. Swarat Chaudhuri)

 lec27-slides 

 

 

HW4 (due by 11:55pm on March 22nd)

11

Mon

Mar 25

Lecture 28: Java Executors and Synchronizers

 lec28-slideslec28-audio

 

 

 

 

Wed

Mar 27

Lecture 29: Dining Philosophers Problem

 lec29-slides 

 

 

 

-

Fri

Mar 29

Midterm Recess

      

12

Mon

Apr 01

Lecture 30: Task Affinity with Places

 lec30-slideslec30-audio HW5, hw_5.zip

 

 

Wed

Apr 03

Lecture 31: More on Actors: Places, Dining Philosophers (Guest lecture by Shams Imam)

 lec31-slides 

DiningPhilosopher.hj

 

 

 

Fri

Apr 05

Lecture 32: Message Passing Interface (MPI)

 lec32-slideslec32-audio

 

 

 

13

Mon

Apr 08

Lecture 33: Message Passing Interface (MPI, contd)

 lec33-slides   

 

 

Wed

Apr 10

Lecture 34: Message Passing Interface (MPI, contd)

 lec34-slides 

 

 

 

 

Fri

Apr 12

Lecture 35: Cloud Computing, Map Reduce

 lec35-slides 

 

 

HW5 (due by 11:55pm on Sunday, April 14th)

14

Mon

Apr 15

Lecture 36: Partitioned Global Address Space (PGAS) languages (Guest lecture by Prof. John Mellor-Crummey)

 lec36-slides  

HW6

 

 

Wed

Apr 17

Lecture 37: Comparison of Parallel Programming Models

 lec37-slides 

 

 

 

 

Fri

Apr 19

Lecture 38: Course Review, Take-home Exam 2 distributed

 lec38-slides   HW6 (due by 11:55pm on April 19th, penalty-free extension till April 26th)

-

Fri

Apr 26

No lectures this week — Exam 2 due by 4pm today

 

 

 

 

 

 

Lab Schedule

Lab #

Date (2013)

Topic

Handouts

Code Examples

1

Jan 08, 09, 10

Infrastructure setup, Async-Finish Parallel Programming

lab1-handoutHelloWorldError.hj, ReciprocalArraySum.hj

2

Jan 15, 16, 17

Abstract performance metrics with async & finish

lab2-handoutArraySum1.hj, Search2.hj, ArraySum3.hj

3

Jan 22, 23, 24

Data race detection and repair

lab3-handoutRacyArraySum1.hj, RacyFib.hj, RacyParSearch.hj, RacyFannkuch.hj

4

Jan 29, 30, 31

Futures, Finish Accumulators

lab4-handoutArraySum2.hj, ArraySum4.hj, binarytrees.hj

5

Feb 05, 06, 07

Real performance, work-sharing and work-stealing runtimes

lab5-handout,

linux-tutorial-handout

nqueens.hj, OneDimAveraging.hj

6

Feb 12, 13, 14

Barriers, Data-Driven Futures

lab6-handoutData-Driven Future Examples: TestAsyncDDF0.hj, TestAsyncDDF2.hj

-

Feb 19, 20, 21

No lab (HW3 due, Exam 1 assigned)

 

 

7

Mar 05, 06, 07

Isolated Statement and Atomic Variables

lab7-handoutspanning_tree_seq.hj

8

Mar 12, 13, 14

Actors

lab8-handoutPiSerial1.hj, PiSerial2.hj, PiUtil.hj, PiActor1.hj, PiActor2.hj, SieveSerial.hj, Sieve.hj, other-actor-examples

9

Mar 19, 20, 21

Java Threads

lab9-handout
nqueens.hj
, spanning_tree_atomic.hj
10

Mar 26, 27, 28

Java Locks

lab10-handoutlab10.zip

-

Apr 02, 03, 04

No new lab (extra time to complete Lab 10 due to midterm recess)

  

11

Apr 09, 10, 11

Message Passing Interface (MPI)

lab11-handoutlab11.zip

12

Apr 16, 17, 18

Map Reduce

lab12-handout 

Grading, Honor Code Policy, Processes and Procedures

Grading will be based on your performance on six homeworks (weighted 40% in all), two exams (weighted 20% each), weekly lecture & lab quizzes (weighted 10% in all), and class participation (weighted 10% in all).

The purpose of the homeworks is to train you to solve problems and to help deepen your understanding of concepts introduced in class. Homeworks 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, quizzes 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 homework 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 (as shown here).  Exams 1 and 2 and all quizzes are pledged under the Honor Code.  They test your individual understanding and knowledge of the material. Collaboration on quizzes and exams is strictly forbidden.  Quizzes are open-book and exams are closed-book.  Finally, it is also your responsibility to protect your homeworks, quizzes and exams from unauthorized access. 

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