CSE 160 Lecture and Reading Schedule (Winter 2010)

This schedule may change, so check frequently.
Lecture slides will be made available by 10AM the day of lecture.

Lecture Date Subject

1 1/5 Introduction.
Text: Chapters 1 and 2.
Background on memory hierarchies: Memory Hierarchy in Cache-Based Systems by Ruud van der Pas, 2002, Sun Microsystems. (Dated, but a nice introduction.). To dig deeper, consult the Wikipedia

2 1/7 Introduction to programming with threads.
Text: Chapters 4 and 6, Chapter 13: pp. 172-173, 178 (SharedInteger, see PJ Documentation).
Javasoft Thread Tutorial. Read Concurrency and Processes and Threads
Download PJ and Program 1 (Program1.tgz) and Hello World (hello.tgz)

3 1/12 Embarrassingly parallel applications; parallel for loops; data sharing; analyzing data dependencies.
Text: Chapters 5 and 7. Re-read chapter 6,pp. §6.3-6.4 (pp. 80-87)

4 1/14 Characterizing performance - speedup; Parallel image processing and generation
Text: Chapters 8 and 11.

5 1/19 Revisiting the Java Memory Model; Weak scaling; Cache Interference.

Text: Chapters 9 and 10.
Synchronization and the Java Memory Model, (Book supplement to Concurrent Programming in Java: Design Principles and Patterns, by Doug Lea, 2nd ed., Addison-Wesley, Nov. 1999, previously handed out in class)

To read further: Eliminate False Sharing, by Herb Sutter (Dr. Dobb’s Journal)

6 1/21 Load balancing. Optimizing for Memory locality.
Text: Chapter 12

Optimizing fast linear algebra kernels for the memory hierarchy (Jim Demmel, UC Berkeley). Ignore algorithm 2.

7 1/26 Reduction, synchronization in Java

Text: Chapter 13.
Read the Synchronization section (ALL) from The Java Tutorials

8 1/28 Programming with Java Threads
Text: Chapter 15.

Three sections from The Java Tutorials: Processes and Threads, Thread Objects, and Atomic Variables.
Short reader on numerical integration, Royal Inst. of Technology, Stockholm.
For reference: Introduction to Java threads, by Donald G. Drake [1996].

9 2/2 More on synchronization. Application Study: Protein sequence querying

Java theory and practice: Going atomic, IBM Developerworks. Read the Hardware synchronization primitives section through the ABA problem
Text: Chapter 37: §37.1-2 (pp. 703-8), §37.3 (pp 714-15), §37.5 (728-31), §37.8-9 (pp. 749-751)

10 2/2 OpenMP; Image segementation
Text: Appendices A and D.
For reference: Getting started with OpenMP (Intel)

11 2/9 Midterm review.

12 2/11 Midterm.

13 2/16 Message passing: programming and performance
Text. Chapter 19 (all), Chapter 20 (In section 20.3 read about broadcast and reduce only).

14 2/18 MPI, the Message Passing Interface
Text. Finish chapter 20 (but skip the section on Flood)
A User’s Guide to MPI, by Peter Pacheco, pp. 1-17. pdf

15 2/23 Message passing application design
Re-read A User’s Guide to MPI, by Peter Pacheco, pp. 1-17. pdf
Modeling performance of an image smoother PDF

16 2/25 Collectives and their applications, advanced message passing techniques
Text. Chapter 24: Sec 24.1-2; Chapter 25: Sec 25.4, Chapter 27: Sec 27.3; Chapter 30.
Bucket sort (Wikipedia)
For reference: Sorting algorithms (Wikipedia)

17 3/2 Data Decomposition and Irregular Problems
Reader on Data Decomposition and Load Balancing
For the programming lab. Text: Chapter 30.

18 3/4 Bitonic sort; Graphical Processing Units
Reader on Bitonic sort
Scalable Parallel Programming with CUDA, J. Nickolls et al., ACM Queue, 6(2):40-53, March/April 2008. (Read only through page 48)
CUDA, Supercomputing for the Masses, by Rob Farber, parts I and II. (15 part article if you area interested in pursuing GPU programmer further, a good soruce of information)

To enquire further about GPUs
CUDA Zone. Articles, CUDA downloads and documentation. From there you can also enter the Developer zone.
GPU Resources A web page with other sources of information about GPUs.

19 3/8 GPU Applications and Performance Programming
Scalable Parallel Programming with CUDA, J. Nickolls et al., ACM Queue, 6(2):40-53, March/April 2008. (Read about parallel reduction)

20 3/11 Final Exam review.

- 3/16 Final Exam, 3pm to 6pm

Maintained by baden @ ucsd.
edu [Wed Mar 10 21:57:14 PST 2010]

Lecture	Date	Subject
1	1/5	Introduction. Text: Chapters 1 and 2. Background on memory hierarchies: Memory Hierarchy in Cache-Based Systems by Ruud van der Pas, 2002, Sun Microsystems. (Dated, but a nice introduction.). To dig deeper, consult the Wikipedia
2	1/7	Introduction to programming with threads. Text: Chapters 4 and 6, Chapter 13: pp. 172-173, 178 (SharedInteger, see PJ Documentation). Javasoft Thread Tutorial. Read Concurrency and Processes and Threads Download PJ and Program 1 (Program1.tgz) and Hello World (hello.tgz)
3	1/12	Embarrassingly parallel applications; parallel for loops; data sharing; analyzing data dependencies. Text: Chapters 5 and 7. Re-read chapter 6,pp. §6.3-6.4 (pp. 80-87)
4	1/14	Characterizing performance - speedup; Parallel image processing and generation Text: Chapters 8 and 11.
5	1/19	Revisiting the Java Memory Model; Weak scaling; Cache Interference. Text: Chapters 9 and 10. Synchronization and the Java Memory Model, (Book supplement to Concurrent Programming in Java: Design Principles and Patterns, by Doug Lea, 2nd ed., Addison-Wesley, Nov. 1999, previously handed out in class) To read further: Eliminate False Sharing, by Herb Sutter (Dr. Dobb’s Journal)
6	1/21	Load balancing. Optimizing for Memory locality. Text: Chapter 12 Optimizing fast linear algebra kernels for the memory hierarchy (Jim Demmel, UC Berkeley). Ignore algorithm 2.
7	1/26	Reduction, synchronization in Java Text: Chapter 13. Read the Synchronization section (ALL) from The Java Tutorials
8	1/28	Programming with Java Threads Text: Chapter 15. Three sections from The Java Tutorials: Processes and Threads, Thread Objects, and Atomic Variables. Short reader on numerical integration, Royal Inst. of Technology, Stockholm. For reference: Introduction to Java threads, by Donald G. Drake [1996].
9	2/2	More on synchronization. Application Study: Protein sequence querying Java theory and practice: Going atomic, IBM Developerworks. Read the Hardware synchronization primitives section through the ABA problem Text: Chapter 37: §37.1-2 (pp. 703-8), §37.3 (pp 714-15), §37.5 (728-31), §37.8-9 (pp. 749-751)
10	2/2	OpenMP; Image segementation Text: Appendices A and D. For reference: Getting started with OpenMP (Intel)
11	2/9	Midterm review.
12	2/11	Midterm.
13	2/16	Message passing: programming and performance Text. Chapter 19 (all), Chapter 20 (In section 20.3 read about broadcast and reduce only).
14	2/18	MPI, the Message Passing Interface Text. Finish chapter 20 (but skip the section on Flood) A User’s Guide to MPI, by Peter Pacheco, pp. 1-17. pdf
15	2/23	Message passing application design Re-read A User’s Guide to MPI, by Peter Pacheco, pp. 1-17. pdf Modeling performance of an image smoother PDF
16	2/25	Collectives and their applications, advanced message passing techniques Text. Chapter 24: Sec 24.1-2; Chapter 25: Sec 25.4, Chapter 27: Sec 27.3; Chapter 30. Bucket sort (Wikipedia) For reference: Sorting algorithms (Wikipedia)
17	3/2	Data Decomposition and Irregular Problems Reader on Data Decomposition and Load Balancing For the programming lab. Text: Chapter 30.
18	3/4	Bitonic sort; Graphical Processing Units Reader on Bitonic sort Scalable Parallel Programming with CUDA, J. Nickolls et al., ACM Queue, 6(2):40-53, March/April 2008. (Read only through page 48) CUDA, Supercomputing for the Masses, by Rob Farber, parts I and II. (15 part article if you area interested in pursuing GPU programmer further, a good soruce of information) To enquire further about GPUs CUDA Zone. Articles, CUDA downloads and documentation. From there you can also enter the Developer zone. GPU Resources A web page with other sources of information about GPUs.
19	3/8	GPU Applications and Performance Programming Scalable Parallel Programming with CUDA, J. Nickolls et al., ACM Queue, 6(2):40-53, March/April 2008. (Read about parallel reduction)
20	3/11	Final Exam review.
-	3/16	Final Exam, 3pm to 6pm