Term projects:

  A group of 2 people.
  Timeline: 

    Determining a project topic: March 24
    Midterm project progress report: April 8
    Project presentation: April 21 and April 24
    Final project report: April 28

  Any of the four types: 
    
    1. Survey the recent advances in one area related to PDS
    2. Empirically evaluating a software system
    3. Design, analyze, evaluate new algorithms for some types of 
       parallel and distributed systems
    4. Your own topics related to PDS

- Survey the recent advances in one area related to PDS

  Fix a good topic; find all related papers by yourselves (5 minimum); 
  summarize the problem and the proposed solutions;
  identify the strengths and limitations of the solutions;
  identify what have been done on this topic and what are the remaining
  issues. 

  Requirement:

  a) The area must not be out-dated.
     - at least 1 paper published in 2008 or later.
     - at least 4 papers published in 2002 or later.

  b) You must be able to clearly identify the (significant) topic. 
     - What is the problem?
     - Why is it a problem?
     - Why is this problem significant?

  c) The survey should give the state of the art of that area.
     - Existing techniques for the problems
     - Strengths and weaknesses of the techniques
     - What have been solved and what have not been solved.

  all these must be reflected in your report and presentation.

Example topics (These topics may be too broad): 

   1. Transactional Memory

   - U. Drepper, "Parallel Programming with Transactional Memory," ACM Queue
     6(5)38-45, Dec. 2008.

   2. New parallel programming models

   - Michael D. Linderman, J. D. Collins, H. Wang, t. H. Meng, "Merge:
     A Programming Model for Heterogeneous Multi-core Systems," ACM ASPLOS 
     2008.

   - J. Dean, and S. Ghemawat, "MapReduce: Simplified Data Processing on 
     Large Clusters," OSDI 2004.

   3. Compiler/OS supports for Multithreading

   - Marek Olszewski, Jason Ansel, Saman Amarasinghe, "Kendo:  Efficient 
     Determistic Multithreading in Software," ACM ASPLOS 2009.
    
   - Z. Anderson, D. Gay, R. Ennals, and E. Brewer, "SharC: Checking Data
     Sharing Strategies for Multithreaded C," ACM PLDI 2008.

   4. Thread scheduling for Multi-core

   - D. Tam, R. Azimi, M. Stumm, "Thread Clustering: Sharing Aware 
     Scheduling on SMP-CMP-SMT Multiprocessors," ACM, EuroSys'2007.

   - M. Rajagopalan, B. T. Lewis, T.A. Anderson, "Thread Scheduling for 
     Multi-Core Platforms," USENIX Workshop on Hot topics in OS, 2007.

   5. Routing in Interconnection networks

   - P. Geoffray, T. Hoefler, "Adaptive Routing Strategies for Modern High
     Performance Networks," HOT Interconnect, 2008.

   - X. Yuan, W. Nienaber, Z. Duan, and R. Melhem, "Oblivious Routing for 
     Fat-Tree Based System Area Networks with Uncertain Traffic Demands," 
     ACM Sigmetrics, pages 337-348, 2007. 

   6. Collective communication optimization

   - A. Faraj, P. Patarasuk, and X. Yuan, "A Study of Process Arrival 
     Patterns for MPI Collective Operations," International Journal of 
     Parallel Programming, 36(6):543-570, December 2008. 

   - Y. Qian and A. Afsahi, "Efficient shared memory and RDMA based 
     collectives on multi-rail QsNetII SMP clusters," 11(4):341-354, 
     Cluster Computing, Dec. 2008.

   7. Accelerator based computing

   - Michael Kistler, John Gunnels, Daniel Brokenshire, Brad Benton,
    "Petascale Computing with Accelerators," ACM PPoPP 2009.

   - S. Ryoo, C. I. Rodrigues, S.S. Baghsorkhi, S. S. Stone, "Optimization
     Principles and Application performance Evaluation of a Multithreaded GPU
     Using CUDE," ACM PPoPP 2008.   

   8. Data intensive computing

     - Kouzes, R.T., Anderson, G.A., Elbert, S.T., Gorton, I., Gracio, D.K.,
       "The Changing Paradigm of Data Intensive Computing," IEEE Computer,
       42(1):26-34, Jan. 2009.

     - Randal E. Bryant, "Data-Intensive Supercomputing: The Case for DISC,"
       TR CMU-CS-07-128, School of Computer Science, CMU, 2007.

   9. Parallel I/O

      - A. Nisar, Weikeng Liao, A. Choudhary, "Scaling Parallel I/O 
      Performance through I/O Delegate and Caching System," ACM SC'08.

      - P.H. Carns, b. W. Settlemyer, and W. B. Ligon III, "Using 
      Server-to-server Communication in Parallel File systems to simplify
      Consistency and improve Performance," ACM SC'08.
  
    10. Lock free data structures
    11. Memory hierarchy design for CMP
    12. on-chip interconnects

- Empirically evaluating a software system

  Install a software system and related benchmarks (write your own 
  if necessary). Empirically measure the performance of the system.
  Summary the performance results and draw conclusions from the results. 

  Requirement:

  a) The software system must not be out-updated.
  b) This may involve software implementation or software installation

  Example topics:

  1. Evaluation of mapreduce on multi-core platforms

  C. Ranger, et. al, "Evaluating MapReduce for Multi-core and Multiprocessor
  Systems," HPCA 2007.

  2. Evaluation of STAR-MPI on different platforms.
  http://star-mpi.sourceforge.net/

  3. Evaluate some lock free data structures on multi-core systems.

  4. Evaluate some collective communication algorithms on clusters

  5. Evaluating and improving sparse matrix/graph message passing 
   algorithms/applications on different platforms. One example is the 
   LU factorization algorithm in 
   http://www.cs.rochester.edu/~kshen/research/s+/.

  6. Evaluating software overheads in common communication libraries.
   You can evaluate the software overheads in some commonly
   used libraries (e.g. MVAPICH, OPENMPI, etc). The results will provide 
   the base line as to how much performance gain can still be achieved in 
   such libraries when various communication optimization techniques are 
   applied. 

- Design, analyze, evaluate new algorithms/applications for some types of 
  parallel and distributed systems

  Anything new (new algorithm, new analysis techniques, 
  new modeling techniques) with a reasonable justification is good.

  - New routing algorithms for fat-trees
  - New network topology
  - New lock free data structures
  - New multithreaded, or message passing algorithms
  - New multithreaded, or message passing applications
  - New collective communication algorithms
  - New performance modeling techniques