Research Project

Resume    About Me 

[Research Fields]    Parallel/Distributed Computing, Model Coupling, Parallel Programming Models

Seine 

Stands for "SharEd INfo spacE", which is an parallel application interaction framework that supports code coupling by creating dynamic geometry-based shared space at runtime among parallel components.  

Enabling Efficient and Flexible Coupling of Parallel Scientific Applications

In this project, we approach the MxN parallel data redistribution problem through a shared-space based perspective. The basic idea is to construct a shared space transparently accessible to data redistributing cohorts so that data redistribution can be achieved by data-sender inserting data (objects) into the shared space and data-receiver retrieving data (objects) from the shared space.  

Salsa

Salsa is a novel, decentralized and asynchronous realization of the "replica exchange" algorithm for simulating the structure, function, folding, and dynamics of proteins. Salsa provides a scalable communication and interaction substrate that presents a virtual shared space abstraction and enables the dynamic and asynchronous interactions required by the simulations to be simply and efficiently implemented.

[MxN Problem]           MxN@ORNL    MxN@Indiana    PAWS    CUMULVS    InterComm    RedGrid    UnixRun

                             Parallel Data Representation(by F. Bertrand)    Parallel Data Distribution Description(by R. Bramley)

                             CCA Scientific Data Components Working Group    Global Arrays

[Model Coupling]        MCT    CCSM

[Shared Memory Systems]    A Summary Page (hardware-based/software-based/mixed)

[Linda/Tuple Space]    Yale Linda Group(link lost)    York Linda Group 

                               Introduction in Designing and Building Parallel Programs (by I. Foster)       

                               An Tuple Space Overview    JavaSpace    IBM's TSpace    Microsoft 

[Parallel/High Performance Computing]    Parallel/High Performance Computing Resources1    Resource2

                                                       Nan's Page    Parallel Computing Archive    

[Distributed Computing]    Globus    Grid Computing    IEEE distributed Systems Online    Grail    Dr.Schmidt's Page

[Super Computers]    Super Computing Site list    Top 500 Super Computer List

                             DataStar    NPACI Hotpage

[Programming Tips] 

1. "A Dynamic Geometry-based Shared Space Interaction Framework for Parallel Scientific Applications", L. Zhang, M. Parashar, Proceedings of the 11th Annual International Conference on High Performance Computing (HiPC 2004) , Bangalore, India, December 2004
2. "Shared Memory Multiprocessors,"  L. Zhang* and M. Parashar,  "in Encyclopedia of Computer Science and Engineering," Editor: B. Wah, John Wiley and Sons, Inc, 2005.
3. "Seine: A Dynamic Geometry-based Shared Space Interaction Framework for Parallel Scientific Applications". L. Zhang and M. Parashar. Concurrency and Computations: Practice and Experience. John Wiley and Sons. 2006.
4. "Enabling Efficient and Flexible Coupling of Parallel Scientific Applications," L. Zhang and M. Parashar, In the Proceedings of the 20th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2006). Rhodes Island, Greece. IEEE Computer Society Press.
   
5. "Salsa: Scalable Asynchronous Replica Exchange for Parallel Molecular Dynamics Applications," L. Zhang, M. Parashar, Emilio Gallicchio and Ronald M. Levy, accepted by the 2006 International Conference on Parallel Processing (ICPP-06). August 14-18, 2006. Columbus, Ohio, USA.