Parallel Programming on Top of DSM System: An Experimental Study

Parallelization of an application with a message-passing model requires time, effort and an important parallel programming knowledge from the programmer. By using a distributed shared memory model, programming a parallel application seems easy but reaching good performances becomes more difficult. In this paper we propose an experimental study of the way to program parallel applications with the DOSMOS DSM system which provides an original programming model with shared distributed objects. Moreover by integrating a development platform and monitoring facilities, the DOSMOS system has been designed to offer a performant user-friendly programming environment.

[1]  Umakishore Ramachandran,et al.  Coherence of Distributed Shared Memory: Unifying Synchronization and Data Transfer , 1989, International Conference on Parallel Processing.

[2]  Jeffrey F. Naughton,et al.  Using shared virtual memory for parallel join processing , 1993, SIGMOD '93.

[3]  Thierry Priol,et al.  Parallel Sparse Matrix by Vector Multiplication using a Shared Virtual Memory Environment , 1993, PPSC.

[4]  Henri E. Bal,et al.  Parallel programming using shared objects and broadcasting , 1992, Computer.

[5]  Brett D. Fleisch,et al.  Mirage: a coherent distributed shared memory design , 1989, SOSP '89.

[6]  Anoop Gupta,et al.  Memory consistency and event ordering in scalable shared-memory multiprocessors , 1990, [1990] Proceedings. The 17th Annual International Symposium on Computer Architecture.

[7]  Lionel Brunie,et al.  Execution analysis of DSM applications: a distributed and scalable approach , 1996, SPDT '96.

[8]  Laurent Lefèvre,et al.  Modèle de mémoire distribuée-partagée pour machine massivement parallèle , 1994 .

[9]  Willy Zwaenepoel,et al.  Implementation and performance of Munin , 1991, SOSP '91.

[10]  Thierry Priol,et al.  Distributing data and control for ray tracing in parallel , 1994, IEEE Computer Graphics and Applications.

[11]  L. Lefevre,et al.  New propositions to improve the efficiency and scalability of DSM systems , 1996, Proceedings of 1996 IEEE Second International Conference on Algorithms and Architectures for Parallel Processing, ICA/sup 3/PP '96.

[12]  Anoop Gupta,et al.  Memory consistency and event ordering in scalable shared-memory multiprocessors , 1990, ISCA '90.

[13]  Vaidy S. Sunderam,et al.  PVM: A Framework for Parallel Distributed Computing , 1990, Concurr. Pract. Exp..

[14]  Jack Dongarra,et al.  Pvm 3 user's guide and reference manual , 1993 .