F. Bodin, P. Beckman, D. Gannon, S. Yang, S. Kesavan, A. Malony, and B. Mohr, "Implementing a parallel C ++ runtime system for scalable parallel systems," in Proceedings, Supercomputing '93, pp. 588--597, Nov. 1993.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....of the original serial code. 2.6 Other Models and Implementations In this section, we survey and briefly compare the approaches represented in this work to nonactor models and implementations. Other actor approaches are considered in Section 3.6. 2.6. 1 pC Gannon and Lee [21] 22] [23], 24] have developed pC , an extension of C with support for distributed data structures similar to FORTRAN D. The pC language provides support for distributed collections, both array based and tree based, of arbitrary types and with full support for the C mechanisms of derivation and ....

F. Bodin, P. Beckman, D. Gannon, S. Yang, S. Kesavan, A. Malony, and B. Mohr, "Implementing a parallel C ++ runtime system for scalable parallel systems," in Proceedings, Supercomputing '93, pp. 588--597, Nov. 1993.

....arrays which limits the programmer s control over the placement and alignment of data. In LPARX, decompositions are first class language objects. They may be allocated at run time, passed to procedures, and manipulated using LPARX s domain calculus, described in Section 3.3. The pC language [14] also supports distributions and decompositions as first class language objects; however, in pC , the application has limited ability in specifying irregular mappings. 3 LPARX Model Description The LPARX model is based on the FIDIL programming language [15] and on our previous work with LPAR ....

F. B. Irisa, P. Beckman, D. Gannon, S. Yang, S. Kesavan, A. Malony, and B. Mohr, "Implementing a parallel c++ runtime system for scalable parallel systems, " in Proceedings of Supercomputing '93, November 1993.

....partitioning strategies (see, for example, 2] These strategies break global arrays into pieces which are distributed across the nodes of a parallel computer. Each node performs the necessary computation on its local section of the global domain. Many data parallel programming languages [3, 4, 5, 6] and libraries [7, 8] provide support for well understood regular block partitioning strategies. This work was supported by a DOE Computational Science Graduate Fellowship Program and NSF contract #ASC 9520372. Computer time on the NAS Power Challenge Array was provided by NASA through the HPCC ....

....A solution to this problem lies in higher level programming models that shield the programmer from low level details of message passing and thread management. Successful higher level models targeted to data parallel applications include HPF [3] Vienna Fortran [4] Split C [5] pC [6], and KeLP [8] To facilitate the domain decomposition strategy described here, a programming model should support two levels, both inter node and intra node, of non uniform block decompositions. In practice, the application will likely determine the optimal decomposition based on factors in the ....

F. Bodin, P. Beckman, D. Gannon, S. Yang, S. Kesavan, A. Malony, and B.Mohr, "Implementing a parallel C++ runtime system for scalable parallel systems," in Proc. Supercomputing, pp. 588--597, 1993.

No context found.

Bodin, F., Beckman, P., Gannon, D, Yang, S, Kesavan, S., Maloney, A. and Mohr, B., "Implementing a Parallel C++ Runtime System for Scalable Parallel Systems", Proc. Supercomputing '93, Portland, OR, 1993, pp. 588--597.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC