Dennis Gannon, Jenq Kuen Lee, and Srinivas Narayana. On Using Object Oriented Parallel Programming to Build Distributed Algebraic Abstractions. In Proceedings of CONPAR 92 - LNCS 634. Springer-Verlag, September 1992.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....high level synchronization constructs (gates vs. monitor [34] M structures [8] ffl constructs to support NUMA (pSather s operator and copy move operations vs. object movement in Emerald [40] ffl constructs to support data parallelism (dist statement and DISTfTg class vs. approaches in PC [30], 46] and C [35] A more complete and detailed description of related work (which involves discussing other specific parallel object oriented languages) can be found in [48] 8.1 Processes Threads There are three general ways to create parallel processes or threads in object oriented ....

Dennis Gannon, Jenq Kuen Lee, and Srinivas Narayana. On Using Object Oriented Parallel Programming to Build Distributed Algebraic Abstractions. In Proceedings of CONPAR 92 - LNCS 634. Springer-Verlag, September 1992.

....Hybrid [184] group objects into protection domains such that at most one thread can be active in a domain. Other than the three main approaches above, a combination of the approaches is possible and used in some languages. For example, Rosette has both actors and passive objects [217] PC [103] presents another variation by supporting the creation of multiple parallel threads, each working on a passive object, resulting in a data parallel model of computation. Each approach leads to a different programmer s view of how threads are created and executed. For example, if threads are ....

....object to select the routines to be executed based on the results of the guard expressions. There is also a uCondition class on which threads can be suspended and resumed. Unlike COOL, C does not have any language constructs for doing thread or object placement. PC A major concern of PC [103, 159] is to be able to build complex distributed data structures (e.g. arrays, lists, sets) in distributed memory machines. PC extends C by introducing the notion of a collection which is a homogeneous group of elements. If coll is a pointer to a collection of elements (of class E) and r is a ....

[Article contains additional citation context not shown here]

Dennis Gannon, Jenq Kuen Lee, and Srinivas Narayana. On Using Object Oriented Parallel Programming to Build Distributed Algebraic Abstractions. In Proceedings of CONPAR 92 - LNCS 634. Springer-Verlag, September 1992.

....The ports include the Kendall Square Research KSR 1, Intel Paragon, TMC CM 5, IBM SP 1, and homogeneous clusters of UNIX workstations using PVM; work on porting pC to the Cray T3D and Meiko CS 2 is in progress. More details about the pC language and runtime system can be found in [8, 9, 14, 15]. 2.1 An Observability and Analysis Model for pC Collection definition and use are the key aspects for program analysis in the pC system. Programmers using pC require support for observing the collection data structures with respect to both their object oriented definition and their ....

D. Gannon, J. K. Lee, On Using Object Oriented Parallel Programming to Build Distributed Algebraic Abstractions, Proc. CONPAR 92--VAPP, Lyon, France, Sept. 1992.

....with the C keyword template. ffl A function object called the Alignment. This function maps collection elements to the abstract coordinate system of the Distribution object. The pC language has a library of standard collection classes that may be used (or subclassed) by the programmer [10, 11, 12, 13]. This includes collection classes such as DistributedArray, DistributedMatrix, DistributedVector, and DistributedGrid. To illustrate the points above, consider the problem of creating a distributed 5 by 5 matrix of floating point numbers. We begin by building a Distribution. A distribution is ....

D. Gannon, J. K. Lee, On Using Object Oriented Parallel Programming to Build Distributed Algebraic Abstractions, Proc. CONPAR/VAPP, Lyon, Sept. 1992.

....X( Y( Y = S X; can be a handy way to construct a collection that has the global structure of a sparse matrix but still allows simple algebraic operators to be applied at the source level. For example, this is used in the pC implementation of the NAS sparse CG benchmark [10]. Along these lines, other useful collections for sparse structured matrices would be DistBandedMatrix TridiagonalMatrix . These will eventually be added to our library. 6 Parallel Tridiagonal Systems and A Fast Poisson Solver In this section we describe the construction of a simple parallel ....

D. Gannon, J. K. Lee, On Using Object Oriented Parallel Programming to Build Distributed Algebraic Abstractions, Proceedings Conpar-Vap, Lyon, Sept. 1992.

....of the target by the run time system. ffl A function object called the Alignment. This function maps collection elements to the abstract coordinate system of the Distribution object. The pC language has a library of standard collection classes that may be used (or subclassed) by the programmer [36, 49, 17, 20]. This includes collection classes such as DistributedArray, DistributedMatrix, DistributedVector, and DistributedGrid. To illustrate the points above, consider the problem of creating a distributed 5 by 5 matrix of floating point numbers. We begin by building a Distribution. A distribution is ....

J. K. Lee D. Gannon. On using object oriented parallel programming to build distributed algebraic abstractions. In Conpar-Vap, pages 769--774. Springer Verlag, 1992.

....memory ports include the Intel Paragon [20] the TMC CM5 [19] the IBM SP 1, and homogeneous clusters of UNIX workstations with PVM [24] Work on porting the runtime system to the Cray T3D and Meiko CS 2 is in progress. More details about the pC language and runtime system can be found in [9, 10, 11, 12, 17]. 3 The pC Performance Analysis Environment The pC integrated performance analysis environment is unique because it is was designed and implemented in concert with the pC language and runtime system. As a result of this tight coupling, the definition and analysis of performance factors is ....

D. Gannon, J. K. Lee, On Using Object Oriented Parallel Programming to Build Distributed Algebraic Abstractions, Proc. CONPAR 92--VAPP, Lyon, France, Sept. 1992.

....to refer to individual objects and subsets of objects in a collection. pC has been implemented on a wide range of commercially available parallel systems; we describe its performance on such platforms later in this chapter. Other examples of pC programs and performance can be found in [10, 11, 8, 3, 12]. Our primary experience with testing the pC ideas on large scale problems has come from our involvement with the NSF Grand Challenge Cosmology Consortium GC 3 . This chapter describes some of these applications. We also discuss two libraries that support parallel I O and persistent objects in ....

D. Gannon and J.-K. Lee. On Using Object Oriented Parallel Programming to Build Distributed Algebraic Abstractions. In Bourge and Cosnard, editors, Proceedings of CONPAR 92--VAPP V, pages 769--774. Springer Verlag, 1992.

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