This paper presents P-RIO, a parallel programming environment that supports an object based software configuration methodology. It promotes a clear separation of the individual sequential computation components from t...
详细信息
This paper presents P-RIO, a parallel programming environment that supports an object based software configuration methodology. It promotes a clear separation of the individual sequential computation components from the interconnection structure used for the interaction between these components. This makes the data and control interactions explicit, simplifying program visualization and understanding. P-RIO includes a graphical tool that helps to configure, monitor and debug parallel programs.
We describe Actors, a flexible, scalable and efficient model of computation, and develop a framework for analyzing the parallel complexity of programs written in it. Actors are asynchronous, autonomous objects which i...
详细信息
We describe Actors, a flexible, scalable and efficient model of computation, and develop a framework for analyzing the parallel complexity of programs written in it. Actors are asynchronous, autonomous objects which interact by message-passing. The data and process decomposition inherent in Actors simplifies modeling real-world systems. High-level concurrent programming abstractions have been developed to simplify program development using Actors; such abstractions do not compromise an efficient and portable implementation. In this paper, we define a parallel complexity model for Actors. The model we develop gives an accurate measure of performance on realistic architectures. We illustrate its use by analyzing a number of examples.
An important development in cluster computing is the availability of multiprocessor workstations. These are able to provide additional computational power to the cluster without increasing network overhead and allow m...
详细信息
ISBN:
(纸本)9780818681172
An important development in cluster computing is the availability of multiprocessor workstations. These are able to provide additional computational power to the cluster without increasing network overhead and allow multiparadigm parallelism, which we define to be the simultaneous application of both distributed and shared memory parallel processing techniques to a single problem. In this paper we compare execution times and speedup of parallel programs written in a pure message-passing paradigm with those that combine message passing and shared-memory primitives in the same application. We consider three basic applications that are common building blocks for many scientific and engineering problems: numerical integration, matrix multiplication and Jacobi iteration. Our results indicate that the added complexity of combining shared- and distributed-memory programming methods in the same program does not contribute sufficiently to performance to justify the added programming complexity.
This paper presents a new structured parallel programming model, "SEQ OF PAR", based on the Communication Closed Layer (CCL) principle of causal composition for parallel programs and Bird-Meertens formalism ...
详细信息
ISBN:
(纸本)0818678763
This paper presents a new structured parallel programming model, "SEQ OF PAR", based on the Communication Closed Layer (CCL) principle of causal composition for parallel programs and Bird-Meertens formalism (BMF) of locality-based parallel computation. This model is to support for more general, architecture-independent parallel programming. It provides a structured approach to integrate task (or process) parallelism and data-parallelism in one framework. The well-founded algebra of CCL and BMF makes it also possible to derive, optimize and verify parallel programs through algebraic transformations. Experimental results show that it is very promising to adopt this programming model for getting efficient, portable parallel code.
Although the processing power and cost-performance benefits of parallel systems are attractive, it is widely accepted that current methods of writing programs for these computers are inadequate. The reason is that the...
详细信息
Although the processing power and cost-performance benefits of parallel systems are attractive, it is widely accepted that current methods of writing programs for these computers are inadequate. The reason is that the higher the abstraction to describe complications, the more difficult it gets to present parallelism, communication and synchronization. This paper describes a new tool, Visper for development of parallel programs. It provides an environment that graphically correlates the control and data flow aspects, in a process communication graph (PCG), without a need for complex textual annotation. It can also express static and run-time communication and replication structures. Our approach is based upon combining the levels of abstraction at which parallel programs are expressed and moving to compositional programming. Ready access to these abstractions is provided by a flexible graphical user interface. In Visper, both ease of preparation and compilation of graphical information to textual code are enabled.
The paper discusses the relationships between hierarchically composite MPP architectures and the software technology derived from the structured parallel programming methodology, in particular the architectural suppor...
详细信息
The paper discusses the relationships between hierarchically composite MPP architectures and the software technology derived from the structured parallel programming methodology, in particular the architectural support to successive modular refinements of parallel applications, and the architectural support to the parallel programming paradigms and their combinations. The structured parallel programming methodology referred here is an application of the Skeletons model. The considered hierarchically composite architectures are MPP machine models for PetaFlops computing, composed of proper combinations of current architectural models of different granularities, where the Processors-In-Memory model is adopted at the finest granularity level. The methodologies are discussed with reference to the current PQE2000 Project on MPP general purpose systems.
This paper presents the BaLinda model, based on last in/first out threads that interact via a shared tuplespace, and discusses the idea of using function based objects as the basic unit of parallel execution, and the ...
详细信息
This paper presents the BaLinda model, based on last in/first out threads that interact via a shared tuplespace, and discusses the idea of using function based objects as the basic unit of parallel execution, and the hierarchical structure to partition tuplespaces. It is argued that the two-level parallel execution, both within and between objects, are well suited to scalable parallel platforms with shared memory nodes connected by high speed networks.
We exploited the recent advances in Internet connectivity and Web technologies for building Web-based parallel programming environments (WPPEs) that facilitate the development and execution of parallel programs on rem...
详细信息
ISBN:
(纸本)9780818681172
We exploited the recent advances in Internet connectivity and Web technologies for building Web-based parallel programming environments (WPPEs) that facilitate the development and execution of parallel programs on remote high-performance computers. A Web browser running on the user's machine provides a user-friendly interface to server-site user accounts and allows the use of parallel computing platforms and software in a convenient manner. The user may create, edit, and execute files through this Web browser interface. This new Web-based client-server architecture has the potential of being used as a future front-end to high-performance computer systems. We discuss the design and implementation of several prototype WPPEs that are currently in use at the Northeast parallel Architectures Center and the Cornell Theory Center. These initial prototypes support high-level parallel programming with Fortran 90 and High Performance Fortran (HPF), as well as explicit low-level programming with Message Passing Interface (MPI). We detail the lessons learned during the development process and outline the tradeoffs of various design choices in the realization of the design. We especially concentrate on providing server-site user accounts, mechanisms to access those accounts through the Web, and the Web-related system security issues.
The MILLIPEDE system is a small yet powerful interface of a virtual parallel machine (VPM) on top of distributed computing environments. MILLIPEDE is thus a convenient environment for porting various existing parallel...
详细信息
The MILLIPEDE system is a small yet powerful interface of a virtual parallel machine (VPM) on top of distributed computing environments. MILLIPEDE is thus a convenient environment for porting various existing parallel programming languages, for the design of new parallel programming languages, and for the development of parallel applications. MILLIPEDE is fully implemented at the Technion on a cluster of PCs running Windows-NT. We briefly describe the MILLIPEDE interface and discuss the implementation issues of several parallel languages.
This paper argues for the development of more general and user-friendly parallel programming models, independent of hardware structures and concurrency concepts of operating systems theory, leading to portable program...
详细信息
This paper argues for the development of more general and user-friendly parallel programming models, independent of hardware structures and concurrency concepts of operating systems theory, leading to portable programs and easy to use languages. It then presents the BaLinda model, based on last in/first out threads that interact via a shared tuplespace, and argues that it is simple enough to be both general and easy to use. It also discusses the idea of using function-based objects as the basic unit of parallel execution and the hierarchical structure to partition tuplespaces.
暂无评论