| George E. Cline and James D. Arthur. Linda-lan: A controlled parallel processing environment. Technical Report TR 92-37, Virginia Polytechnic Institute and State University, 1992. |
....that allows experimentation and modification. In order to gain this flexibility in experimentation, an implementation of distributed tuplespace for a network of workstations has been developed. The experiences of this implementation effort have found existing distributed tuplespace implementations [6, 12, 16, 31, 44, 49] to be incomplete in their descriptions of the implementation issues faced and the potential solutions and pitfalls in addressing these issues. This paper focuses on filling this gap, by sharing our experiences in designing and implementing a distributed tuplespace, focusing on the design issues ....
....transmitted back and forth. Processor Location of a Tuple For tuplespace (or any DSM) to allow the sharing of data, a process must be able to locate and retrieve the data it requires. Reference [44] terms this issue tuplespace organization and distribution. One choice, taken by Cline and Arthur [16], is to centralize tuplespace on a single node of the parallel machine. All tuples are stored on the one processor, and locating a tuple is simplified because all processes route the request to this node. While this approach does provide parallelism by allowing the computation to be divided across ....
[Article contains additional citation context not shown here]
George E. Cline and James D. Arthur. Linda-lan: A controlled parallel processing environment. Technical Report TR 92-37, Virginia Polytechnic Institute and State University, 1992.
....that allows experimentation and modification. In order to gain this flexibility in experimentation, an implementation of distributed tuplespace for a network of workstations has been developed. The experiences of this implementation effort have found existing distributed tuplespace implementations [6, 12, 16, 31, 44, 49] to be incomplete in their descriptions of the implementation issues faced and the potential solutions and pitfalls in addressing these issues. This paper focuses on filling this gap, by sharing our experiences in designing and implementing a distributed tuplespace, focusing on the design issues ....
....is transmitted back and forth. Processor Location of a Tuple For tuplespace (or any DSM) to allow the sharing of data, a process must be able to locate and retrieve the data it requires. This issue is termed tuplespace organization and distribution in [44] One choice, taken by Cline and Arthur [16], is to centralize tuplespace on a single node of the parallel machine. All tuples are stored on the one processor, and locating a tuple is simplified because all processes simply route the request to this node. While this approach does provide parallelism by allowing the computation to be divided ....
[Article contains additional citation context not shown here]
George E. Cline and James D. Arthur. Linda-lan: A controlled parallel processing environment. Technical Report TR 92-37, Virginia Polytechnic Institute and State University, 1992.
No context found.
G. Cline and J. Arthur, `Linda-LAN: a controlled parallel processing environment', Proceedings of the Twelfth Annual IEEE International Phoenix Conference on Computers and Communications, Phoenix AZ, March 1993, pp. 112--119.
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