The present work illustrates the architecture and utilization of a simulated ATM testbed, which enables studies of ATM-based workstation networks to be carried over another network technology, like Ethernet. The current testbed models a very simple ATM network (applications lay directly over AAL), but it allows an easy addition of protocol layers in order to evaluate their impact on the performance of the whole system. In particular, we have measured the communication latency and the global performance achieved by the ATM model and have compared them with the performance of both an Ethernet-based workstation cluster and a supercomputer. 1 Introduction Up to now, high performance computing has been exploited mostly by vector and massively p...
This report experimentally assesses the effect of the underlying network in a cluster-based computin...
This paper investigates the use of ATM for cluster based computing. The need for a native ATM API is...
Recent developments in communication architectures for parallel machines have made significant progr...
This paper provides an experimental assessment of the impact of the underlying networking in a clust...
We have previously reported a design for a host interface board intended to connect workstations to ...
The advent of high-speed local and wide area networks has made geographically distributed NOWs an ap...
Parallel computing on clusters of workstations is receiving much attention from the research communi...
Asynchronous Transfer Mode (ATM) technology is currently receiving extensive attention in the comput...
Exploiting clusters of workstations as a single computational resource is an attractive alternative ...
Due to the high cost of a large ATM network working up to full strength to apply our ideas about net...
Techniques for measuring and modeling ATM traffic are reviewed. The requirements for cell level ATM ...
In this paper, we examine and characterize effects of communication interactions of parallel and se...
This paper provides experimental data and analysis to quantify both the peak and sustained performan...
This brief paper outlines our strategies for providing a hardware and software solution to interfaci...
Asynchronous Transfer Mode (ATM) switches are the basic components of Broadband Integrated Services ...
This report experimentally assesses the effect of the underlying network in a cluster-based computin...
This paper investigates the use of ATM for cluster based computing. The need for a native ATM API is...
Recent developments in communication architectures for parallel machines have made significant progr...
This paper provides an experimental assessment of the impact of the underlying networking in a clust...
We have previously reported a design for a host interface board intended to connect workstations to ...
The advent of high-speed local and wide area networks has made geographically distributed NOWs an ap...
Parallel computing on clusters of workstations is receiving much attention from the research communi...
Asynchronous Transfer Mode (ATM) technology is currently receiving extensive attention in the comput...
Exploiting clusters of workstations as a single computational resource is an attractive alternative ...
Due to the high cost of a large ATM network working up to full strength to apply our ideas about net...
Techniques for measuring and modeling ATM traffic are reviewed. The requirements for cell level ATM ...
In this paper, we examine and characterize effects of communication interactions of parallel and se...
This paper provides experimental data and analysis to quantify both the peak and sustained performan...
This brief paper outlines our strategies for providing a hardware and software solution to interfaci...
Asynchronous Transfer Mode (ATM) switches are the basic components of Broadband Integrated Services ...
This report experimentally assesses the effect of the underlying network in a cluster-based computin...
This paper investigates the use of ATM for cluster based computing. The need for a native ATM API is...
Recent developments in communication architectures for parallel machines have made significant progr...