In this paper, we present a system called DONOW (Database on Network of Workstation), that is an example of an implementation and maintenance of a low cost distributed database without performances penalties. the syst...
详细信息
High performance clusters (HPCs) based on commodity hardware are becoming more and more popular in the parallel computing community. these new platforms offer a hardware capable of a very low latency and a very high t...
详细信息
High performance clusters (HPCs) based on commodity hardware are becoming more and more popular in the parallel computing community. these new platforms offer a hardware capable of a very low latency and a very high throughput at an unbeatable cost, making them attractive for a large variety of parallel and distributedapplications. With adequate communication software, HPCs have the potential to achieve a level of performance similar to massively parallel computers. However, for parallelapplicationsthat present a high communication/computation ratio, it is still essential to provide the lowest latency in order to minimize the communication overhead. In this paper, we are investigating message aggregation techniques to improve parallel simulations of fine-grain ATM communication network models. Even if message aggregation is a well-known solution for improving the communication performance of high latency interconnection networks, the complex interaction between message aggregation and the underlying communication software is often ignored. We show that message aggregation must carefully take into account the characteristics of the communication software to be efficient on an HPC. this methodology can be applied as a preliminary step to tune a message aggregation algorithm for a given combination of hardware architecture and communication software layer.
this paper presents a novel architecture for parallel database processing called Multi-Wavelength Optical Content Addressable parallel Processor (MW-OCAPP). MW-OCAPP is designed to provide efficient parallel retrieval...
详细信息
parallel simulation has the potential to accelerate the execution of simulation applications. However, developing a parallel discrete-event simulation from scratch requires an in-depth knowledge of the mapping process...
详细信息
parallel simulation has the potential to accelerate the execution of simulation applications. However, developing a parallel discrete-event simulation from scratch requires an in-depth knowledge of the mapping process from the physical model to the simulation model, and a substantial effort in optimising performance. this paper presents an overview of the SPaDES (Structured parallel Discrete-Event Simulation) parallel simulation framework. We focus on the performance analysis of SPaDES/C++, an implementation of SPaDES on a distributed-memory Fujitsu AP3000 parallel computer. SPaDES/C++ hides the underlying complex parallel simulation synchronization and parallel programming details from the simulationist. Our empirical results show that the SPaDES framework can deliver good speedup if the process granularity is properly optimised.
Checkpointing is a very effective technique to tolerate the occurrence of failures in distributed and parallelapplications. the existing algorithms in the literature are basically divided into two main classes: coord...
详细信息
Checkpointing is a very effective technique to tolerate the occurrence of failures in distributed and parallelapplications. the existing algorithms in the literature are basically divided into two main classes: coordinated and independent checkpointing. this paper presents an experimental study that compares the performance of these two classes of algorithms. the main conclusion of our study is that coordinated checkpointing is more efficient than independent checkpointing and all the arguments against the performance of coordinated algorithms were not verified in practice.
Coupling computer resources to work on a given problem has been a successful strategy for years. Due to the existence of high bandwidth WAN it has become possible to couple big machines to build clusters that outperfo...
详细信息
Coupling computer resources to work on a given problem has been a successful strategy for years. Due to the existence of high bandwidth WAN it has become possible to couple big machines to build clusters that outperform the most powerful existing single computers. In the following we will speak of such a powerful cluster as a metacomputer. While for MPPs the message passing model has been standardized already 4 years ago, a standard for interoperable MPI has only been published recently. In this paper we briefly present an approach for MPI based metacomputing called PACX-MPI. We shortly describe other approaches, and give an overview of the technical concept.
To support incremental replay of message-passing applications, processes must periodically checkpoint and the content of some messages must be logged, to break dependencies of the current state of the execution on pas...
详细信息
To support incremental replay of message-passing applications, processes must periodically checkpoint and the content of some messages must be logged, to break dependencies of the current state of the execution on past events. the paper presents a new adaptive logging algorithm that dynamically decides whether to log a message based on dependencies the incoming message introduces on past events of the execution. the paper discusses the implementation issues of the algorithm and evaluates its performances on several applications, showing how it improves previously known schemes.
Multihop lightwave networks are becoming increasingly popular in optical networks. It is attractive to consider regular graphs as the logical topology for a multihop network, due to its low diameter. Standard regular ...
详细信息
A parallel program archetype is an abstraction that captures the common features of a class of problems with similar computational structure and combines them with a parallelization strategy to produce a pattern of da...
详细信息
A parallel program archetype is an abstraction that captures the common features of a class of problems with similar computational structure and combines them with a parallelization strategy to produce a pattern of dataflow and communication. Such abstractions are useful in application development, both as a conceptual framework and as a basis for tools and techniques. this paper describes an approach to parallel application development based on archetypes and presents two example archetypes withapplications.
暂无评论