Dependability analysis of a large network is NP-hard due to the state space explosion. A hierarchical Boolean algebraic method was recently introduced to efficiently evaluate static terminal reliability and task-based...
详细信息
ISBN:
(纸本)081864222X
Dependability analysis of a large network is NP-hard due to the state space explosion. A hierarchical Boolean algebraic method was recently introduced to efficiently evaluate static terminal reliability and task-based reliability by dividing the problem into smaller, more manageable pieces. We extend this method to evaluate time-dependent reliability and availability, collectively referred to as `dependability', and to approximate MTTF.
In the last few years, research advances in dynamic scheduling at application and runtime system levels have contributed to improving the performance of scientific applications in heterogeneous environments. This pape...
详细信息
Most studies of processor scheduling in multiprogrammed parallel systems have ignored the I/O performed by applications. Recent studies have demonstrated that significant I/O operations are performed by a number of di...
详细信息
Most studies of processor scheduling in multiprogrammed parallel systems have ignored the I/O performed by applications. Recent studies have demonstrated that significant I/O operations are performed by a number of different classes of parallel applications. This paper focuses on some basic issues that underlie scheduling in multiprogrammed parallel environments running applications with I/O. Characterization of the I/O behavior of parallel applications is discussed first. Based on simulation models this research investigates the influence of these I/O characteristics on processor scheduling.
Despite the large I/O capabilities in modern cluster architectures with. local disks on each node, applications mostly are not enabled to fully exploit them. This is especially problematic for data intensive applicati...
详细信息
ISBN:
(纸本)0769516866
Despite the large I/O capabilities in modern cluster architectures with. local disks on each node, applications mostly are not enabled to fully exploit them. This is especially problematic for data intensive applications which often suffer from low I/O performance. As one solution for this problem, a Distribution I/O Management (DIOM) system has been developed to manage a transparent distribution of data across cluster nodes and to then allow applications to access, this. data purely from local disks. In order to be effective,. however this distribution process requires semantic information about both the application and the input data. This work therefore extends DIOM to include independent specifications for both dataformats and application I/O patterns and thereby decouples them. This work is driven by an application from nuclear medical imaging, the reconstruction of PET images, for which DIOM has proven to be an adequate solution enabling truly scalable I/O and thereby improving the overall application performance.
Lattice basis reduction has important applications in the areas of computer algebra, cryptography and combinatorial optimization. Several efficient sequential algorithms are known. Recently, parallel algorithms have b...
详细信息
ISBN:
(纸本)081864222X
Lattice basis reduction has important applications in the areas of computer algebra, cryptography and combinatorial optimization. Several efficient sequential algorithms are known. Recently, parallel algorithms have been developed but until now a formal proof for the efficiency of parallel algorithms with n2 processors has been omitted, where n denotes the dimension of the lattice. In this paper, a variant of the well-known basis reduction algorithms is presented that is well suited for the computation with fast floating point arithmetic and for the implementation on a mesh-connected array of n2 processors. In addition, an error analysis and a proof of the parallel efficiency is provided.
This paper presents a fault-tolerant manager for distributed applications. This manager provides an efficient recovery of hosts' failures on networks of workstations. An independent checkpointing is used to automa...
详细信息
ISBN:
(纸本)081864222X
This paper presents a fault-tolerant manager for distributed applications. This manager provides an efficient recovery of hosts' failures on networks of workstations. An independent checkpointing is used to automatically recover application processes affected by host failures. Domino-effects are avoided by means of message logging and file versions management. STAR provides an efficient software failure detection by structuring hosts in a logical ring. Performance measurements in a real environment show the interest and the limits of our system.
Advances in networking and storage technologies have made it possible to build multimedia on-demand servers that provide service similar to those of neighborhood videotape rental stores. In this work, we propose a spe...
详细信息
Advances in networking and storage technologies have made it possible to build multimedia on-demand servers that provide service similar to those of neighborhood videotape rental stores. In this work, we propose a specialized high-performance programmable multiprocessor architecture which allows continuous playback of media-streams to large number of clients, a critical factor in multimedia servers. This architecture supports dynamic phase shifts in media distribution which is particularly useful in a distributed environment. We introduce algorithms for maximum concurrency extraction and to avoid task migration in the presence of dynamically changing demand. We show that our solution performs an order of magnitude better than other known solutions.
The proceedings contains 125 papers from the 12th International parallelprocessingsymposium and 9th symposium on parallel and distributedprocessing. Topics discussed include: broadcast on d-dimensional all-port and...
详细信息
The proceedings contains 125 papers from the 12th International parallelprocessingsymposium and 9th symposium on parallel and distributedprocessing. Topics discussed include: broadcast on d-dimensional all-port and wormhole-routed torus;time-step optimal broadcast;hiding communication latency;non-deterministic communication over synchronous channels;coarse-grain broadcast communication model;all-to-some personalized communication;distributed memory multiprocessors;sparse algorithms;processor-in-memory arrays;block-cyclic distribution;global communication optimization;compiler and runtime library approaches;parallel MATLAB compiler;and multi-port hypercubes message-passing parallel programs.
SystemC has become a very popular standardized language for the modeling of System-On-Chip (SoC) devices. However, due to the ever increasing complexity of SoC designs, the ever longer simulation times affect SoC expl...
详细信息
ISBN:
(纸本)9780769534718
SystemC has become a very popular standardized language for the modeling of System-On-Chip (SoC) devices. However, due to the ever increasing complexity of SoC designs, the ever longer simulation times affect SoC exploration potential and time-to-market. In order to reduce these times, we have developed a parallel System C kernel. Because the System C semantics require a high level of synchronization which can dramatically affect the performance, we investigate in this paper some ways to reduce the synchronization overheads. We validate then our approaches against an academic design model and a real, industrial application.
UbiWorld is a concept that ties together the notion of Ubiquitous Computing (Ubicomp) with that of using virtual reality for rapid prototyping. The goal is to develop an environment where one can explore Ubicomp type ...
详细信息
ISBN:
(纸本)0818675829
UbiWorld is a concept that ties together the notion of Ubiquitous Computing (Ubicomp) with that of using virtual reality for rapid prototyping. The goal is to develop an environment where one can explore Ubicomp type concepts without having to build real Ubicomp hardware. The basic notion is to extend object models in a virtual world using distributed wide area heterogeneous computing technology to provide complex networking and processing capabilities to virtual reality objects.
暂无评论