With our society more information-driven, we have begun to distribute data in wide-area storage systems. At the same time, both physical failure and logic error have made it difficult to bring the necessary recovery t...
详细信息
ISBN:
(纸本)9780769537474
With our society more information-driven, we have begun to distribute data in wide-area storage systems. At the same time, both physical failure and logic error have made it difficult to bring the necessary recovery to bear on remote data disaster, and understanding this proceeding. We describe ARRAY, a system architecture for data disaster recovery that combines reliability, storage space, and security to improve performance for data recovery applications. The paper presents an exhaustive analysis of the design space of ARRAY systems, focusing on the trade-offs between reliability, storage space, security, and performance that ARRAY must make. We present RSRAII (Replication-based Snapshot Redundant Array of Independent Imagefiles) which is a configurable RAIDlike data erasure-coding, and also others benefits come from consolidation both erasure-coding and replication strategies. A novel algorithm is proposed to improve snapshot performance referred to as SMPDP (Snapshot based on Multi-Parallel Degree Pipeline).
With increasing defect density, microprocessors, especially the embedded caches, will encounter more faults. Adding spare resources to replace defective components is a widely accepted method for yield enhancement. In...
详细信息
We demonstrate a timing jitter compensation system by regulating the 10 th harmonic phase difference of mode locked laser pulses for long distance timing distribution. So far we have obtained 48-ps timing jitter of a...
详细信息
ISBN:
(纸本)9781424438303
We demonstrate a timing jitter compensation system by regulating the 10 th harmonic phase difference of mode locked laser pulses for long distance timing distribution. So far we have obtained 48-ps timing jitter of a 40-kilometer fiber link.
At present, e-commerce and e-services system can provide trust information about services provider performance to the customers in the near future. Such information is an accumulation value by long-term evaluation of ...
详细信息
At present, e-commerce and e-services system can provide trust information about services provider performance to the customers in the near future. Such information is an accumulation value by long-term evaluation of quality of service, but it does not reflect the Service's future trends. This paper presents an approach using a cubic fitting curve to simulate the quality of services by the least square method. This approach can calculate the QOS of the future point in time, helps the customer to understand intuitive trend of QOS, and to select the trust service.
With the growing popularity of XML and emergence of streaming data model, processing streaming XML has become an important topic. This paper proposes keyword search solution over XML fragment streams based on hole-fil...
详细信息
ISBN:
(纸本)9781424449095
With the growing popularity of XML and emergence of streaming data model, processing streaming XML has become an important topic. This paper proposes keyword search solution over XML fragment streams based on hole-filler model. Two efficient indexes, dual list and sketch are developed to further improve the performance: dual list indexes the candidate XML fragments to keep track of the relationship among fragments that include keywords and sketch summarizes the candidate XML elements to compute SLCA. SLCA computing algorithm, which is triggered by certain keywords, avoids redundant operations on computing the SLCA of elements that not contribute to the final result. The algorithm produces partial answers continuously without having to wait for the end of the stream. We illustrate the effectiveness of the algorithms developed with experiments.
Trace-driven cache simulation is the most widely used method to evaluate different cache structures. Several techniques have been proposed to reduce the simulation time of sequential trace-driven simulation. An obviou...
详细信息
Trace-driven cache simulation is the most widely used method to evaluate different cache structures. Several techniques have been proposed to reduce the simulation time of sequential trace-driven simulation. An obvious way to achieve fast parallel simulation is to simulate the individual independent sets of a cache concurrently on different compute resources. We propose improvements to current trace-driven simulation methods to make them faster and more economical. This paper considers the use of generic GPU to accelerate cache simulation which exploits set-partitioning as the main source of parallelism. We develop more efficient parallel simulation techniques by introducing more knowledge into the compute unified device architecture (CUDA) on the GPU. Our experimental result shows that the new algorithm can produce performance results for a number of set-associative caches in just a single simulation run and still produce the exact results.
This research aims to develop a combined sense system that uses both the sense of a force feedback as well as visual feedback in the shape of microscopic features from a micro sample. It is thought that the efficiency...
详细信息
The problem of planning the overlaps of multiple alternative configurations is critical to maximize the reliability of a reconfigurable fault-tolerant system based on field programmable gate arrays. To address the pro...
详细信息
ISBN:
(纸本)9781424443598
The problem of planning the overlaps of multiple alternative configurations is critical to maximize the reliability of a reconfigurable fault-tolerant system based on field programmable gate arrays. To address the problem, an unnecessary assumption made in previous work is removed and a second-order approximation domain-partition method is proposed. Experimental results on ITC99 benchmark circuits demonstrate the proposed technique outperforms previous work in failure rate with less memory cost to store configurations.
Domain-partition (DP) model is a general model for reliability maximization problem under given redundancy. In this paper, an improved DP model is used to formulate a reconfiguration computing based fault tolerant sys...
详细信息
Domain-partition (DP) model is a general model for reliability maximization problem under given redundancy. In this paper, an improved DP model is used to formulate a reconfiguration computing based fault tolerant system which is self-repairable in case of failure, and is solved as a nonlinear planning problem. The assumptions made in previous work are relaxed. An improved algorithm is proposed to reduce the time cost for calculating the reliability. Experiments on ITCpsila99 benchmark circuits are carried out. Results show the proposed approach outperforms previous works in failure rate with less memory cost to store configurations.
Lightpath reconfiguration management system has been designed and implemented for IP-over-CWDM networks with ROADMs. The system can search possible lightpaths made by ROADMs with specified switch states. The function ...
详细信息
暂无评论