For systems.containing a large number of processing elements (PEs), the capability to recover from a PE fault is important. The dynamic redundancy (DR) network can tolerate faults in the network and support a system t...
详细信息
ISBN:
(纸本)0818607491
For systems.containing a large number of processing elements (PEs), the capability to recover from a PE fault is important. The dynamic redundancy (DR) network can tolerate faults in the network and support a system that tolerates PE faults without degradation in performance by adding spare PEs, while retaining the full capability of a multistage cube. A variation of the DR network, the reduced DR (RDR) network, is presented which can be implemented more cost effectively while retaining most of the advantages of the DR. The reliability of systems.containing the DR or RDR networks and spare PEs and the reliability of systems.with no spare PEs are also estimated and compared. It is shown that using the DR or RDR network and spare PEs in a system can achieve better system reliability over a wide range of N, where N is the number of functioning PEs, than can using any kind of N multiplied by N fault-tolerant network and no spares.
The authors present and analyze a receiver-initiated scheduling algorithm for distributed soft real-time systems. The algorithm is based on a 'poll when underloaded' approach. Using simulation, the deadline mi...
详细信息
ISBN:
(纸本)0818607491
The authors present and analyze a receiver-initiated scheduling algorithm for distributed soft real-time systems. The algorithm is based on a 'poll when underloaded' approach. Using simulation, the deadline miss ratio and mean lateness of the algorithm are derived for different workloads and overheads. The performance profile of the algorithm shows stable behavior when load or management overheads are high. Its performance is compared with that of sender-initiated scheduling algorithm that uses a 'first-fit' strategy. The sender-initiated algorithm outperforms the receiver-initiated algorithm when the load is light. The results show that although there is a clear need for dynamic deadline-oriented scheduling at medium to high loads, a simple algorithm would suffice at low loads.
To meet the growing demand for online transaction processing, several DB (database management) and DC (data communication management) subsystems.can be coupled together to form a distributed DB/DC system. A recovery p...
详细信息
ISBN:
(纸本)0818607491
To meet the growing demand for online transaction processing, several DB (database management) and DC (data communication management) subsystems.can be coupled together to form a distributed DB/DC system. A recovery protocol is needed not only to provide for the recovery of transactions affected by the failure, but also to localize recovery operations. Two such protocols based on a progressive approach, namely, a synchronous progressive and an asynchronous progressive protocol, along with a pessimistic protocol, are analyzed. Their performance during normal transaction processing is contrasted with that of a transaction processing system without any recovery protocol. A queuing model is developed and simulated to predict the transaction response time. The progressive recovery approach is found to reduce normal processing overhead and lead to performance improvement over the pessimistic approach.
Next generation military and commercial engine control systems.are planned to be distributed engine control (DEC) systems. Many technology improvements will be required to achieve a successful DEC that provides the hi...
详细信息
As a basic reliability guarantee technology in distributedsystems. failure detection provides the ability of timely detecting the liveliness of runtime systems. Effective Failure Detection is very important to J2EE a...
详细信息
The proceedings contain 25 papers. The special focus in this conference is on software tool and its development. The topics include: purely functional global variables;compiler support for profiling C++ template metap...
ISBN:
(纸本)9789949231782
The proceedings contain 25 papers. The special focus in this conference is on software tool and its development. The topics include: purely functional global variables;compiler support for profiling C++ template metaprograms;database-driven tool support for DisCo executable specifications;a multi-layer diagrammatic (Meta) modelling environment;the INTEGRA tool integration framework;a model for language-independent mobile agents;layered artificial intelligence framework for autonomous agents;interleaving human and search-based software architecture design;class and object model conformance using OWL2 reasoners;bounded saturation based CTL model checking;automated code synthesis for run-time verification of distributed embedded systems.a declarative approach to solving challenging search problems;personalized side-quest generation for computer role-playing games;adjusting effort estimation using micro-productivity profiles;quantitative system reliability approach for optimizing IT security costs in an AI environment;component reuse in ensemble-based medical image processing applications;extended choice relation framework for workflow testing and towards more reliable C++ template metaprograms.
The proceedings contain 13 papers. The special focus in this conference is on Benchmarking, Measuring, and Optimizing. The topics include: Artemis: An Automatic Test Suite Generator for Large Scale OLAP database;OStor...
ISBN:
(纸本)9783030710576
The proceedings contain 13 papers. The special focus in this conference is on Benchmarking, Measuring, and Optimizing. The topics include: Artemis: An Automatic Test Suite Generator for Large Scale OLAP database;OStoreBench: Benchmarking distributed Object Storage systems.Using Real-World Application Scenarios;ConfAdvisor: An Automatic Configuration Tuning Framework for NoSQL database Benchmarking with a Black-box Approach;Optimization of the Himeno Benchmark for SX-Aurora TSUBASA;Parallel Sorted Sparse Approximate Inverse Preconditioning Algorithm on GPU;preface;characterizing the Sharing Behavior of Applications Using software Transactional Memory;ComScribe: Identifying Intra-node GPU Communication;a Benchmark of Ocular Disease Intelligent Recognition: One Shot for Multi-disease Detection;MAS3K: An Open Dataset for Marine Animal Segmentation;benchmarking Blockchain Interactions in Mobile Edge Cloud softwaresystems.
In this paper, we present our approach to developing global picture archiving and communication system (PACS) remote consultation and diagnosis (RCD) application using the Open software Foundation (OSF) distributed Co...
详细信息
ISBN:
(纸本)0819417831
In this paper, we present our approach to developing global picture archiving and communication system (PACS) remote consultation and diagnosis (RCD) application using the Open software Foundation (OSF) distributed Computing Environment (DCE) services and toolkits. The current RCD system now uses programming services similar to those offered by OSF DCE, the Cell Directory Service, the distributed Time Service, the Security Service, the RPC Facility, and the Threads Facility. In this research we have formally applied OSF DCE services to the Global PACS RCD software. The use of OSF DCE services for Global PACS enables us to develop a robust distributed structure and new user services which feature reliability and scalability for Global PACS environments.
The popularity of online free album services in the recent prevailing Web2.0 paradigm has posed great challenges to the existing image storage systems. In this paper, we analyze the characteristics of online image sto...
详细信息
ISBN:
(纸本)9780769529097
The popularity of online free album services in the recent prevailing Web2.0 paradigm has posed great challenges to the existing image storage systems. In this paper, we analyze the characteristics of online image storage techniques from a system perspective. We present a novel framework called OBSI, which stands for an object based storage system for storing and retrieving images of online album services. In the design of OBSI, we employ a novel divide and conquer approach which subdivides OBSI into two layers: an object layer and a chunk layer. The chunk layer handles the "dirty work", such as disk space management and reliability guarantee. The object layer provides a uniform object storage and retrieval interface to applications. OBSI reduces disk access by employing a simple and yet effective storage allocation algorithm which allocates storage objects continuously as clustered to their respective metadata Experimental results show that OBSI provides high efficiency and throughput in image storage and retrieval services.
As the scale of high performance computing systems.grows, three main challenges arise: the programmability, reliability, and energy efficiency of those systems. Accomplishing all three without sacrificing performance ...
详细信息
暂无评论