Adaptive Granularity Research Articles

Adaptive Structural Index for Efficient Processing of XML Path Queries

This paper proposes an adaptive structural index: AS-Index (adaptive structural index), which can avoid the problem of the existing indexes. AS-Index is based on F&B-Index. It consists of F&B-Index, Query-Table and Part-Table. Frequent queries are kept in Query-Table avoiding redundant operations in query processing. Based on Query-Table an efficient bottom-up query processing is also proposed for answering infrequent queries using the frequent queries in Query-Table. Part-Table is used for optimizing the queries with descendant edges. The existing adaptive structural indexes need to traverse the whole document for adaptation, and their adaptation granularity is XML element node. For AS-Index, the adaptation granularity is F&B-Index node which includes a set of XML element nodes, and its adaptation is an efficient and incremental process that supports branch queries. The experimental results demonstrate that this index significantly outperforms the previous structural indexes in terms of query processing and adaptation efficiencies. For large XML documents, compared with the existing adaptive

인터넷 기반 클러스터 시스템 환경에서 부하공유 및 결함허용 알고리즘

인터넷 기반의 클러스터 시스템 환경에서 알고리즘의 이식성을 높이기 위해서는 네트워크의 특성 및 노드의 이질성에 따른 부하 불균형, 그리고 네트워크나 노드의 결함과 같은 다양한 수행환경의 변화에도 효과적으로 적응할 수 있어야 한다. 본 논문에서 제안하는 Expanded-WF 알고리즘은 Weighted Factoring 알고리즘을 기반으로 부하공유론 위하여 적응할당정책과 개선된 고정 분할 단위 알고리즘을 적용하고 결함허용을 위하여 작업을 중복 수행하는 기법을 적용한다. 적응할당정책으로는 느린 종노드의 작업을 빠른 종노드가 대신 수행하는 기법을 적용하였고, 개선된 고정 분할 단위 알고리즘은 네트워크의 통신시간과 계산시간을 겹치게 하는 것이다. 두 개의 네트워크 환경으로 구성된 이기종의 클러스터 환경에서 PVM을 이용한 행렬의 곱셈 프로그램으로 실험한 결과, 본 논문에서 제안한 알고리즘이 NOW 환경에서 효율적인 Send, GSS, Weighted Factoring 알고리즘보다 각각 55%, 63%, 그리고 20% 효율적임을 보였으며, 또한 결함허용도 가능함을 보였다. Since there are various networks and heterogeneity of nodes in Internet, the existing load-sharing algorithms are hardly adapted for use in Internet-based clustering systems. Therefore, in Internet-based clustering systems, a load-sharing algorithm must consider various conditions such as heterogeneity of nodes, characteristics of a network and imbalance of load, and so on. This paper has proposed an expanded-WF algorithm which is based on a WF (Weighted Factoring) algorithm for load-sharing in Internet-based clustering systems. The proposed algorithm uses an adaptive granularity strategy for load-sharing and duplicate execution of partial job for fault-tolerance. For the simulation, the to matrix multiplication using PVM is performed on the heterogeneous clustering environment which consists of two different networks. Compared to other algorithms such as Send, GSS and Weighted Factoring, the proposed algorithm results in an improvement of performance by 55%, 63% and 20%, respectively. Also, this paper shows that It can process the fault-tolerance.

Multirate video multicast over the Internet: an overview

Multirate multicast is an effective method for video distribution to a set of heterogeneous receivers. We present a comprehensive survey on multirate video multicast over the best effort Internet. We first review the key techniques in video encoding and network transport, and describe the representative approaches. We then study various trade-offs based on some important design issues and performance criteria, such as bandwidth economy, adaptation granularity, and coding complexity. Finally, we present some ongoing work and discuss possible avenues for future research.

Dynamic deficit round-robin scheduling scheme for variable-length packets

A dynamic deficit round-robin (DDRR) scheduling scheme for variable-length packets is proposed. It can resolve the drawback of the conventional deficit round-robin (DRR) scheduler that short-packet delay performance and high throughput cannot be satisfied simultaneously. DDRR uses an adaptive granularity for the deficit counter, where the granularity is dynamically changed according to packet lengths in queues. The algorithm, along with the simulation results showing the efficiency, are presented. The DDRR scheduler was implemented for 5 Tbit/s switching system.

Adaptive, fine-grained sharing in a client-server OODBMS

For reasons of simplicity and communication efficiency, a number of existing object-oriented database management systems are based on page server architectures; data pages are their minimum unit of transfer and client caching. Despite their efficiency, page servers are often criticized as being too retrictive when it comes to concurrency, as existing systems use pages as the minimum locking unit as well. In this paper we show how to support object-level locking in a page-server context. Several approaches are described, including an adaptive granularity approach that uses page-level locking for most pages but switches to object-level locking when finer-grained sharing is demanded. Each of the approaches is based on extending the idea of callback locking. We study the performance of these approaches, comparing them to both a pure page server and a pure object server. For the range of workload that we have examined, our results indicate that the adaptive page server provides very good performance, usually outperforming the pure page server and the other page-server variants as well. In addition, the adaptive page server is often preferable to the pure object server; our results provides insight into when each approach is likely to perform better.

Adaptive granularity: Transparent integration of fine- and coarse-grain communication

The granularity of shared data is one of the key factors affecting the performance of distributed shared memory machines (DSM). Given that programs exhibit quite different sharing patterns, providing only one or two fixed granularities cannot result in an efficient use of resources. On the other hand, supporting arbitrarily granularity sizes significantly increases not only hardware complexity but software overhead as well. Furthermore. the efficient use of arbitrarily granularities put the burden on users to provide information about program behavior to compilers and/or runtime systems. These kind of requirements tend to restrict the programmability of the shared memory model. In this paper, we present a new communication scheme, calledAdaptive Granularity (AG). Adaptive Granularity makes it possible to transparently integrate bulk transfer into the shared memory model by supporting variable-size granularity and memory replication. It consists of two protocols: one for small data and another for large data. For small size data, the standard hardware DSM protocol is used and the granularity is fixed to the size of a cache line. For large array data, the protocol for bulk data is used instead, and the granularity varies depending on the runtime sharing behavior of the applications. Simulation results show that AG improves performance up to 43% over the hardware implementation of DSM (e.g., DASH, Alewife). Compared with an equivalent architecture that supports fine-grain memory replication at the fixed granularity of a cache line (e.g., Typhoon), AG reduces execution time up to 35%.

Fine-grained sharing in a page server OODBMS

For reasons of simplicity and communication efficiency, a number of existing object-oriented database management systems are based on page server architectures; data pages are their minimum unit of transfer and client caching. Despite their efficiency, page servers are often criticized as being too restrictive when it comes to concurrency, as existing systems use pages as the minimum locking unit as well. In this paper we show how to support object-level locking in a page server context. Several approaches are described, including an adaptive granularity approach that uses page-level locking for most pages but switches to object-level locking when finer-grained sharing is demanded. We study the performance of these approaches, comparing them to both a pure page server and a pure object server. For the range of workloads that we have examined, our results indicate that a page server is clearly preferable to an object server. Moreover, the adaptive page server is shown to provide very good performance, generally outperforming the pure page server, the pure object server, and the other alternatives as well.

An adaptive granularity control algorithm for the parallel execution of functional programs

An on-line (run time), adaptive algorithm for granularity control of the parallel execution of functional programs is presented. This algorithm utilizes the inherent parallelism of functional programs, yet it endeavours to limit excessive parallelism. It can be applied to programs without any prior knowledge of their behaviour, and it does not require the programmer to add explicit parallel annotations. The algorithm takes advantage of the ability to expose, at run time, the shape of the underlying computation graph of the program. It also balances between the amount of local computation and the costs of remote execution. Based on these considerations, the algorithm allocates tasks to processing elements in a way that tries to minimize the overall execution time of the program. Continuous sampling of the computation graph allows self-tuning of the algorithm, when the underlying graph changes gradually.