Summary form only given. The authors describe a hardware and software architectural model for the characterization and analysis of genomes of select organisms. The data for research is obtained by semantically relatin...
详细信息
Summary form only given. The authors describe a hardware and software architectural model for the characterization and analysis of genomes of select organisms. The data for research is obtained by semantically relating existing heterogeneous genetic databases. The authors have developed an architectural model based on associative memory structures at the hardware level and an object-oriented model at the software level. Simulation studies are under way to establish the appropriateness of a system based on a set of tagged associative processors operating in parallel which can be used for gene sequencing and analysis. They have identified primitive instructions on the machine which are consonant with biologists' map manipulation and usage requirements.< >
Presents an algorithm for parallel hash-join computation on main-memory databases that adapts to data skew, and its implementation on the IBM RP3 multiprocessor. The algorithm exploits the random access capabilities o...
详细信息
Presents an algorithm for parallel hash-join computation on main-memory databases that adapts to data skew, and its implementation on the IBM RP3 multiprocessor. The algorithm exploits the random access capabilities of main memory databases to detect and counteract skew on the fly. Data skew is detected at run time by monitoring the observed frequencies of values of the join attribute and applying to them a threshold function that takes account of the distribution of workload among processors. If and when this threshold is reached for certain values of the join attribute, the computation corresponding to it is fragmented among an appropriate number of processors. Fragmentation requires some replication of input tuples-modestly increasing the total workload, but reduces the completion time significantly by reducing workload at the overloaded processor. A simplified analysis is supplemented by experiments. The description and analysis of the algorithm are based on the shared-nothing model. The implementation uses hierarchical shared memory providing non-uniform memory access.< >
This paper describes new load balancing algorithms for parallel database processing on shared memory multiprocessors. The goal of load balancing is to reduce overhead as well as load imbalance, but there is a tradeoff...
详细信息
This paper describes new load balancing algorithms for parallel database processing on shared memory multiprocessors. The goal of load balancing is to reduce overhead as well as load imbalance, but there is a tradeoff between them in ordinary algorithms. Unfortunately, optimum performance can hardly be obtained using ordinary algorithms because their performances depend on several factors such as database size, the number of processors and data distribution. The proposed algorithms solve these problems by varying the number of tasks allocated at a time ( which was fixed in ordinary algorithms ) according to the number of remaining tasks and the maximum and minimum processing times of a task. Performance evaluations show that the proposed algorithms achieve fair load balancing with lower overhead independent of the above factors.< >
Summary form only given. The Hubble space telescope (HST) Ingest program reads files representing external database tables of any topology, normalizes or joins the tables to the HST catalog database topology, parses a...
详细信息
Summary form only given. The Hubble space telescope (HST) Ingest program reads files representing external database tables of any topology, normalizes or joins the tables to the HST catalog database topology, parses and converts data values, and writes the tuples to the HST catalog. Ingest is driven by translation tables defining the interdatabase mapping and can be altered on-the-fly. Ingest has proven to be a powerful tool in an environment where multiple databases rapidly evolve.< >
Rule interpreters usually start with an initial database and perform the inference procedure in cycles, ending with a final database. In a real time environment it is possible to receive updates to the initial databas...
详细信息
The authors have show previously (1989, 1991) that processing OODBs can be viewed as the manipulation of patterns of object associations. parallel, multiple wavefront algorithms based on an identification approach for...
详细信息
The authors have show previously (1989, 1991) that processing OODBs can be viewed as the manipulation of patterns of object associations. parallel, multiple wavefront algorithms based on an identification approach for verifying association patterns have been introduced. The current paper presents an elimination approach for processing OODBs. The new approach allows more processors to operate concurrently on a query, thus allowing a higher degree of parallelism in query processing. A formal proof of the correctness of the new approach is given, and a parallel elimination algorithm for processing tree queries is presented. Some simulation results are also provided to compare the performance of the identification approach with the elimination approach.< >
Summary form only given. The authors propose an efficient data organization for the storage and subsequent retrieval of large volume of cartographic data. The concept of address squares has been used extensively. The ...
详细信息
Summary form only given. The authors propose an efficient data organization for the storage and subsequent retrieval of large volume of cartographic data. The concept of address squares has been used extensively. The inherent parallelism in the data has been explored in order to improve computational efficiency. Several parallel algorithms related to the analysis of the cartographic data based on the proposed data organisation, have also been presented.< >
When data are uniformly distributed, parallel join algorithms scale up well. However, scalability is curtailed by data skew-nonuniform distribution of data between processors. Investigation of this problem has been ha...
详细信息
When data are uniformly distributed, parallel join algorithms scale up well. However, scalability is curtailed by data skew-nonuniform distribution of data between processors. Investigation of this problem has been hampered by incomplete understanding of data skew as well as inadequate analytic performance models. The authors use a new model of data skew that addresses these shortcomings to examine the effects of skewed workloads on the scalability of the hybrid hash, scheduling hash, and sort-merge parallel join algorithms. Results indicate that the extent to which data skew degrades scalability varies with the join algorithm, the workload and the type of data skew. None of the three algorithms has the best scalability and response time in all cases.< >
A new decentralized commit protocol is proposed for distributed database systems. This protocol can be applied to any size of systems and is (log/sub 2/N)-2 resilient to site failures where N is the number of sites in...
详细信息
ISBN:
(纸本)081862275X
A new decentralized commit protocol is proposed for distributed database systems. This protocol can be applied to any size of systems and is (log/sub 2/N)-2 resilient to site failures where N is the number of sites in the system. In addition, the number of messages sent among N sites is O(N log/sub 2//sup 2/N) which is only a factor of log/sub 2/ N over the message complexity lower bound O(N ln N).< >
Presents a new approach to parallel computation of transitive closure queries using a semantic data fragmentation. Tuples of a large base relation denote edges in a graph, which models a transportation network. A frag...
详细信息
Presents a new approach to parallel computation of transitive closure queries using a semantic data fragmentation. Tuples of a large base relation denote edges in a graph, which models a transportation network. A fragmentation algorithm is proposed which produces a partitioning of the base relation into several fragments such that any fragment corresponds to a subgraph. One fragment, called high-speed fragment, collects all edges which guarantee maximum speed. Thus, the fragmentation algorithm induces a hierarchical relationship between the high-speed fragment and all other fragments. With this fragmentation, any query about paths connecting two nodes can be answered by using just the fragments in which nodes are located and the high-speed fragment. In general, if each fragment is managed by a distinguished processor, then the query can be answered by three processors working in parallel. This schema can be applied recursively to generate an arbitrary number of hierarchical levels.< >
暂无评论