Stringent performance requirements in DB applications have led to the use of parallelism for database processing. To allow the database system to take advantage of the performance of parallel shared-nothing systems, the physical DB design must be appropriate for the DB structure and the workload. We develop decision algorithms that will select a good physical DB design both when the DB is first loaded into the system (static decision) and while the DB is being used by the workload (dynamic decision). Our decision algorithms take the database structure, workload, and system characteristics as inputs. The static (or initial) physical DB design decision algorithm involves: • selecting a partitioning attribute for each relation that determines how the relation is fragmented across the nodes (allowing for high I/O bandwidth); • selecting indexes on the relation attributes to allow faster accesses compared to sequential file scans; • selecting the attributes by which to cluster a relation in order to take advantage of the prefetching and caching involved in I/O access; • grouping of relations to allow DB operations (joins) on relation pairs to be executed locally

Department of Computer Science. 32 200 words This thesis describes the novel features of an extended Linda system, called eLinda. The main contribution of eLinda is the introduction of a powerful and flexible mechanism for expressing the queries used for data retrieval in Linda systems. This provides simplicity for applications that would otherwise need to handle complex retrieval operations explicitly, and enhances efficiency, particularly where the data is distributed across a network. Other extensions introduce support for distributed multimedia resources, and provide additional support for efficient data distribution across a communication network. The enhanced functionality of the eLinda system is described in detail and compared with existing Linda systems, both commercial products and research projects. This is done primarily with an emphasis on the expressiveness

Software Distributed Shared Memory (S-DSM) can be used to build cost-effective high-performance computing platforms out of clusters of individual computers. In this project we propose to extend this to new applications, such as database and web servers, that currently have not been studied extensively for S-DSM. We also propose to study large-scale S-DSM systems for embedded platforms. An example application for such a large-scale system is a distributed surveillance system with several hundreds of intelligent nodes where each node collects data from its environment, processes the data and puts it in a shared database system. The project is a cooperation with Axis Communications AB in Lund which will contribute in a reference group and with equipment to build an embedded S-DSM system. 1 Introduction and

Multiprocessors are being used increasingly to support workloads in which some or all of the jobs are parallel. For these systems, new scheduling algorithms are required to allocate resources in such a way as to offer good response times while being capable of sustaining high system loads. Until recently, research in this area has focussed on processors as the critical resource, but for many parallel workloads, memory will likely also become a concern. In this thesis, we investigate the design of parallel-job scheduling disciplines, considering simultaneously processors and memory as critical resources. First, we demonstrate that preemption is a necessary feature of parallel-job schedulers in order to obtain good response times given the types of workloads found in practice. Next, we develop analytic bounds on the achievable system throughput with respect to both processing and memory for the case where no knowledge exists about the speedup characteristics of individual jobs. Through t...

Introduction Clusters of small-scale SMP computers are becoming more and more common as high-performance computing needs have arised, not only in national scientific laboratories, but also in enterprises of various kinds. An SMP-cluster represents a sweet-spot of cost-efficiency compared to a larger SMP system or to a cluster with smaller nodes. With the emergance of OpenMP, shared memory computing has also become mainstream in the parallel computing world. Unfortunately, clusters of SMPs do not directly support a shared memory programming model in hardware and software distributed shared memory (DSM) techniques must be adopted in order to run OpenMP on a cluster of SMP as well as on, e.g., a high-end Sun Enterprise server. This abstract describes a research project which has been initiated to alleviate some of the problems of running OpenMP applications on clusters of SMPs. The acronym Intone stands for Innovative Tools for Non-Experts. Although OpenMP is not stated in the project

The Aurora distributed shared data system implements a shared-data abstraction on distributedmemory platforms, such as clusters, using abstract data types. Aurora programs are written in C++ and instantiate shared-data objects whose data-sharing behaviour can be optimized using a novel technique called scoped behaviour. Each object and each phase of the computation (i.e., use-context) can be independently optimized with per-object and per-context flexibility. Within the scoped behaviour framework, optimizations such as bulk-data transfer can be implemented and made available to the application programmer.

Small organisations can now have access to high raw processing power using networks of workstations (NOW) as parallel computing pl atforms. Software Distributed Shared Memory (Software DSM) packages have been devel ped to facilq ate the programming of such systems. However, because of the high interprocessl atencies in a NOW, the performance of a software DSM appl ication is more susceptible to the partitioning of the problem than what might be expected. This paper presents an approach for a tool to visualise the execution of a program in a way that highl ights performance bottl enecks. The tool associates identified bottl enecks with the corresponding source codel ines in order to determine what piece of code is the cause of poor performance. The visual#R tion technique is demonstrated in two case studies. They cl ar l show that the visual isation is indeed useful and provides an effective way to acquire an understanding of what characterises an applications sharing behaviour.