Publications
110 results found
Furmento N, Mayer A, McGough S, et al., 2001, An integrated grid environment for component applications, Berlin, 2nd international workshop on grid computing, GRID 2001, Denver, CO, Publisher: Springer, Pages: 26-37
Computational grids present many obstacles to their effective exploitation by non-trivial applications. We present a grid middleware, implemented using Java and Jini, that eliminates these obstacles through the intelligent use of meta-data relating to the structure, behaviour and performance of an application. We demonstrate how different problem sizes and selection criteria (minimum execution time or minimum cost) utilise different implementations for the optimal solution of a set of linear equations.
Furmento N, Mayer A, McGough S, et al., 2001, Optimisation of component-based applications within a grid environment (Available on CD-ROM), Denver, Colorado, Supercomputing '01: proceedings of the 2001 ACM/IEEE conference on Supercomputing, Publisher: ACM Press, Pages: 30-30
Chung AJ, Field T, 2001, A Simple Recursive Tesselator, Journal of Graphics Tools, Vol: 5, Pages: 1-9
Kelly PHJ, Beckmann O, Field T, et al., 2001, THEMIS: component dependence metadata in adaptive parallel computations, Parallel Processing Letters, Vol: 11, Pages: 455-470, ISSN: 0129-6264
Furmento N, Mayer A, McGough S, et al., 2001, An integrated grid environment for component applications, Berlin, 2nd international workshop on grid computing, GRID 2001, Denver, CO, Publisher: Springer, Pages: 26-37
Field AJ, Hansen TL, Kelly PHJ, 2000, Run-time fusion of MPI calls in a parallel C++ library, LCPC2000, The 13th International Workshop on Languages and Compilers for High-Performance Computing, Yorktown Heights
Cheadle AM, Field AJ, Marlow S, et al., 2000, Non-stop Haskell, Proc. Int. Conf. on Functional Programming, Montreal, Pages: 257-267
Field AJ, Harrison PG, 1999, Sojourn Times in a Random Queue With and Without Preemption, European Journal of Operational Research, Vol: 112, Pages: 646-653
Al-Battran S, Wiley RL, Woods J, et al., 1999, Parallel Simulation of Plankton Ecology, Proc. IASTED International Conference on Modelling and Simulation, Philadelphia, Pages: 259-263
Burton AD, Field AJ, To HW, 1998, A Cell-Cell Barnes Hut Algorithm for Fast Particle Simulation, Australian Computer Science Communications, Vol: 20, Pages: 267-278
Field T, Harrison P, Kanani K, 1998, Automatic Generation of Verifiable Cache Coherence Simulation Models from High-level Specifications, Australian Computer Science Communications, Vol: 20, Pages: 261-275
Performance modelling and verification are vital steps in the development cycle of any cache coherency protocol. Two separate models are usually required to perform each analysis step and as protocols become increasingly complex each can become correspondingly unwieldy. We examine how stochastic process algebra can be used to describe cache coherency protocols in such a way as to allow both the correctness and performance of the protocol to be investigated together. We reintroduce a ...
Field AJ, Harrison PG, Kanani K, 1998, Automatic generation of verifiable cache coherence simulation models from high-level specifications, 4th Australasian Theory Symposium (CATS 98), Publisher: SPRINGER-VERLAG SINGAPORE PTE LTD, Pages: 261-275
- Author Web Link
- Cite
- Citations: 2
Harrison PG, Field AJ, 1998, Sojourn Times in a Random Queue with and without, European Journal of Operations Research
Field AJ, Harrison PG, Parry J, 1998, Response times in client-server systems, 10th International Conference on Computer Performance Evaluation - Modelling Techniques and Tools (Tools 98), Publisher: SPRINGER-VERLAG BERLIN, Pages: 75-92, ISSN: 0302-9743
Field AJ, Harrison PG, 1997, A Stochastic Model of Cache Coherency Overhead in SCI, IEE Proceedings on Computers and Digital Techniques, Vol: 144, Pages: 175-186
We present a new analytical performance model of the IEEE P1596 Standard Coherent Interface, which is a distributed cache coherency protocol for shared memory multiprocessors. We focus upon an implementation of the protocol on a unidirectional ring architecture (the default architecture for SCI systems). We identify the possible memory and cache line states and corresponding processor actions for a memory access and derive the equilibrium line state probabilities by solving a Markov model expressed as a set of fixed point equations. The probabilities of a processor performing a particular action then follow, from which the message transmission profile for each processor is derived. These traffic equations are then fed into an M/G/1 model for the ring architecture in which the ring traffic at a node has priority over traffic originating in that node. Further analysis then leads to the mean message transmission time, and hence the mean memory access time, and processor utilisation. We illustrate the application of the model by undertaking a performance comparison of two alternative node architectures and report some numerical results for various parameterisations.\r\n
Field AJ, Kelly PHJ, Qian W, 1997, M-Tree: A Parallel Abstract Data Type for Block-Irregular Adaptive Applications, EuroPar'97, Publisher: Springer
Field AJ, Harrison PG, 1997, Stochastic Model of Cache Coherency Overhead in SCI, IEE Proceedings Transactions on Computers and Digital Techniques, Vol: 144
Chung AJ, Field AJ, 1997, Rendering Radiosity Solutions by Adaptive Gathering, Journal of Graphics Tools, Vol: 2, Pages: 31-44
Field T, Warren S, Woods J, et al., 1997, Parallel Simulation of Complex Plankton Ecosystems, Fujitsu Parallel Computing Workshop
In an attempt to understand the dynamics of plankton populations in the world's oceans and to study the effect of environmental changes on plankton ecosystems, a case tool has been developed to enable biologists to construct arbirarily complex simulations of a closed volume of sea water over an extended period. This Virtual Ecology Workbench (VEW) enables pre-coded science modules to be plugged together using a graphical user interface, the resulting software configuration being compiled automatically into a single sequential C code. Here we discuss the characteristics of the generated code and describe a number of parallelisation strategies for speeding up the dominant "Lagrangian" components of the simulation. The parallelisation is achieved in a modular fashion using MPI, requiring minimal changes to the structure of the existing VEW system. The target platform is Fujitsu AP1000, although the code will execute on any platform supporing MPI. The parallelisation offers the potential to perform very large and detailed simulations, significantly beyond the scope of the existing sequential code.\r\n
Field AJ, Kelly PHJ, Qian W, 1997, M-Tree: A Parallel Abstract Data Type for Block-Irregular Adaptive Applications, EuroPar'97, Publisher: Springer
Field T, Harrison P, 1996, Modelling and validation of shared memory coherency protocols, Performance Evaluation, Vol: 27, Pages: 541-563
Field T, Harrison P, 1996, Modelling and validation of shared memory coherency protocols, Performance Evaluation, Vol: 27, Pages: 541-563
Field A, Hutton JAR, 1996, The integration of functional languages and relational databasess, Departmental Technical Report: 96/3, Publisher: Department of Computing, Imperial College London
The rapid increase in the use and size of relational databases is demanding increasingly fast and efficient database management systems. There is currently considerable research effort being directed towards the use of parallel processing to provide such performance improvements.Here we extend the Haskell language and its compiler to support SQL database queries as the first step towards performing query processing in a parallel function environment. SQL queries are generated from the translation of Haskell list comprehensions at compile-time and are used to query a relational database at run-time thereby allowing a Haskell program to access and process data stored in a relational database. We shown that query processing can be partitioned between the SQL and Haskell domains and conclude that if query processing is migrated into the Haskell domain with both domains supported on the same hardware platform then access performance is reduced. However, it is proposed that if separate platforms, and in particular a parallel Haskell platform are used to support the two processing domains, then increased performance should be possible. Finally we explore some other areas of interest such as lazy database access and dynamic query construction that might be the subject further work.
Field T, Hutton J, 1996, The Integration of Functional Programming Languages and Relational Databases
Wu Q, Field AJ, Kelly PHJ, 1996, Data abstraction for parallel adaptive computation, 1996 Workshop on Abstract Machine Models for Parallel and Distributed Computing, Publisher: I O S PRESS, Pages: 105-118, ISSN: 1383-7575
Bennett AJ, Field AJ, Harrison PG, 1996, Modelling and Validation of Shared Memory Coherency Protocols, Proceedings of PERFORMANCE '96, International Conference on Performance Theory, Measurement and Evaluation of Computer and Communication Systems, Lausanne, IFIP WG7.3
Field AJ, Harrison PG, 1996, A Methodology for the Performance Modelling of Distributed Cache Coherent Multiprocessors, The State-of-the-art in Performance Modeling and Simulation, Editors: Bagchi, Walrand, Zobrist, Bagchi, Walrand, Zobrist, Publisher: Gordon and Breach, Pages: 55-92
Kanani K, Field AJ, Harrison PG, 1996, Performance Modelling and Verification of Cache Coherency Protocols using Stochastic Process Algebra, 4th Workshop on Process Algebras and Performance Modelling
Field T, Harrison P, 1995, An Analytical Model of the Standard Coherent Interface "SCI"., 1995 International Conference on Parallel Processing, August 14-18, 1995, Urbana-Champain, Illinois, USA, Pages: 173-177
Field AJ, Harrison PG, 1995, An Analytical Model of the Standard Coherent Interface 'SCI, Proceedings of the International Conference on Parallel Processing, Oconomowoc, Wisconsin, Pages: 173-177
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.