CAFS in action

For those few readers who do not know, CAFS is a system developed by ICL to search through data at speeds of several million characters per second. Its full name is Content Addressable File Store Information Search Processor, CAFS-ISP or CAFS for short. It is an intelligent hardware-based searching engine, currently available with both ICL's 2966 family of computers and the recently announced Series 39, operating within the VME environment. It uses content addressing techniques to perform fast searches of data or text stored on discs: almost all fields are equally accessible as search keys. Software in the mainframe generates a search task; the CAFS hardware performs the search, and returns the hit records to the mainframe. Because special hardware is used, the searching process is very much more efficient than searching performed by any software method. Various software interfaces are available which allow CAFS to be used in many different situations. CAFS can be used with existing systems without significant change. It can be used to make online enquiries of mainframe files or databases or directly from user written high level language programs. These interfaces are outlined in the body of the report.

Working memory and working attention: What could possibly evolve?

The concept of “working” memory is traceable back to nineteenth century theorists (Baldwin, 1894; James 1890) but the term itself was not used until the mid-twentieth century (Miller, Galanter & Pribram, 1960). A variety of different explanatory constructs have since evolved which all make use of the working memory label (Miyake & Shah, 1999). This history is briefly reviewed and alternative formulations of working memory (as language-processor, executive attention, and global workspace) are considered as potential mechanisms for cognitive change within and between individuals and between species. A means, derived from the literature on human problem-solving (Newell & Simon, 1972), of tracing memory and computational demands across a single task is described and applied to two specific examples of tool-use by chimpanzees and early hominids. The examples show how specific proposals for necessary and/or sufficient computational and memory requirements can be more rigorously assessed on a task by task basis. General difficulties in connecting cognitive theories (arising from the observed capabilities of individuals deprived of material support) with archaeological data (primarily remnants of material culture) are discussed.

Information processing: US Patent 4,409,617

An information processor for rendering input data compatible with standard video recording and/or display equipment, comprizing means for digitizing the input data over periods which are synchronous with the fields of a standard video signal, a store adapted to store the digitized data and release stored digitized data in correspondence wiht the line scan of a standard video monitor, the store having two halves which correspond to the interlaced fields of a standard video signal and being so arranged that one half is filed while the other is emptied, and means for converting the released stored digitized data into video luminance signals. The input signals may be in digital or analogue form. A second stage which reconstitutes the recorded data is also described.

A narrow band pulsed eddy current instrument for materials testing

The principles of operation of an experimental prototype instrument known as J-SCAN are described along with the derivation of formulae for the rapid calculation of normalized impedances; the structure of the instrument; relevant probe design parameters; digital quantization errors; and approaches for the optimization of single frequency operation. An eddy current probe is used As the inductance element of a passive tuned-circuit which is repeatedly excited with short impulses. Each impulse excites an oscillation which is subject to decay dependent upon the values of the tuned-circuit components: resistance, inductance and capacitance. Changing conditions under the probe that affect the resistance and inductance of this circuit will thus be detected through changes in the transient response. These changes in transient response, oscillation frequency and rate of decay, are digitized, and then normalized values for probe resistance and inductance changes are calculated immediately in a micro processor. This approach coupled with a minimum analogue processing and maximum of digital processing has advantages compared with the conventional approaches to eddy current instruments. In particular there are: the absence of an out of balance condition and the flexibility and stability of digital data processing.

Global hydrology modelling and uncertainty: running multiple ensembles with a campus grid.

Uncertainties associated with the representation of various physical processes in global climate models (GCMs) mean that, when projections from GCMs are used in climate change impact studies, the uncertainty propagates through to the impact estimates. A complete treatment of this ‘climate model structural uncertainty’ is necessary so that decision-makers are presented with an uncertainty range around the impact estimates. This uncertainty is often underexplored owing to the human and computer processing time required to perform the numerous simulations. Here, we present a 189-member ensemble of global river runoff and water resource stress simulations that adequately address this uncertainty. Following several adaptations and modifications, the ensemble creation time has been reduced from 750 h on a typical single-processor personal computer to 9 h of high-throughput computing on the University of Reading Campus Grid. Here, we outline the changes that had to be made to the hydrological impacts model and to the Campus Grid, and present the main results. We show that, although there is considerable uncertainty in both the magnitude and the sign of regional runoff changes across different GCMs with climate change, there is much less uncertainty in runoff changes for regions that experience large runoff increases (e.g. the high northern latitudes and Central Asia) and large runoff decreases (e.g. the Mediterranean). Furthermore, there is consensus that the percentage of the global population at risk to water resource stress will increase with climate change.

An analysis of real time implementation of Fourier transform-based frequency recognition algorithms

Frequency recognition is an important task in many engineering fields such as audio signal processing and telecommunications engineering, for example in applications like Dual-Tone Multi-Frequency (DTMF) detection or the recognition of the carrier frequency of a Global Positioning, System (GPS) signal. This paper will present results of investigations on several common Fourier Transform-based frequency recognition algorithms implemented in real time on a Texas Instruments (TI) TMS320C6713 Digital Signal Processor (DSP) core. In addition, suitable metrics are going to be evaluated in order to ascertain which of these selected algorithms is appropriate for audio signal processing(1).

Nested parallelism for multi-core HPC systems using Java

Since its introduction in 1993, the Message Passing Interface (MPI) has become a de facto standard for writing High Performance Computing (HPC) applications on clusters and Massively Parallel Processors (MPPs). The recent emergence of multi-core processor systems presents a new challenge for established parallel programming paradigms, including those based on MPI. This paper presents a new Java messaging system called MPJ Express. Using this system, we exploit multiple levels of parallelism - messaging and threading - to improve application performance on multi-core processors. We refer to our approach as nested parallelism. This MPI-like Java library can support nested parallelism by using Java or Java OpenMP (JOMP) threads within an MPJ Express process. Practicality of this approach is assessed by porting to Java a massively parallel structure formation code from Cosmology called Gadget-2. We introduce nested parallelism in the Java version of the simulation code and report good speed-ups. To the best of our knowledge it is the first time this kind of hybrid parallelism is demonstrated in a high performance Java application. (C) 2009 Elsevier Inc. All rights reserved.

Processors (WO 2010/082067 A2)

A processing system comprises a plurality of processors (12) and communication means (20) arranged to carry messages between the processors, wherein each of the processors (12) has an operating instruction memory field (32, 34, 36) arranged to hold stored operating instructions including a re-routing target address. Each processor is arranged to receive a message (38) including operating instructions including a target address. On receipt of the message, each processor is arranged to: check the target address in the message to determine whether it corresponds to an address associated with the processor; if the target address in the message does correspond to an address associated with the processor, to check the operating instructions in the message to determine whether the message is to be re-routed; and, if the message is to be re-routed, to replace operating instructions within the message with the stored operating instructions, and place the message on the communication means for delivery to the re-routing target address.

An MPI-based implementation of intelligent agents on clusters

Recent research in multi-agent systems incorporate fault tolerance concepts, but does not explore the extension and implementation of such ideas for large scale parallel computing systems. The work reported in this paper investigates a swarm array computing approach, namely 'Intelligent Agents'. A task to be executed on a parallel computing system is decomposed to sub-tasks and mapped onto agents that traverse an abstracted hardware layer. The agents intercommunicate across processors to share information during the event of a predicted core/processor failure and for successfully completing the task. The feasibility of the approach is validated by implementation of a parallel reduction algorithm on a computer cluster using the Message Passing Interface.

Intelligent agents for fault tolerance: from multi-agent simulation to cluster-based implementation

Recent research in multi-agent systems incorporate fault tolerance concepts, but does not explore the extension and implementation of such ideas for large scale parallel computing systems. The work reported in this paper investigates a swarm array computing approach, namely 'Intelligent Agents'. A task to be executed on a parallel computing system is decomposed to sub-tasks and mapped onto agents that traverse an abstracted hardware layer. The agents intercommunicate across processors to share information during the event of a predicted core/processor failure and for successfully completing the task. The feasibility of the approach is validated by simulations on an FPGA using a multi-agent simulator, and implementation of a parallel reduction algorithm on a computer cluster using the Message Passing Interface.

A cluster-based implementation of a fault-tolerant parallel reduction algorithm using swarm-array computing

Recent research in multi-agent systems incorporate fault tolerance concepts. However, the research does not explore the extension and implementation of such ideas for large scale parallel computing systems. The work reported in this paper investigates a swarm array computing approach, namely ‘Intelligent Agents’. In the approach considered a task to be executed on a parallel computing system is decomposed to sub-tasks and mapped onto agents that traverse an abstracted hardware layer. The agents intercommunicate across processors to share information during the event of a predicted core/processor failure and for successfully completing the task. The agents hence contribute towards fault tolerance and towards building reliable systems. The feasibility of the approach is validated by simulations on an FPGA using a multi-agent simulator and implementation of a parallel reduction algorithm on a computer cluster using the Message Passing Interface.

Parallelism in control

A parallel structure is suggested for feedback control systems. Such a technique can be applied to either single or multi-sensor environments and is ideally suited for parallel processor implementation. The control input actually applied is based on a weighted summation of the different parallel controller values, the weightings being either fixed values or chosen by an adaptive decision-making mechanism. The effect of different controller combinations is a field now open to study.

Neural networks for power systems alarm handling

A multi-layered architecture of self-organizing neural networks is being developed as part of an intelligent alarm processor to analyse a stream of power grid fault messages and provide a suggested diagnosis of the fault location. Feedback concerning the accuracy of the diagnosis is provided by an object-oriented grid simulator which acts as an external supervisor to the learning system. The utilization of artificial neural networks within this environment should result in a powerful generic alarm processor which will not require extensive training by a human expert to produce accurate results.

New fast SCFT algorithm applied to binary diblock copolymer/homopolymer blends

We present an efficient strategy for mapping out the classical phase behavior of block copolymer systems using self-consistent field theory (SCFT). With our new algorithm, the complete solution of a classical block copolymer phase can be evaluated typically in a fraction of a second on a single-processor computer, even for highly segregated melts. This is accomplished by implementing the standard unit-cell approximation (UCA) for the cylindrical and spherical phases, and solving the resulting equations using a Bessel function expansion. Here the method is used to investigate blends of AB diblock copolymer and A homopolymer, concentrating on the situation where the two molecules are of similar size.

PDM 2006: Proceedings of the International Workshop on Data Mining

Recently major processor manufacturers have announced a dramatic shift in their paradigm to increase computing power over the coming years. Instead of focusing on faster clock speeds and more powerful single core CPUs, the trend clearly goes towards multi core systems. This will also result in a paradigm shift for the development of algorithms for computationally expensive tasks, such as data mining applications. Obviously, work on parallel algorithms is not new per se but concentrated efforts in the many application domains are still missing. Multi-core systems, but also clusters of workstations and even large-scale distributed computing infrastructures provide new opportunities and pose new challenges for the design of parallel and distributed algorithms. Since data mining and machine learning systems rely on high performance computing systems, research on the corresponding algorithms must be on the forefront of parallel algorithm research in order to keep pushing data mining and machine learning applications to be more powerful and, especially for the former, interactive. To bring together researchers and practitioners working in this exciting field, a workshop on parallel data mining was organized as part of PKDD/ECML 2006 (Berlin, Germany). The six contributions selected for the program describe various aspects of data mining and machine learning approaches featuring low to high degrees of parallelism: The first contribution focuses the classic problem of distributed association rule mining and focuses on communication efficiency to improve the state of the art. After this a parallelization technique for speeding up decision tree construction by means of thread-level parallelism for shared memory systems is presented. The next paper discusses the design of a parallel approach for dis- tributed memory systems of the frequent subgraphs mining problem. This approach is based on a hierarchical communication topology to solve issues related to multi-domain computational envi- ronments. The forth paper describes the combined use and the customization of software packages to facilitate a top down parallelism in the tuning of Support Vector Machines (SVM) and the next contribution presents an interesting idea concerning parallel training of Conditional Random Fields (CRFs) and motivates their use in labeling sequential data. The last contribution finally focuses on very efficient feature selection. It describes a parallel algorithm for feature selection from random subsets. Selecting the papers included in this volume would not have been possible without the help of an international Program Committee that has provided detailed reviews for each paper. We would like to also thank Matthew Otey who helped with publicity for the workshop.