The memory requirements of digital signal processing and multimedia applications have grown steadily over the last several decades. From embedded systems to supercomputers, the design of computing platforms involves a balance between processing elements and memory sizes to avoid the memory wall. This paper presents an algorithm based on both dataflow and approximate computing approaches in order to find a good balance between the memory requirements of an application and the quality of the result. The designer of the computing system can use these evaluations early in the design process to make hardware and software design decisions. The proposed method does not require any modification in the algorithm's computations, but optimises how data are fetched from and written to memory. We show in this paper how the proposed algorithm saves 27.7% of memory for the full SKA SDP signal processing computing pipeline, and up to 68.75% for a wavelet transform in embedded systems.

The Square Kilometre Array is the world's largest mega-Science project of the next decade aiming to build enormous radio telescope arrays across Western Australia and Southern Africa. With 160 TeraByte/sec data generated in just stage one of the 50 year project and over 260 PetaFLOPS compute requirements it presents unprecedented data movement and processing challenges in its correlators, the detection and timing of pulsars, supercomputing pipelines for generating images, and scalable middleware. This talk will outline the project and its scientific goals, some of the key data processing pipelines, and will discuss the progress made by the design teams toward overcoming its computing challenges.

A texture descriptor is a collection of quantified measurements of a texture's properties. They are used to describe how the basic unit of a texture is repeated in an image, such as the pattern size, pattern linelikeness, directional unification and directionality. These quantified measures have often been calculated in the spatial domain. This paper proposes a new approach of calculating texture deature descriptors in the frequency domain. It also introduces new texture feature descriptors, which describe how the unit of texture is repeated global throughout the image, such as pattern formation linelikeness and repetition directionality.

The Square Kilometre Array (SKA) will push the boundaries of radio astronomy. As such, it will need enormous computing power to process the tremendous amount of data it will produce. Significant savings in computing could be made if some of this processing was done in single-precision. This paper presents our end-to-end modelling of the SKA Imaging Pipeline. We model the signals received by the Central Signal Processor (CSP) using our Sky Generator Model. We then process the sky signals with our CSP Correlator Model to generate the visibilities that are passed to the Science Data Processor (SDP). These visibilities are gridded Fourier transformed by our SDP Imaging Model to produce a dirty image. This dirty image is then deconvolved to produce an image of the sky. Through our models we investigate the error introduced with reduced numerical precision, and we perform various tests to explore the limits of single-precision processing.

A weighted edge-coloured graph is a graph for which each edge is assigned both a positive weight and a discrete colour, and can be used to model transportation and computer networks in which there are multiple transportation modes. In such a graph paths are compared by their total weight in each colour, resulting in a Pareto set of minimal paths from one vertex to another. This paper will give a tight upper bound on the cardinality of a minimal set of paths for any weighted edge-coloured graph. Additionally, a bound is presented on the expected number of minimal paths in weighted edge–bicoloured graphs. These bounds indicate that despite weighted edge-coloured graphs are theoretically intractable, amenability to computation is typically found in practice.

In this paper we present our end-to-end model of the imaging pipeline in the Square Kilometre Array. Our Sky Generator models the signals that are received by the Central Signal Processor (CSP), our CSP Correlator model then processes those signals to generate visibilities to pass to the Science Data Processor (SDP). Our SDP Imaging model then grids the visibilities and inverse Fourier transforms them to produce a dirty image of the sky. Our modelling allows us to investigate the error that is introduced due to reduced numerical precision, and we then propose techniques to mitigate this error, and thus reduce the required amount of computational hardware.

In this paper we present our end-to-end model of the imaging pipeline in the Square Kilometre Array. Our Sky Generator models the signals that are received by the Central Signal Processor (CSP), our CSP Correlator model then processes those signals to generate visibilities to pass to the Science Data Processor (SDP). Our SDP Imaging model then grids the visibilities and inverse Fourier transforms them to produce a dirty image of the sky. Our modelling allows us to investigate the error that is introduced due to reduced numerical precision, and we then propose techniques to mitigate this error, and thus reduce the required amount of computational hardware.

Many networked systems involve multiple modes of transport. Such systems are called multimodal, and examples include logistic networks, biomedical phenomena and telecommunication networks. Existing techniques for determining minimal paths in multimodal networks have either required heuristics or else application-specific constraints to obtain tractable problems, removing the multimodal traits of the network during analysis. In this paper weighted colored-edge graphs are introduced for modeling multimodal networks, where colors represent the modes of transportation. Minimal paths are selected using a partial order that compares the weights in each color, resulting in a Pareto set of minimal paths. Although the computation of minimal paths is theoretically intractable and [Formula: see text]-complete, the approach is shown to be tractable through experimental analyses without the need to apply heuristics or constraints.

A real-time feature point matching algorithm is introduced. It extracts vector-based ColourFAST feature strength and direction measures from the colour channels of the pixels in an image. This information is combined with the relative locations of the feature points to provide frame-by-frame scale and rotation invariant matching. The resulting algorithm is specifically designed for high throughput and optimised for GPU pipelining on embedded devices. Results are given showing high-framerate matching is achieved on 720p resolution images.

The Fourier transform is the main processing step applied to data collected from the Square Kilometre Array (SKA) receivers. The requirement is to compute a Fourier transform of 219 real byte samples in real-time, while minimizing the power consumption. We address this challenge by optimizing a FFT implementation for execution on the Kalray MPPA manycore processor. Although this processor delivers high floating-point performances, we use fixed-point number representations in order to reduce the memory consumption and the I/O bandwidth. The result is an execution time of 1,07ms per FFT, including data transfers. This enables to use only two first-generation MPPA chips per flow of data coming from the receivers, for a total power consumption of 17.4W.

A realtime feature point detection algorithm called ColourFAST is introduced. ColourFAST extracts vector-based feature strength and direction measures from the colour channels of any pixel in an image. The extracted information is applied to create an effective feature point tracker. These feature point and tracker algorithms have a pipeline design optimized for GPU processors. Results are provided for an implementation on mobile devices developed using programmable shaders. Its performance demonstrates several improvements over conventional FAST feature point detection and Lucas-Kanade tracking.

With the rapid advances in mobile technology many mobile devices are capable of capturing high quality images and video with their embedded camera. This paper investigates techniques for real-time processing of the resulting images, particularly on-device utilizing a graphical processing unit. Issues and limitations of image processing on mobile devices are discussed, and the performance of graphical processing units on a range of devices measured through a programmable shader implementation of Canny edge detection.

Many networked systems involve multiple modes of transport. Such systems are called multimodal, and examples include logistic networks, biomedical phenomena, manufacturing process and telecommunication networks. Existing techniques for determining optimal paths in multimodal networks have either required heuristics or else application-specific constraints to obtain tractable problems, removing the multimodal traits of the network during analysis. In this paper weighted coloured--edge graphs are introduced to model multimodal networks, where colours represent the modes of transportation. Optimal paths are selected using a partial order that compares the weights in each colour, resulting in a Pareto optimal set of shortest paths. This approach is shown to be tractable through experimental analyses for random and real multimodal networks without the need to apply heuristics or constraints.

New approaches for data provenance and data management (DPDM) are required for mega science projects like the Square Kilometer Array, characterized by extremely large data volume and intense data rates, therefore demanding innovative and highly efficient computational paradigms. In this context, we explore a stream-computing approach with the emphasis on the use of accelerators. In particular, we make use of a new generation of high performance stream-based parallelization middleware known as InfoSphere Streams. Its viability for managing and ensuring interoperability and integrity of signal processing data pipelines is demonstrated in radio astronomy.IBM InfoSphere Streams embraces the stream-computing paradigm. It is a shift from conventional data mining techniques (involving analysis of existing data from databases) towards real-time analytic processing. We discuss using InfoSphere Streams for effective DPDM in radio astronomy and propose a way in which InfoSphere Streams can be utilized for large antennae arrays. We present a case-study: the InfoSphere Streams implementation of an autocorrelating spectrometer, and using this example we discuss the advantages of the stream-computing approach and the utilization of hardware accelerators.

A weighted coloured–edge graph is a graph for which each edge is assigned both a positive weight and a discrete colour, and can be used to model transportation and computer networks in which there are multiple transportation modes. In such a graph paths are compared by their total weight in each colour, resulting in a Pareto set of minimal paths from one vertex to another. This paper will give a tight upper bound on the cardinality of a minimal set of paths for any weighted coloured–edge graph. Additionally, a bound is presented on the expected number of minimal paths in weighted bicoloured–edge

Given a variety ν and ν-algebras A and B, an algebraic formationF: A ⇉ B is a ν-homomorphism FL R × A → B, for some ν-algebra R, and the resulting functions F (r,-): A → B for r ∈ R are termed formable. Firstly, as motivation for the study of algebraic formations, categorical formations and their relationship with natural transformations are explained. Then, formations and formable functions are described for some common varieties of algebras, including semilattices, lattices, groups, and implication algebras. Some of their general properties are investigated for congruence modular varieties, including the description of a uniform congruence which provides information on the structure of B.

e signi cantly reduced data is persisted to a suitable store by this SINK PE. e persisted data can be used to perform longer integrations or deeper spectral analysis. UDOP (User De ned OPerator) PEs are used to implement the accelerator device speci c logic on the respective host. e accelerator devices are used to perform the time to frequency domain conversion. Communication between host and accelerator device is performed asynchronously in combination with multi-bu ering. In most cases the initial size chosen for a tuple to be optimal for a particular type of accelerator device usually implies that it contains data values for many frequency domain operations. Hence this FUNCTOR PE performs an integration operation to aggregate the auto-correlated results for the frequency domain operations performed within a tuple. SPADE Application Data ow Graph