In this paper, we report on our "Iridis-Pi" cluster, which consists of 64 Raspberry Pi Model B nodes each equipped with a 700 MHz ARM processor, 256 MiB of RAM and a 16 GiB SD card for local storage. The cluster has a number of advantages which are not shared with conventional data-centre based cluster, including its low total power consumption, easy portability due to its small size and weight, affordability, and passive, ambient cooling. We propose that these attributes make Iridis-Pi ideally suited to educational applications, where it provides a low-cost starting point to inspire and enable students to understand and apply highperformance computing and data handling to tackle complex engineering and scientific challenges. We present the results of benchmarking both the computational power and network performance of the "Iridis-Pi." We also argue that such systems should be considered in some additional specialist application areas where these unique attributes may prove advantageous. We believe that the choice of an ARM CPU foreshadows a trend towards the increasing adoption of low-power, non-PC-compatible architectures in high performance clusters.

X-ray computed tomography is an established volume imaging technique used routinely in medical diagnosis, industrial non-destructive testing, and a wide range of scientific fields. Traditionally, computed tomography uses scanning geometries with a single axis of rotation together with reconstruction algorithms specifically designed for this setup. Recently there has however been increasing interest in more complex scanning geometries. These include so called X-ray computed laminography systems capable of imaging specimens with large lateral dimensions or large aspect ratios, neither of which are well suited to conventional CT scanning procedures. Developments throughout this field have thus been rapid, including the introduction of novel system trajectories, the application and refinement of various reconstruction methods, and the use of recently developed computational hardware and software techniques to accelerate reconstruction times. Here we examine the advances made in the last several years and consider their impact on the state of the art.

Carbon fibre reinforced polymers (CFRPs) are of interest to the aerospace sector for meeting future CO2 emission targets due to their weight reduction potential. However, the detection of structural and matrix defects is crucial for determining the performance and suitability of CFRPs in current and future generations of aircraft. Computed laminography (CL), a well-established nondestructive testing method, is well-suited to the scanning of CFRP components with large aspect ratios, for which conventional computed tomography is less suitable. Utilising an existing Nikon Metrology custom build X-ray CT scanner, two lift-in lift-out robotic sample manipulator systems are used to extend the capability of the system and allow the exploration of atypical scanning geometries. Implementing raster and limited angle trajectories, reconstructions using the ASTRA Tomography Toolbox and the SIRT algorithm are able to show structural defects in CFRPs, despite the reduced information inherent with CL systems. This paper reports on the system design and initial experiments that demonstrate benefits and drawbacks of different design options and scanning trajectory choices.

No abstract

Abstract-Iterative reconstruction of tomographic data relies on the precise knowledge of the geometric properties of the scan system. Common tomography systems such as rotational tomography, C-arm systems, helical scanners or tomosynthesis scanners generally use motions described by few rotational or linear motion axis. We are interested in applications in nondestructive testing, where objects might have large aspect rations and complex shapes. For these problems, more complex scan trajectories are required which can be achieved with robotic manipulator systems that have several linear or rotational degrees of freedom.For the geometric calibration of our system, instead of using an approach that scans a calibrated phantom with markers at known relative position, we propose an approach that uses one (or several) markers with unknown relative positions. The fiducial marker is then moved by a known amount along one degree of freedom, thus tracing out a "virtual" phantom. Using the assumed spacial locations of the markers together with the locations of the markers on the imaging plane, we use a nonlinear optimisation method to estimate the orientation of the linear and rotational manipulator axis, the detector and source location and the detector orientation.