The processing power available to scientists and engineers using supercomputers over the last few decades has grown exponentially, permitting significantly more sophisticated simulations, and as a consequence, generating proportionally larger output datasets. This change has taken place in tandem with a gradual shift in the design and implementation of simulation and post-processing software, with a shift from simulation as a first step and visualisation/analysis as a second, towards in-situ on the fly methods that provide immediate visual feedback, place less strain on file-systems and reduce overall data-movement and copying. Concurrently, processor speed increases have dramatically slowed and multi and many-core architectures have instead become the norm for virtually all High Performance computing (HPC) machines. This in turn has led to a shift away from the traditional distributed one rank per node model, to one rank per process, using multiple processes per multicore node, and then back towards one rank per node again, using distributed and multi-threaded frameworks combined.
This thesis consists of a series of publications that demonstrate how software design for analysis and visualisation has tracked these architectural changes and pushed the boundaries of HPC visualisation using dataflow techniques in distributed environments. The first publication shows how support for the time dimension in parallel pipelines can be implemented, demonstrating how information flow within an application can be leveraged to optimise performance and add features such as analysis of time-dependent flows and comparison of datasets at different timesteps. A method of integrating dataflow pipelines with in-situ visualisation is subsequently presented, using asynchronous coupling of user driven GUI controls and a live simulation running on a supercomputer. The loose coupling of analysis and simulation allows for reduced IO, immediate feedback and the ability to change simulation parameters on the fly.
A significant drawback of parallel pipelines is the inefficiency caused by improper load-balancing, particularly during interactive analysis where the user may select between different features of interest, this problem is addressed in the fourth publication by integrating a high performance partitioning library into the visualization pipeline and extending the information flow up and down the pipeline to support it. This extension is demonstrated in the third publication (published earlier) on massive meshes with extremely high complexity and shows that general purpose visualization tools such as ParaView can be made to compete with bespoke software written for a dedicated task.
The future of software running on many-core architectures will involve task-based runtimes, with dynamic load-balancing, asynchronous execution based on dataflow graphs, work stealing and concurrent data sharing between simulation and analysis. The final paper of this thesis presents an optimisation for one such runtime, in support of these future HPC applications.
Hal asz's Theorem gives an upper bound for the mean value of a multiplicative function f. The bound is sharp for general such f, and, in particular, it implies that a multiplicative function with jf(n)j 1 has either mean value 0, or is \close to" nit for some xed t. The proofs in the current literature have certain features that are di cult to motivate
and which are not particularly exible. In this article we supply a di erent, more exible, proof, which indicates how one might obtain asymptotics, and can be modi ed to treat short intervals and arithmetic progressions. We use these results to obtain new, arguably simpler,
proofs that there are always primes in short intervals (Hoheisel's Theorem), and that there are always primes near to the start of an arithmetic progression (Linnik's Theorem).
This article explores the relationship between the prison and mental illness, focusing on the ways in which the system of separate confinement was associated with mental breakdown and how maintaining the integrity of prison discipline mitigated against prisoners obtaining treatment or removal to an asylum. Examples are taken from English and Irish prisons, from the introduction of separate confinement at Pentonville Prison in London in 1842 until the late nineteenth century, exploring the persistence of the system of separation in the face of evidence that it was harming the minds of prisoners. The article also briefly examines the ways in which prison doctors argued that they were dealing with special categories of prisoner, adept at feigning, intrinsically weak-minded and whose mental deterioration was embedded in their criminality, factors that served to reinforce the harmful environment for mentally ill prisoners.
The survey, which was conducted in July 2017, captures 1220 responses, and is based on a representative sample of UK population
based on gender, income level, education level, and place of residence in the UK. It was structured to ask questions about informants'
current usage of, opinions about, and future intentions to use the following sharing categories: places to stay (e.g. Airbnb, Beds on Board), rides (e.g. Uber, Liftshare), rental cars (e.g. Easycar, Zipcar),
parking (e.g. JustPark, Your Parking Space), services (e.g. Parcelly, TaskRabbit), meals (e.g. MealSharing, Eatwith), pre-owned goods (e.g. eBay, Gumtree) and funding (e.g. Justgiving, Crowdcube).
[Introductory paragraph] The present generation must confront a challenge. The challenge is to determine what it must do for the sake of future generations. This challenge is quite puzzling because the present generation, like its predecessors, will pass on to future generations a complex mix of goods, inventions, institutions and opportunities containing a range of benefits and burdens. In this thesis, I focus on one key intergenerational problem – anthropogenic climate change – considering some of the questions of intergenerational justice that it raises. While it has not always been the case, climate and climate change have recently taken on new significance as a process to which humans can, and in fact do, contribute. More specifically, while paleoclimatic data show substantial variation in the Earth's climate (Masson- Delmotte, Schulz, Abe-Ouchi, Beer, Ganopolski, J.F. González Rouco, E. Jansen, et al., 2013: 385), an ever-growing mass of evidence shows that human activity – particularly the sustained emission of greenhouse gases (GHGs) – is beginning to change the global climate, with much greater changes still to come (IPCC, 2013b: 4, 19ff). This produces what is known as anthropogenic climate change, "a change in the state of the climate that can be identified (e.g., by using statistical tests) by changes in the mean and/or the variability of its properties, and that persists for an extended period, typically decades or longer", and that results from human activities (IPCC, 2013a: 1448, 1450).