GPRM: a high performance programming framework for manycore processors

Processors with large numbers of cores are becoming commonplace. In order to utilise the available resources in such systems, the programming paradigm has to move towards increased parallelism. However, increased parallelism does not necessarily lead to better performance. Parallel programming models have to provide not only flexible ways of defining parallel tasks, but also efficient methods to manage the created tasks. Moreover, in a general-purpose system, applications residing in the system compete for the shared resources. Thread and task scheduling in such a multiprogrammed multithreaded environment is a significant challenge. In this thesis, we introduce a new task-based parallel reduction model, called the Glasgow Parallel Reduction Machine (GPRM). Our main objective is to provide high performance while maintaining ease of programming. GPRM supports native parallelism; it provides a modular way of expressing parallel tasks and the communication patterns between them. Compiling a GPRM program results in an Intermediate Representation (IR) containing useful information about tasks, their dependencies, as well as the initial mapping information. This compile-time information helps reduce the overhead of runtime task scheduling and is key to high performance. Generally speaking, the granularity and the number of tasks are major factors in achieving high performance. These factors are even more important in the case of GPRM, as it is highly dependent on tasks, rather than threads. We use three basic benchmarks to provide a detailed comparison of GPRM with Intel OpenMP, Cilk Plus, and Threading Building Blocks (TBB) on the Intel Xeon Phi, and with GNU OpenMP on the Tilera TILEPro64. GPRM shows superior performance in almost all cases, only by controlling the number of tasks. GPRM also provides a low-overhead mechanism, called “Global Sharing”, which improves performance in multiprogramming situations. We use OpenMP, as the most popular model for shared-memory parallel programming as the main GPRM competitor for solving three well-known problems on both platforms: LU factorisation of Sparse Matrices, Image Convolution, and Linked List Processing. We focus on proposing solutions that best fit into the GPRM’s model of execution. GPRM outperforms OpenMP in all cases on the TILEPro64. On the Xeon Phi, our solution for the LU Factorisation results in notable performance improvement for sparse matrices with large numbers of small blocks. We investigate the overhead of GPRM’s task creation and distribution for very short computations using the Image Convolution benchmark. We show that this overhead can be mitigated by combining smaller tasks into larger ones. As a result, GPRM can outperform OpenMP for convolving large 2D matrices on the Xeon Phi. Finally, we demonstrate that our parallel worksharing construct provides an efficient solution for Linked List processing and performs better than OpenMP implementations on the Xeon Phi. The results are very promising, as they verify that our parallel programming framework for manycore processors is flexible and scalable, and can provide high performance without sacrificing productivity.

The use of Acceptance and Commitment Therapy to address psychological distress experienced by caregivers: a randomised controlled feasibility trial

Background: An extensive research literature has documented the impact of caring for an individual with acquired brain injury (ABI) on caregivers and family members, including role adjustment, psychological distress, social isolation, family tension and coping with the cognitive and behavioural difficulties of the injured person. Given these findings it is important this population have access to services and supports. Acceptance and Commitment Therapy (ACT) is an intervention that helps individuals to accept difficult experiences and commit to behaviour that is consistent with their values. Research into the effectiveness of ACT to support caregivers is at a preliminary stage. Aim: To investigate the feasibility of using ACT to reduce psychological distress and increase psychological flexibility in ABI caregivers. A secondary aim was to gain an understanding of the experience of caregivers in this context and how this can inform the development and delivery of interventions for this population. Method: Phase one was a randomised controlled feasibility trial of an ACT intervention for use with ABI caregivers. The parameters of this study were formulated around the PICO (population, intervention, control, and outcome) framework. Eighteen carers were recruited and randomised to ACT or an enhanced treatment as usual (ETAU) group. ACT was implemented over 3 sessions; and ETAU was implemented over 2 sessions. The General Health Questionnaire, Valuing Questionnaire, Acceptance and Action Questionnaire, Experiential Avoidance of Caregiving Questionnaire and the Flexibility of Responses to Self-Critical Thoughts Scale were administered to both groups at baseline and following the final session. Phase two used a retrospective qualitative design that involved conducting semi-structured interviews with four participants from phase one. Results: ACT and control participants were successfully recruited. Positive feedback was obtained from ACT participants suggesting that the intervention was acceptable. There were no significant differences between the ACT and ETAU groups on outcome measures. However, there were challenges retaining participants and the overall attrition rate was high (44.44%). Therefore a number of participants did not complete the full complement of sessions, which may have impacted on this result. Qualitative results illustrated the challenges this population face including significant adjustments in their life, the emotional impact of having a loved one with a brain injury and trying to adapt to the changes in the injured person. In addition, findings elucidated the types of support that this population would find helpful and the barriers to accessing same. Conclusions: Findings from this study highlight factors that will help the development of this intervention further for a caring population. Recommendations for future implementation include completing some preparatory work with carers before beginning the intervention, consideration of a larger sample and wider recruitment strategy from local services, barriers to attending interventions and the possibility of holding groups in local venues.