Automatic relative debugging of OpenMP programs

In this work we show how automatic relative debugging can be used to find differences in computation between a correct serial program and an OpenMP parallel version of that program that does not yield correct results. Backtracking and re-execution are used to determine the first OpenMP parallel region that produces a difference in computation that may lead to an incorrect value the user has indicated. Our approach also lends itself to finding differences between parallel computations, where executing with M threads produces expected results but an N thread execution does not (M, N > 1, M ≠ N). OpenMP programs created using a parallelization tool are addressed by utilizing static analysis and directive information from the tool. Hand-parallelized programs, where OpenMP directives are inserted by the user, are addressed by performing data dependence and directive analysis.

The effect of bonds on loyalty towards auditors: the mediating role of commitment

The study examines the impact of knowledge and social bonds on commitment and behavioural loyalty in auditor-client relationships. A model is proposed and tested using data collected from stock exchange company executives in the UK. The results show the significant effects of the knowledge and social bonds on commitment. Commitment is shown to be a mediating variable, which influences word-of-mouth and continuance but not the purchase of non-audit services. In the light of these findings, suggestions are provided to auditors in developing relationship bonds and managing the relationship at the firm level.

Psychological bonds and their impact on behavioral loyalty in auditor-client relationships

Purpose – The purpose of this paper is to examine the effect of the psychological bond on behavioral loyalty (word-of-mouth, continuance and non-audit services) to audit firms providing services to companies listed on the Polish Stock Exchange. Design/methodology/approach – A model is proposed and tested using structural equation modeling with LISREL. Data were collected from top executives of companies listed on the Warsaw Stock Exchange. Findings – The psychological bond has a positive effect on word-of-mouth, continuance and non-audit services. Research limitations/implications – The current research is limited to the investigation of the psychological bond as an antecedent of behavioral loyalty in Poland. Future research should identify and assess other antecedents and replicate these across different countries. A longitudinal survey across different points in time might reveal more useful information about auditor-client relationships. Practical implications – Auditors need to consider ways in which they can develop the psychological bond with their clients. This bond is the basis for the client believing the audit firm is superior to others, which has been found to lead to behavioral loyalty in this study. In particular, management of the auditor brand and reputation, personal experience of the audit firm and alumni relations are discussed as ways of enhancing the psychological bond among client executives. Originality/value – This study is the first to examine the impact of the psychological bond on behavioral loyalty in auditor-client relationships.