Exploring translation of OpenMP to OpenACC 2.5: lessons learned

Scientists who want to exploit the computing power of the latest parallel architectures are faced with a diverse set of architectures and a number of programming languages, models and approaches. Among several such programming techniques are directive-based programming models, OpenMP and OpenACC. This paper explores the similarities and the functionality gaps between both models and presents insights into the translation process of constructs from OpenMP to OpenACC. An empirical study of performance and portability across multicore platforms and GPU accelerators for varying workload sizes is also presented.