A Comprehensive Comparison and Analysis of OpenACC and OpenMP 4.5 for NVIDIA GPUs

Abstract

HPC systems having accelerator attached to it is the new normal. However, programming these accelerators to get good performance is very complex and tedious. Hence, directive based programming such as OpenMP and OpenACC are gaining wide popularity for parallel programming. They simplify the programming experience by abstracting the low-level complexities from the user. In this paper, we have done an extensive comparison of OpenMP 4.5 and OpenACC for GPU programming. Performance comparison of these two APIs on NVIDIA Tesla GPUs namely, P100 and V100 has also been captured. Data Transfer times, Kernel Execution times, Total Execution times and Performance portability are the criteria for comparison. The challenges faced while parallelizing the applications using the directives thus leading to improper outputs has also been dotted.