Can Large Language Models Write Parallel Code?

Abstract: LLMs are increasingly becoming a popular tool for software development. Their ability to model and generate source code has been demonstrated in a variety of contexts, including code completion, summarization, translation, and lookup. However, they often struggle to generate code for complex programs. In this paper, we study the capabilities of state-of-the-art LLMs to generate parallel code. In order to evaluate LLMs, we create a benchmark, ParEval, consisting of prompts that represent 420 different coding tasks related to scientific and parallel computing. We use ParEval to evaluate the effectiveness of several state-of-the-art open- and closed-source LLMs on these tasks. We introduce novel metrics for evaluating the performance of generated code, and use them to explore how well each LLM performs for 12 different computational problem types and six different parallel programming models.