Learning Performance-Improving Code Edits

arXiv:2302.07867v5 Announce Type: replace-cross
Abstract: With the decline of Moore's law, optimizing program performance has become a major focus of software research. However, high-level optimizations such as API and algorithm changes remain elusive due to the difficulty of understanding the semantics of code. Simultaneously, pretrained large language models (LLMs) have demonstrated strong capabilities at solving a wide range of programming tasks. To that end, we introduce a framework for adapting LLMs to high-level program optimization. First, we curate a dataset …

abstract algorithm api arxiv become capabilities code cs.ai cs.lg cs.pf cs.se focus however improving language language models large language large language models law llms major performance research semantics software type understanding