一句话：提出基于Transformer的DeepDev-PERF，在53%情况下为C#应用生成与开发者一致的性能优化补丁。
软件性能优化通常依赖性能专家人工识别低效代码并修复，过程耗时且难以规模化。本文提出DeepDev-PERF，一种基于Transformer的方法，为C#应用自动建议性能改进补丁。模型先在英文与源代码语料上预训练，再针对C#性能改进补丁生成任务微调。评估表明，在53%的情况下，模型生成的性能改进建议与开发者手工修复一致（摘要在此处截断），展示了深度学习自动化性能优化的潜力。
Improving software performance is an important yet challenging part of the software development cycle. Today, the majority of performance inefficiencies are identified and patched by performance experts. Recent advancements in deep learning approaches and the wide-spread availability of open-source data creates a great opportunity to automate the identification and patching of performance problems. In this paper, we present DeepDev-PERF, a transformer-based approach to suggest performance improvements for C# applications. We pretrain DeepDev-PERF on English and Source code corpora, followed by finetuning for the task of generating performance improvement patches for C# applications. Our evaluation shows that our model can generate the same performance improvement suggestion as the developer fix in 53
DOI 原文 ·
@inproceedings{paperbot7046,
title = {DeepDev-PERF: a deep learning-based approach for improving software performance},
author = {Spandan Garg and Roshanak Zilouchian Moghaddam and Colin B. Clement and Neel Sundaresan and Chen Wu},
booktitle = {FSE},
year = {2022},
doi = {10.1145/3540250.3549096}
}