.png){kind=icon}
返回
Supersonic: Learning to Generate Source Code Optimizations in C/C plus
.png){kind=icon}
OA
AI
DOI：10.1109/TSE.2024.3423769.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Software optimization refines programs for resource efficiency while preserving functionality. Traditionally, it is a process done by developers and compilers. This paper introduces a third option, automated optimization at the source code level. We present Supersonic , a neural approach targeting minor source code modifications for optimization. Using a seq2seq model, Supersonic is trained on C/C++ program pairs ( x(t) , x(t+1) ), where x(t+1) is an optimized version of x(t) , and outputs a diff. Supersonic 's performance is benchmarked against OpenAI's GPT-3.5-Turbo and GPT-4 on competitive programming tasks. The experiments show that Supersonic not only outperforms both models on the code optimization task but also minimizes the extent of the change with a model more than 600x smaller than GPT-3.5-Turbo and 3700x smaller than GPT-4.
Keyword:
Optimization
Codes
Training
Source coding
Task analysis
Decoding
Vectors
Code optimization
Seq2Seq learning
large language model
期刊
IF:
5.6
论文数:
2.9K
被引数:
1.1W
机构
引用论文
Mechanism of action of a yeast activator: Direct effect of GAL4 derivatives on mammalian TFIID-promoter interactions.png)
Cell
CellIF0
PREAI
分享收藏
Research on the Efficiency of Wireless Power Transfer System Based on Multi-Auxiliary Transmitting Coils基于多辅助发射线圈的无线电能传输系统效率研究
PREAI
分享收藏
查看更多内容