.png){kind=icon}
.png){kind=icon}
Return
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}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
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.
Keywords:
Optimization
Codes
Training
Source coding
Task analysis
Decoding
Vectors
Code optimization
Seq2Seq learning
large language model
Journal
IF:
5.6
Papers:
2.8K
Citations:
1.1W