Sökning: id:"swepub:oai:DiVA.org:kth-339526" >
Supersonic: Learnin...
Supersonic: Learning to Generate Source Code Optimizations in C/C++
-
- Chen, Zimin (författare)
- KTH,Teoretisk datalogi, TCS
-
- Fang, Sen (författare)
- KTH,Teoretisk datalogi, TCS
-
- Monperrus, Martin (författare)
- KTH,Teoretisk datalogi, TCS
-
(creator_code:org_t)
- 2023
- Engelska.
- Relaterad länk:
-
https://urn.kb.se/re...
Abstract
Ämnesord
Stäng
- 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 (xt, xt+1), where xt+1 is an optimized version of xt, 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.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Datalogi
- Computer Science
Publikations- och innehållstyp
- vet (ämneskategori)
- ovr (ämneskategori)