Search: onr:"swepub:oai:DiVA.org:kth-339526" >
Supersonic: Learnin...
-
Chen, ZiminKTH,Teoretisk datalogi, TCS
(author)
Supersonic: Learning to Generate Source Code Optimizations in C/C++
Publisher, publication year, extent ...
Numbers
-
LIBRIS-ID:oai:DiVA.org:kth-339526
-
https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-339526URI
Supplementary language notes
-
Language:English
-
Summary in:English
Part of subdatabase
Classification
-
Subject category:vet swepub-contenttype
-
Subject category:ovr swepub-publicationtype
Notes
-
QC 20231120
-
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.
Subject headings and genre
Added entries (persons, corporate bodies, meetings, titles ...)
-
Fang, SenKTH,Teoretisk datalogi, TCS(Swepub:kth)u1b71h6u
(author)
-
Monperrus, MartinKTH,Teoretisk datalogi, TCS(Swepub:kth)u13jhcyf
(author)
-
KTHTeoretisk datalogi, TCS
(creator_code:org_t)
Internet link
To the university's database