Sökning: onr:"swepub:oai:DiVA.org:kth-339526" > Supersonic: Learnin...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 02046nam a2200301 4500 | |
001 | oai:DiVA.org:kth-339526 | |
003 | SwePub | |
008 | 231113s2023 | |||||||||||000 ||eng| | |
024 | 7 | a https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-3395262 URI |
040 | a (SwePub)kth | |
041 | a engb eng | |
042 | 9 SwePub | |
072 | 7 | a vet2 swepub-contenttype |
072 | 7 | a ovr2 swepub-publicationtype |
100 | 1 | a Chen, Ziminu KTH,Teoretisk datalogi, TCS4 aut0 (Swepub:kth)u1igab2d |
245 | 1 0 | a Supersonic: Learning to Generate Source Code Optimizations in C/C++ |
264 | 1 | c 2023 |
338 | a print2 rdacarrier | |
500 | a QC 20231120 | |
520 | a 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. | |
650 | 7 | a NATURVETENSKAPx Data- och informationsvetenskapx Datavetenskap0 (SwePub)102012 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Computer and Information Sciencesx Computer Sciences0 (SwePub)102012 hsv//eng |
653 | a Datalogi | |
653 | a Computer Science | |
700 | 1 | a Fang, Senu KTH,Teoretisk datalogi, TCS4 aut0 (Swepub:kth)u1b71h6u |
700 | 1 | a Monperrus, Martinu KTH,Teoretisk datalogi, TCS4 aut0 (Swepub:kth)u13jhcyf |
710 | 2 | a KTHb Teoretisk datalogi, TCS4 org |
856 | 4 8 | u https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-339526 |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.