Please use this identifier to cite or link to this item: https://rd.uffs.edu.br/handle/prefix/9707
Full metadata record
DC FieldValueLanguage
dc.contributor.advisor1Feitosa, Samuel da Silva-
dc.creatorTerres, Luiz Paulo Grafetti-
dc.date2026-06-24-
dc.date.accessioned2026-10-15T13:18:48Z-
dc.date.available2026-
dc.date.available2026-10-15T13:18:48Z-
dc.date.issued2026-
dc.identifier.urihttps://rd.uffs.edu.br/handle/prefix/9707-
dc.description.resumoCompilers are fundamental tools for software infrastructure, yet their complex implementation makes them prone to bugs and hard to formally verify. The literature presents a range of techniques that aim at random testing (fuzzing) compilers for maintaining acceptable levels of correctness. Among traditional tools for compiler fuzzing, the complex implementation and maintenance of code generators and mutators remain an open challenge. Recent efforts aim to address this challenge by employing Large Language Models (LLMs) for test case generation. This paper presents Goopfuzz, a fuzzer that leverages Gemini 3.1 Pro and targets SSA passes in Go compilers in a differential testing, mutation-based, and coverageguided approach. By leveraging the Gemini model to generate code mutators and removing the LLM from the fuzzing loop, the Goopfuzz hybrid approach mitigates the complex implementation challenge associated with traditional methods and the low throughput of LLM-pure solutions. During Goopfuzz experiments, Gemini 3.1 Pro synthesized 76.25% of all 157 working mutators on the first try. Synthesized mutators produced a total of 165,321 unique Go programs to serve as test cases during the fuzzing campaign, exercising 15.75% of the SSA implementation portion of the Go compiler. The differential testing oracle evaluated the compilation results for those programs against the last two stable releases of the official Go compiler (1.25.10 and 1.26.3) in different optimization levels.pt_BR
dc.description.provenanceSubmitted by Biblioteca Chapeco (biblio.ch@uffs.edu.br) on 2026-10-14T15:48:33Z No. of bitstreams: 1 TERRES.pdf: 678969 bytes, checksum: 4423acf56541f9ce6bed32315b41fe20 (MD5)en
dc.description.provenanceApproved for entry into archive by Franciele Scaglioni da Cruz (franciele.cruz@uffs.edu.br) on 2026-10-15T13:18:48Z (GMT) No. of bitstreams: 1 TERRES.pdf: 678969 bytes, checksum: 4423acf56541f9ce6bed32315b41fe20 (MD5)en
dc.description.provenanceMade available in DSpace on 2026-10-15T13:18:48Z (GMT). No. of bitstreams: 1 TERRES.pdf: 678969 bytes, checksum: 4423acf56541f9ce6bed32315b41fe20 (MD5) Previous issue date: 2026en
dc.languageporpt_BR
dc.publisherUniversidade Federal da Fronteira Sulpt_BR
dc.publisher.countryBrasilpt_BR
dc.publisher.departmentCampus Chapecópt_BR
dc.publisher.initialsUFFSpt_BR
dc.rightsAcesso Abertopt_BR
dc.subjectMontadores e compiladorespt_BR
dc.subjectLinguagem de programaçãopt_BR
dc.subjectGeração de códigopt_BR
dc.subjectTestespt_BR
dc.subjectInteligência artificialpt_BR
dc.subjectOtimizaçãopt_BR
dc.titleDifferential testing SSA optimization passes in Go compilers using LLM generated code mutatorspt_BR
dc.typeMonografiapt_BR
Appears in Collections:Ciência da Computação

Files in This Item:
File Description SizeFormat 
TERRES.pdf663.06 kBAdobe PDFView/Open
Show simple item record Recommend this item


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.