Please use this identifier to cite or link to this item: https://rd.uffs.edu.br/handle/prefix/9187
Full metadata record
DC FieldValueLanguage
dc.contributor.advisor1Feitosa, Samuel da Silva-
dc.creatorMagnabosco, Fernando Schreiner-
dc.date2025-12-09-
dc.date.accessioned2026-03-30T18:17:17Z-
dc.date.available2026-
dc.date.available2026-03-30T18:17:17Z-
dc.date.issued2025-
dc.identifier.urihttps://rd.uffs.edu.br/handle/prefix/9187-
dc.description.resumoThis work proposes an approach for testing Rust compilers using Large Language Models (LLMs) to generate random code focused on unstable features. The methodology implements a differential testing system that uses the official rustc compiler as an oracle to filter semantically valid test cases before submitting them to gccrs, an alternative compiler under development. The system targets complex features such as trait specialization and constant evalua- tion. Results from 1,403 generated instances show that while LLMs struggle with the strict semantic rules of Rust’s nightly features (yielding a 3.7% validity rate), the filtering process proved crucial. The validated test cases revealed that the target compiler (gccrs) is currently limited by infrastructure bottlenecks—specifically due to missing language items and standard library linkage—rather than logic errors in complex passes. Crucially, the absence of critical crashes (ICEs) suggests stability in the compiler’s frontend parsing, even if backend integration remains incomplete. This study demons- trates that LLM-based fuzzing can serve as an effective "maturity probe"for emerging compilers.pt_BR
dc.description.provenanceSubmitted by Daniele Rohr (daniele.rohr@uffs.edu.br) on 2026-03-27T11:50:19Z No. of bitstreams: 1 MAGNABOSCO.pdf: 698583 bytes, checksum: 0682f5ec392225415ffe37d8a6e6d64f (MD5)en
dc.description.provenanceApproved for entry into archive by DIONE ROSSI FARIAS (dione@uffs.edu.br) on 2026-03-30T18:17:17Z (GMT) No. of bitstreams: 1 MAGNABOSCO.pdf: 698583 bytes, checksum: 0682f5ec392225415ffe37d8a6e6d64f (MD5)en
dc.description.provenanceMade available in DSpace on 2026-03-30T18:17:17Z (GMT). No. of bitstreams: 1 MAGNABOSCO.pdf: 698583 bytes, checksum: 0682f5ec392225415ffe37d8a6e6d64f (MD5) Previous issue date: 2025en
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.subjectTestespt_BR
dc.subjectGeração de códigopt_BR
dc.subjectInteligência artificialpt_BR
dc.titleGeração de código rust aleatório utilizando modelos grandes de linguagem para testes de compiladorespt_BR
dc.typeMonografiapt_BR
Appears in Collections:Ciência da Computação

Files in This Item:
File Description SizeFormat 
MAGNABOSCO.pdf682.21 kBAdobe PDFView/Open
Show simple item record Recommend this item


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