{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/124525"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/124525","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Understanding and simplifying bug-inducing inputs for deep-learning compilers","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01","abstract_has_math":false,"creators":["Liu, Jiawei"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Zhang, Lingming"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:25:02Z","subjects":["Compiler Testing","Test Reduction","Deep Learning Compilers"],"languages":["en","eng"],"rights":["Copyright 2024 Jiawei Liu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/124525","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Zhang, Lingming"]},{"key":"dc:creator","label":"Author","values":["Liu, Jiawei"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-05","2024-04-18"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Compiler Testing","Test Reduction","Deep Learning Compilers"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2024 Jiawei Liu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/124525"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01","The student, Jiawei Liu, accepted the attached license on 2024-04-12 at 23:56.","The student, Jiawei Liu, submitted this Thesis for approval on 2024-04-13 at 00:34.","This Thesis was approved for publication on 2024-04-18 at 10:52.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20392 on 2024-09-16 at 00:43:35","With the recent evolution of parallel computing and compilation techniques, deep learning (DL) models have increasingly been deployed using DL compilers to achieve real-time performance in resource-constrained environments. The compiler stack is complex and initially drafted, making the debugging of DL compilers challenging, especially given the limited time and number of compiler experts available. Complicating matters further, the massive and often duplicated bug reports (e.g., fuzzing bugs) may contain obscure or even no error messages (e.g., semantic bugs) for models consisting of thousands of layers. This situation makes it extremely challenging to understand and localize compiler failures. To address this emerging challenge, we propose new techniques for automatically reducing and deduplicating DL compiler bug reports: We define the test-case reduction problem in DL compilers for general graph-level inputs and propose sub-graph minimality as the reduction target. Based on the Delta Debugging framework, we perform validity-preserving graph partitioning guided by heuristics from error-prone patterns. Using graph matching, we deduplicate test cases with graph isomorphism and expedite reductions by matching minimized graphs against incoming ones. We have integrated our techniques into a new tool, NNReduce, which is the first graph-level reducer with a sub-graph minimality guarantee, implemented for ONNX model formats. We applied NNReduce to reduce and deduplicate both fuzzer-generated and real-world bug reports, creating a new dataset for extensive evaluation. Our results show that NNReduce can reduce test cases by up to 3.14× (for fuzzing bugs) and 90.9x (for real-world bugs) smaller than the existing half-automated reduction tool, Polygraphy by NVIDIA. NNReduce also improves error-message-based deduplication by achieving up to a 2.36x smaller distinct set of bug reports."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Understanding and simplifying bug-inducing inputs for deep-learning compilers"]}]}],"canonical_facts":{"dc:contributor":["Zhang, Lingming"],"dc:creator":["Liu, Jiawei"],"dc:date":["2024-05","2024-04-18"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01","The student, Jiawei Liu, accepted the attached license on 2024-04-12 at 23:56.","The student, Jiawei Liu, submitted this Thesis for approval on 2024-04-13 at 00:34.","This Thesis was approved for publication on 2024-04-18 at 10:52.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20392 on 2024-09-16 at 00:43:35","With the recent evolution of parallel computing and compilation techniques, deep learning (DL) models have increasingly been deployed using DL compilers to achieve real-time performance in resource-constrained environments. The compiler stack is complex and initially drafted, making the debugging of DL compilers challenging, especially given the limited time and number of compiler experts available. Complicating matters further, the massive and often duplicated bug reports (e.g., fuzzing bugs) may contain obscure or even no error messages (e.g., semantic bugs) for models consisting of thousands of layers. This situation makes it extremely challenging to understand and localize compiler failures. To address this emerging challenge, we propose new techniques for automatically reducing and deduplicating DL compiler bug reports: We define the test-case reduction problem in DL compilers for general graph-level inputs and propose sub-graph minimality as the reduction target. Based on the Delta Debugging framework, we perform validity-preserving graph partitioning guided by heuristics from error-prone patterns. Using graph matching, we deduplicate test cases with graph isomorphism and expedite reductions by matching minimized graphs against incoming ones. We have integrated our techniques into a new tool, NNReduce, which is the first graph-level reducer with a sub-graph minimality guarantee, implemented for ONNX model formats. We applied NNReduce to reduce and deduplicate both fuzzer-generated and real-world bug reports, creating a new dataset for extensive evaluation. Our results show that NNReduce can reduce test cases by up to 3.14× (for fuzzing bugs) and 90.9x (for real-world bugs) smaller than the existing half-automated reduction tool, Polygraphy by NVIDIA. NNReduce also improves error-message-based deduplication by achieving up to a 2.36x smaller distinct set of bug reports."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/124525"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 Jiawei Liu"],"dc:subject":["Compiler Testing","Test Reduction","Deep Learning Compilers"],"dc:title":["Understanding and simplifying bug-inducing inputs for deep-learning compilers"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:02Z"}