{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129174"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129174","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Scaling deep learning computation over the inter-core connected intelligence processor","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","abstract_has_math":false,"creators":["Liu, Yiqi"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Huang, Jian"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-03-04","date_published":"2025-03-04","updated_at":"2026-07-22T22:25:04Z","subjects":["Deep Learning Compiler","Intelligence Processing Unit","Distributed Shared Memory","ML Accelerator"],"languages":["en","eng"],"rights":["Copyright 2025 Yiqi Liu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129174","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Huang, Jian"]},{"key":"dc:creator","label":"Author","values":["Liu, Yiqi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-03-04","2025-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"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 Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep Learning Compiler","Intelligence Processing Unit","Distributed Shared Memory","ML Accelerator"]}]},{"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 2025 Yiqi Liu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129174"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","The student, Yiqi Liu, accepted the attached license on 2025-03-03 at 10:44.","The student, Yiqi Liu, submitted this Thesis for approval on 2025-03-03 at 10:50.","This Thesis was approved for publication on 2025-03-04 at 10:54.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21656 on 2025-10-19 at 18:09:08","As AI chips incorporate numerous parallelized cores to scale deep learning (DL) computing, inter-core communication is enabled recently by employing high-bandwidth and low-latency interconnect links on the chip (e.g., Graphcore IPU). It allows each core to directly access the fast scratchpad memory in other cores, which enables new parallel computing paradigms. However, without proper support for the scalable inter-core connections in current DL compilers, it is hard for developers to exploit the benefits of this new architecture. This thesis proposes T10, the first DL compiler to exploit the inter-core communication bandwidth and distributed on-chip memory on AI chips. To formulate the computation and communication patterns of tensor operators in this new architecture, T10 introduces a distributed tensor abstraction rTensor. T10 maps a DNN model to execution plans with a generalized compute-shift pattern, by partitioning DNN computation into sub-operators and mapping them to cores, so that the cores can exchange data following predictable patterns. T10 makes globally optimized trade-offs between on-chip memory consumption and inter-core communication overhead, selects the best execution plan from a vast optimization space, and alleviates unnecessary inter-core communications. Our evaluation with a real inter-core connected AI chip, the Graphcore IPU, shows up to 3.3× performance improvement, and scalability support for larger models, compared to state-of-the-art DL compilers and vendor libraries."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Scaling deep learning computation over the inter-core connected intelligence processor"]}]}],"canonical_facts":{"dc:contributor":["Huang, Jian"],"dc:creator":["Liu, Yiqi"],"dc:date":["2025-03-04","2025-05"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","The student, Yiqi Liu, accepted the attached license on 2025-03-03 at 10:44.","The student, Yiqi Liu, submitted this Thesis for approval on 2025-03-03 at 10:50.","This Thesis was approved for publication on 2025-03-04 at 10:54.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21656 on 2025-10-19 at 18:09:08","As AI chips incorporate numerous parallelized cores to scale deep learning (DL) computing, inter-core communication is enabled recently by employing high-bandwidth and low-latency interconnect links on the chip (e.g., Graphcore IPU). It allows each core to directly access the fast scratchpad memory in other cores, which enables new parallel computing paradigms. However, without proper support for the scalable inter-core connections in current DL compilers, it is hard for developers to exploit the benefits of this new architecture. This thesis proposes T10, the first DL compiler to exploit the inter-core communication bandwidth and distributed on-chip memory on AI chips. To formulate the computation and communication patterns of tensor operators in this new architecture, T10 introduces a distributed tensor abstraction rTensor. T10 maps a DNN model to execution plans with a generalized compute-shift pattern, by partitioning DNN computation into sub-operators and mapping them to cores, so that the cores can exchange data following predictable patterns. T10 makes globally optimized trade-offs between on-chip memory consumption and inter-core communication overhead, selects the best execution plan from a vast optimization space, and alleviates unnecessary inter-core communications. Our evaluation with a real inter-core connected AI chip, the Graphcore IPU, shows up to 3.3× performance improvement, and scalability support for larger models, compared to state-of-the-art DL compilers and vendor libraries."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129174"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Yiqi Liu"],"dc:subject":["Deep Learning Compiler","Intelligence Processing Unit","Distributed Shared Memory","ML Accelerator"],"dc:title":["Scaling deep learning computation over the inter-core connected intelligence processor"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:04Z"}