{"id":{"repo_id":"mtu","oai_identifier":"oai:digitalcommons.mtu.edu:etdr-3032"},"canonical_url":"https://search.ndltd.org/etd/mtu/oai:digitalcommons.mtu.edu:etdr-3032","repository":{"repo_id":"mtu","name":"Michigan Technological University","base_url":"https://digitalcommons.mtu.edu/do/oai/"},"display":{"title":"Kangaroo: Dynamic Fusion of Branch Instructions in a Pipelined Uniprocessor","abstract":"Small pipelined processors are becoming more common as a complement to superscalars in a multi-core chip. However, current uniprocessors offer little in the way of ILP. We present kangaroo, a novel approach to instruction fusion in a pipelined processor. Kangaroo dynamically fuses two adjacent instructions to create a pair that travels through the pipeline as a unit. The instructions re-enter the pipeline as a pair the next time the first instruction is fetched. Unlike in prior art, an instruction, once fused, is not fetched again. Any pair of adjacent instructions can be fused using this technique, including dependent instructions. In this thesis, we focus on fusing branches to prior instructions. We introduce the fusion mechanism and discuss its implementation. Finally, we evaluate its performance with respect to a baseline six-stage pipelined uniprocessor with several benchmarks.","abstract_html":"Small pipelined processors are becoming more common as a complement to superscalars in a multi-core chip. However, current uniprocessors offer little in the way of ILP. We present kangaroo, a novel approach to instruction fusion in a pipelined processor. Kangaroo dynamically fuses two adjacent instructions to create a pair that travels through the pipeline as a unit. The instructions re-enter the pipeline as a pair the next time the first instruction is fetched. Unlike in prior art, an instruction, once fused, is not fetched again. Any pair of adjacent instructions can be fused using this technique, including dependent instructions. In this thesis, we focus on fusing branches to prior instructions. We introduce the fusion mechanism and discuss its implementation. Finally, we evaluate its performance with respect to a baseline six-stage pipelined uniprocessor with several benchmarks.","abstract_has_math":false,"creators":["Larkin, Sarah E."],"institution":null,"degree_name":"Master of Science in Computer Science (MS)","degree_level":"Open Access Master's Thesis","degree_discipline":"Department of Computer Science","degree_department":null,"school":null,"contributors":["Soner Onder"],"advisors":[],"committee_chairs":[],"committee_members":["Zhenlin Wang","Jianhui Yue"],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:19:20Z","subjects":["computer architecture","instruction fusion","pipelined processor","RISC","Systems Architecture"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.mtu.edu/etdr/1906"],"render_values":[{"text":"https://digitalcommons.mtu.edu/etdr/1906","href":"https://digitalcommons.mtu.edu/etdr/1906","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.37099/mtu.dc.etdr/1906","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/10.37099/mtu.dc.etdr/1906","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.mtu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.mtu.edu%3Aetdr-3032","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Soner Onder"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Zhenlin Wang","Jianhui Yue"]},{"key":"dc:creator","label":"Author","values":["Larkin, Sarah E."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.created","label":"Dc Date Created","values":["2025-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Department of Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Open Access Master's Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Computer Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["computer architecture","instruction fusion","pipelined processor","RISC","Systems Architecture"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.37099/mtu.dc.etdr/1906","https://digitalcommons.mtu.edu/etdr/1906"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Small pipelined processors are becoming more common as a complement to superscalars in a multi-core chip. However, current uniprocessors offer little in the way of ILP. We present kangaroo, a novel approach to instruction fusion in a pipelined processor. Kangaroo dynamically fuses two adjacent instructions to create a pair that travels through the pipeline as a unit. The instructions re-enter the pipeline as a pair the next time the first instruction is fetched. Unlike in prior art, an instruction, once fused, is not fetched again. Any pair of adjacent instructions can be fused using this technique, including dependent instructions. In this thesis, we focus on fusing branches to prior instructions. We introduce the fusion mechanism and discuss its implementation. Finally, we evaluate its performance with respect to a baseline six-stage pipelined uniprocessor with several benchmarks."]},{"key":"dc:title","label":"Title","values":["Kangaroo: Dynamic Fusion of Branch Instructions in a Pipelined Uniprocessor"]}]}],"canonical_facts":{"dc:contributor":["Soner Onder"],"dc:contributor.committeemember":["Zhenlin Wang","Jianhui Yue"],"dc:creator":["Larkin, Sarah E."],"dc:date.created":["2025-01-01T08:00:00Z"],"dc:description.abstract":["Small pipelined processors are becoming more common as a complement to superscalars in a multi-core chip. However, current uniprocessors offer little in the way of ILP. We present kangaroo, a novel approach to instruction fusion in a pipelined processor. Kangaroo dynamically fuses two adjacent instructions to create a pair that travels through the pipeline as a unit. The instructions re-enter the pipeline as a pair the next time the first instruction is fetched. Unlike in prior art, an instruction, once fused, is not fetched again. Any pair of adjacent instructions can be fused using this technique, including dependent instructions. In this thesis, we focus on fusing branches to prior instructions. We introduce the fusion mechanism and discuss its implementation. Finally, we evaluate its performance with respect to a baseline six-stage pipelined uniprocessor with several benchmarks."],"dc:identifier":["10.37099/mtu.dc.etdr/1906","https://digitalcommons.mtu.edu/etdr/1906"],"dc:subject":["computer architecture","instruction fusion","pipelined processor","RISC","Systems Architecture"],"dc:title":["Kangaroo: Dynamic Fusion of Branch Instructions in a Pipelined Uniprocessor"],"thesis:degree_discipline":["Department of Computer Science"],"thesis:degree_level":["Open Access Master's Thesis"],"thesis:degree_name":["Master of Science in Computer Science (MS)"]},"updated_at":"2026-11-19T08:19:20Z"}