{"doi":"10.1145/301631.301668","title":"New tiling techniques to improve cache temporal locality","abstract":"<jats:p>\n            Tiling is a well-known loop transformation to improve temporal locality of nested loops. Current compiler algorithms for tiling are limited to loops which are perfectly nested or can be transformed, in trivial ways, into a perfect nest. This paper presents a number of program transformations to enable tiling for a class of nontrivial imperfectly-nested loops such that cache locality is improved. We define a program model for such loops and develop compiler algorithms for their tiling. We propose to adopt\n            <jats:italic>odd-even variable duplication</jats:italic>\n            to break anti- and output dependences without unduly increasing the working-set size, and to adopt\n            <jats:italic>speculative execution</jats:italic>\n            to enable tiling of loops which may terminate prematurely due to, e.g. convergence tests in iterative algorithms. We have implemented these techniques in a research compiler, Panorama. Initial experiments with several benchmark programs are performed on SGI workstations based on MIPS R5K and R10K processors. Overall, the transformed programs run faster by 9% to 164%.\n          </jats:p>","journal":"ACM SIGPLAN Notices","year":1999,"id":26893,"datarank":2.258578179462771,"base_score":3.5263605246161616,"endowment":3.5263605246161616,"self_citation_contribution":0.5289540786924243,"citation_network_contribution":1.7296241007703466,"self_endowment_contribution":0.5289540786924243,"citer_contribution":1.7296241007703466,"corpus_percentile":null,"corpus_rank":null,"citation_count":33,"citer_count":33,"citers_with_citation_signal":28,"citers_with_endowment":28,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":120792,"name":"Zhiyuan Li","orcid":null,"position":1,"is_corresponding":false},{"id":154519,"name":"Yonghong Song","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"base_score":3.5263605246161616,"endowment":3.5263605246161616,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"24523987","pmcid":null,"openalex_id":"https://openalex.org/W2999265844","authors":[],"funders":[],"total_grants":0,"fwci":0.309,"citation_percentile":0.66563023,"influential_citations":0,"citation_trend":[{"year":2012,"count":2},{"year":2013,"count":4},{"year":2014,"count":4},{"year":2016,"count":1},{"year":2017,"count":4},{"year":2018,"count":1},{"year":2019,"count":2},{"year":2020,"count":1},{"year":2021,"count":2},{"year":2023,"count":1},{"year":2024,"count":2},{"year":2026,"count":2}],"oa_status":"bronze","license":"https://www.acm.org/publications/policies/copyright_policy#Background","oa_locations":[{"url":"https://dl.acm.org/doi/pdf/10.1145/301631.301668","host_type":"journal"},{"url":"https://dl.acm.org/doi/pdf/10.1145/301631.301668","host_type":"publisher"},{"url":"https://dl.acm.org/doi/10.1145/301631.301668","host_type":"publisher"},{"url":"https://doi.org/10.1145/301631.301668","host_type":"journal"}],"fields_of_study":["Parallel Computing and Optimization Techniques","Embedded Systems Design Techniques","Interconnection Networks and Systems"],"mesh_terms":[],"keywords":["Loop tiling","Computer science","Nested loop join","Parallel computing","Locality","Locality of reference","Loop optimization","Cache","Compiler","Benchmark (surveying)","Optimizing compiler","Theoretical computer science","Algorithm","Programming language"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-06-08T15:58:29.205104Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}