{"id":"https://openalex.org/W4393146752","doi":"https://doi.org/10.1109/asp-dac58780.2024.10473837","title":"Collaborative Coalescing of Redundant Memory Access for GPU System","display_name":"Collaborative Coalescing of Redundant Memory Access for GPU System","publication_year":2024,"publication_date":"2024-01-22","ids":{"openalex":"https://openalex.org/W4393146752","doi":"https://doi.org/10.1109/asp-dac58780.2024.10473837"},"language":"en","primary_location":{"id":"doi:10.1109/asp-dac58780.2024.10473837","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asp-dac58780.2024.10473837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112710370","display_name":"Fan Jiang","orcid":"https://orcid.org/0000-0001-5676-7911"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Fan Jiang","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057936875","display_name":"Chengeng Li","orcid":"https://orcid.org/0000-0003-0740-0974"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chengeng Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100653327","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-1059-3642"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013248987","display_name":"Jiang Xu","orcid":"https://orcid.org/0000-0001-9089-7752"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiang Xu","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112710370"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":1.0278,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72061946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9365000128746033,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9365000128746033,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8209570646286011},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4793727695941925},{"id":"https://openalex.org/keywords/random-access-memory","display_name":"Random access memory","score":0.47024407982826233},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3708809018135071},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1116478443145752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209570646286011},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4793727695941925},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.47024407982826233},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3708809018135071},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1116478443145752}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asp-dac58780.2024.10473837","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asp-dac58780.2024.10473837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-136379","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-136379","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1985818188","https://openalex.org/W2080592089","https://openalex.org/W2092283255","https://openalex.org/W2128120785","https://openalex.org/W2130820665","https://openalex.org/W2169275978","https://openalex.org/W2170382128","https://openalex.org/W2235724720","https://openalex.org/W2566040696","https://openalex.org/W2619002702","https://openalex.org/W2910737925","https://openalex.org/W2913561863","https://openalex.org/W2967335569","https://openalex.org/W3093933627","https://openalex.org/W3102510044","https://openalex.org/W3159607817","https://openalex.org/W3206857466","https://openalex.org/W4318686046"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"GPU-based":[0],"computing":[1],"serves":[2],"as":[3],"the":[4,8,82,108],"primary":[5],"solution":[6],"driving":[7],"performance":[9,18,100],"of":[10],"HPC":[11],"systems.":[12],"However,":[13],"modern":[14],"GPU":[15,47],"systems":[16],"encounter":[17],"bottlenecks":[19],"resulting":[20],"from":[21,65],"heavy":[22],"memory":[23,43,60],"access":[24,44],"traffic":[25,106],"and":[26,45,68,80,101],"insufficient":[27],"NoC":[28,105],"bandwidth.":[29],"In":[30],"this":[31],"work,":[32],"we":[33,53,72],"propose":[34],"a":[35,55,74],"collaborative":[36],"coalescing":[37,56],"mechanism":[38],"aimed":[39],"at":[40],"eliminating":[41],"redundant":[42],"boosting":[46],"system":[48],"performance.":[49],"To":[50],"achieve":[51],"this,":[52],"design":[54],"unit":[57],"for":[58],"each":[59],"partition,":[61],"effectively":[62],"merging":[63],"requests":[64],"both":[66],"inter-cluster":[67],"intra-cluster":[69],"SMs.":[70,89],"Additionally,":[71],"introduce":[73],"hierarchical":[75],"multicast":[76],"module":[77],"to":[78,86],"replicate":[79],"distribute":[81],"coalesced":[83],"reply":[84],"messages":[85],"multiple":[87],"destination":[88],"Experimental":[90],"results":[91],"show":[92],"that":[93],"our":[94],"method":[95],"achieves":[96],"20.6%":[97],"improvement":[98],"on":[99,104],"27.1%":[102],"reduction":[103],"over":[107],"baseline.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}