{"id":"https://openalex.org/W4401408716","doi":"https://doi.org/10.1145/3673038.3673075","title":"AdCoalescer: An Adaptive Coalescer to Reduce the Inter-Module Traffic in MCM-GPUs","display_name":"AdCoalescer: An Adaptive Coalescer to Reduce the Inter-Module Traffic in MCM-GPUs","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4401408716","doi":"https://doi.org/10.1145/3673038.3673075"},"language":"en","primary_location":{"id":"doi:10.1145/3673038.3673075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673075","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673075","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100534811","display_name":"Xu Zhang","orcid":"https://orcid.org/0009-0005-8856-8278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["Defense Innovation Institute, China"],"raw_orcid":"https://orcid.org/0009-0005-8856-8278","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049705266","display_name":"Guangda Zhang","orcid":"https://orcid.org/0000-0003-4732-9674"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangda Zhang","raw_affiliation_strings":["Defense Innovation Institute, China"],"raw_orcid":"https://orcid.org/0000-0003-4732-9674","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364374","display_name":"Lu Wang","orcid":"https://orcid.org/0000-0001-5759-6544"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Wang","raw_affiliation_strings":["Defense Innovation Institute, China"],"raw_orcid":"https://orcid.org/0000-0001-5759-6544","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101891026","display_name":"Shiqing Zhang","orcid":"https://orcid.org/0000-0002-6690-3718"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiqing Zhang","raw_affiliation_strings":["Defense Innovation Institute, China"],"raw_orcid":"https://orcid.org/0000-0002-6690-3718","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072444630","display_name":"Xia Zhao","orcid":"https://orcid.org/0000-0001-6479-9200"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia Zhao","raw_affiliation_strings":["Defense Innovation Institute, China"],"raw_orcid":"https://orcid.org/0000-0001-6479-9200","affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1001","last_page":"1011"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7952658534049988},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5948210954666138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952658534049988},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5948210954666138}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3673038.3673075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673075","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3673038.3673075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673075","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401408716.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2018337509","https://openalex.org/W2028499920","https://openalex.org/W2034822545","https://openalex.org/W2034861439","https://openalex.org/W2047060659","https://openalex.org/W2080592089","https://openalex.org/W2170059648","https://openalex.org/W2415968792","https://openalex.org/W2441593292","https://openalex.org/W2612695082","https://openalex.org/W2619002702","https://openalex.org/W2625200202","https://openalex.org/W2761710529","https://openalex.org/W2802000047","https://openalex.org/W2883882491","https://openalex.org/W2903659818","https://openalex.org/W2929862812","https://openalex.org/W2933483662","https://openalex.org/W2976376602","https://openalex.org/W3017302221","https://openalex.org/W3100877701","https://openalex.org/W4308084044","https://openalex.org/W4319996559","https://openalex.org/W4360831793"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"The":[0],"demand":[1],"for":[2],"greater":[3],"computing":[4],"power":[5],"has":[6],"driven":[7],"the":[8,27,35,65],"development":[9],"of":[10],"Multi-chip-module":[11],"GPUs":[12],"(MCM-GPUs),":[13],"which":[14,53],"greatly":[15],"improve":[16],"parallel":[17],"processing":[18],"capabilities.":[19],"Unfortunately,":[20],"MCM-GPUs":[21],"have":[22],"encountered":[23],"a":[24,50],"notable":[25],"challenge,":[26],"performance":[28],"bottleneck":[29],"caused":[30],"by":[31],"remote":[32],"accesses":[33],"through":[34],"inter-module":[36],"network.":[37],"In":[38],"this":[39],"work,":[40],"we":[41],"found":[42],"significant":[43],"data":[44,74],"access":[45],"redundancy":[46],"among":[47],"SMs":[48],"within":[49],"GPU":[51],"module":[52],"can":[54],"be":[55],"coalesced":[56],"to":[57,63,68],"reduce":[58],"network":[59],"pressure.":[60],"However,":[61],"how":[62],"design":[64],"coalescing":[66],"scheme":[67],"identify":[69],"memory":[70],"addresses":[71],"with":[72],"high":[73],"locality":[75],"is":[76],"still":[77],"not":[78],"clear.":[79]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}