{"id":"https://openalex.org/W4416203786","doi":"https://doi.org/10.1145/3712285.3759811","title":"A Streaming Collectives Interface Targeting Dataflow Acceleration and HPC Workloads","display_name":"A Streaming Collectives Interface Targeting Dataflow Acceleration and HPC Workloads","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416203786","doi":"https://doi.org/10.1145/3712285.3759811"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759811","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759811","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3712285.3759811","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092212149","display_name":"Nicholas Contini","orcid":"https://orcid.org/0009-0006-1918-397X"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nicholas Contini","raw_affiliation_strings":["Ohio State University, Columbus, Ohio, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120400064","display_name":"Jake Queiser","orcid":"https://orcid.org/0009-0006-6421-2768"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jake Queiser","raw_affiliation_strings":["Ohio State University, Columbus, Ohio, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103171233","display_name":"Bharath Ramesh","orcid":"https://orcid.org/0000-0002-6430-8587"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bharath Ramesh","raw_affiliation_strings":["Ohio State University, Columbus, Ohio, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034293705","display_name":"Hari Subramoni","orcid":"https://orcid.org/0000-0002-1200-2754"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hari Subramoni","raw_affiliation_strings":["Ohio State University, Columbus, Ohio, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhabaleswar K. Panda","raw_affiliation_strings":["Ohio State University, Columbus, Ohio, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092212149"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.1983,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90142591,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1935","last_page":"1950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5224999785423279,"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":0.5224999785423279,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.3693999946117401,"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":0.011900000274181366,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.906499981880188},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6851999759674072},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.65829998254776},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.65420001745224},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.6194999814033508},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6111000180244446},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5246000289916992},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.489300012588501},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45159998536109924}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.906499981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8499000072479248},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6851999759674072},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.65829998254776},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.65420001745224},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.6194999814033508},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6111000180244446},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5246000289916992},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C103987645","wikidata":"https://www.wikidata.org/wiki/Q985806","display_name":"Network interface","level":3,"score":0.4429999887943268},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.33390000462532043},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3255999982357025},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.29019999504089355},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26489999890327454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759811","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759811","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3712285.3759811","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759811","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2649662271","display_name":null,"funder_award_id":"NCR-130002","funder_id":"https://openalex.org/F4320314399","funder_display_name":"Access Group Center for Research and Policy Analysis"},{"id":"https://openalex.org/G965775444","display_name":null,"funder_award_id":"2311830, 2312927, 2323116, 2415201, 2504944","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320314399","display_name":"Access Group Center for Research and Policy Analysis","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2070940137","https://openalex.org/W2294630901","https://openalex.org/W2538589664","https://openalex.org/W2626953429","https://openalex.org/W2894590528","https://openalex.org/W2899691047","https://openalex.org/W2971734772","https://openalex.org/W3010835436","https://openalex.org/W3013726790","https://openalex.org/W3103188330","https://openalex.org/W3121665290","https://openalex.org/W3123031798","https://openalex.org/W3127736057","https://openalex.org/W3128575430","https://openalex.org/W3158831985","https://openalex.org/W4206396251","https://openalex.org/W4288086140","https://openalex.org/W4311787046","https://openalex.org/W4313894250","https://openalex.org/W4319067108","https://openalex.org/W4319309389","https://openalex.org/W4360831816","https://openalex.org/W4381327316","https://openalex.org/W4400446017","https://openalex.org/W4401861898","https://openalex.org/W4405755182","https://openalex.org/W4406157368","https://openalex.org/W4406171852"],"related_works":[],"abstract_inverted_index":{"Dataflow":[0],"accelerators":[1],"can":[2,73],"provide":[3],"energy":[4],"efficient":[5],"and":[6,52,79,128],"high-performance":[7],"alternatives":[8],"to":[9,19,36,49,54,56,68,81,117,122],"current":[10],"popular":[11],"architectures.":[12,27],"However,":[13],"little":[14],"work":[15],"has":[16],"been":[17],"done":[18],"enable":[20],"accelerator-initiated,":[21],"scalable":[22],"collective":[23],"communication":[24],"for":[25,94],"these":[26],"We":[28,110],"develop":[29,61],"a":[30,62,86,97,138,146],"High":[31],"Level":[32],"Synthesis":[33],"(HLS)":[34],"interface":[35,64,89],"bridge":[37],"this":[38],"gap":[39],"through":[40,77],"software-hardware":[41],"co-design.":[42],"Given":[43],"the":[44,69,82,88,102],"tendency":[45],"of":[46],"dataflow":[47],"applications":[48],"use":[50],"reads":[51],"writes":[53],"streams":[55],"express":[57],"data":[58],"transfer,":[59],"we":[60,100,136],"streaming":[63],"implementing":[65],"fine-grained":[66],"transfers":[67],"host":[70],"processor.":[71],"Data":[72],"then":[74],"be":[75],"communicated":[76],"MPI":[78],"transferred":[80],"receiving":[83],"accelerator.":[84],"As":[85,96],"result,":[87],"uses":[90],"few":[91],"hardware":[92],"resources":[93],"communication.":[95],"case":[98],"study,":[99],"enhance":[101],"HPL":[103],"benchmark":[104,140],"from":[105],"HPCC_FPGA":[106],"with":[107],"our":[108,112],"contributions.":[109],"evaluate":[111],"final":[113],"design":[114,137],"on":[115],"up":[116,121],"16":[118],"FPGAs,":[119],"achieving":[120],"18%":[123],"improvement":[124],"in":[125,132,145],"application":[126],"throughput":[127],"36%":[129],"reduced":[130],"latency":[131],"kernel":[133],"execution.":[134],"Additionally,":[135],"stencil":[139],"that":[141],"showcases":[142],"superlinear":[143],"speedup":[144],"strong":[147],"scaling":[148],"scenario.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-12T00:00:00"}