{"id":"https://openalex.org/W4396814852","doi":"https://doi.org/10.23919/isc.2024.10528923","title":"ROCm-Aware Leader-based Designs for MPI Neighbourhood Collectives","display_name":"ROCm-Aware Leader-based Designs for MPI Neighbourhood Collectives","publication_year":2024,"publication_date":"2024-05-01","ids":{"openalex":"https://openalex.org/W4396814852","doi":"https://doi.org/10.23919/isc.2024.10528923"},"language":"en","primary_location":{"id":"doi:10.23919/isc.2024.10528923","is_oa":true,"landing_page_url":"https://doi.org/10.23919/isc.2024.10528923","pdf_url":"https://ieeexplore.ieee.org/ielx7/10528919/10528920/10528923.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ISC High Performance 2024 Research Paper Proceedings (39th International Conference)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/10528919/10528920/10528923.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081527852","display_name":"Y\u0131ltan Hassan Temu\u00e7in","orcid":"https://orcid.org/0000-0002-4145-4848"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Y\u0131ltan Hassan Temu\u00e7in","raw_affiliation_strings":["Queen's University,ECE Department,Kingston,ON,Canada","ECE Department, Queen's University, Kingston, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University,ECE Department,Kingston,ON,Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"ECE Department, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097335858","display_name":"Mahdieh Gazimirsaeed","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahdieh Gazimirsaeed","raw_affiliation_strings":["DCGPU and Accelerated Processing Advanced Micro Devices Inc,Austin,TX,USA","DCGPU and Accelerated Processing Advanced Micro Devices Inc, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"DCGPU and Accelerated Processing Advanced Micro Devices Inc,Austin,TX,USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"DCGPU and Accelerated Processing Advanced Micro Devices Inc, Austin, TX, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009842811","display_name":"Ryan E. Grant","orcid":"https://orcid.org/0000-0002-0163-3892"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ryan E. Grant","raw_affiliation_strings":["Queen's University,ECE Department,Kingston,ON,Canada","ECE Department, Queen's University, Kingston, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University,ECE Department,Kingston,ON,Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"ECE Department, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039854005","display_name":"Ahmad Afsahi","orcid":"https://orcid.org/0000-0002-2924-6851"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmad Afsahi","raw_affiliation_strings":["Queen's University,ECE Department,Kingston,ON,Canada","ECE Department, Queen's University, Kingston, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University,ECE Department,Kingston,ON,Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"ECE Department, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081527852"],"corresponding_institution_ids":["https://openalex.org/I204722609"],"apc_list":null,"apc_paid":null,"fwci":1.1265,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77473578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9991999864578247,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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":0.9969000220298767,"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/computer-science","display_name":"Computer science","score":0.8550379276275635},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8275203108787537},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7485429644584656},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6944848299026489},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6943623423576355},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6639430522918701},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4557603597640991},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4272286891937256},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.39393362402915955},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35689985752105713},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1403811275959015}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8550379276275635},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8275203108787537},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7485429644584656},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6944848299026489},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6943623423576355},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6639430522918701},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4557603597640991},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4272286891937256},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39393362402915955},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35689985752105713},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1403811275959015},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/isc.2024.10528923","is_oa":true,"landing_page_url":"https://doi.org/10.23919/isc.2024.10528923","pdf_url":"https://ieeexplore.ieee.org/ielx7/10528919/10528920/10528923.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ISC High Performance 2024 Research Paper Proceedings (39th International Conference)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.23919/isc.2024.10528923","is_oa":true,"landing_page_url":"https://doi.org/10.23919/isc.2024.10528923","pdf_url":"https://ieeexplore.ieee.org/ielx7/10528919/10528920/10528923.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ISC High Performance 2024 Research Paper Proceedings (39th International Conference)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396814852.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2035080386","https://openalex.org/W2047102972","https://openalex.org/W2048621586","https://openalex.org/W2097215900","https://openalex.org/W2117859758","https://openalex.org/W2130860518","https://openalex.org/W2469124187","https://openalex.org/W2482039329","https://openalex.org/W2529031466","https://openalex.org/W2739644231","https://openalex.org/W2787701215","https://openalex.org/W2885707392","https://openalex.org/W2963753177","https://openalex.org/W2971519680","https://openalex.org/W3039165326","https://openalex.org/W3092142141","https://openalex.org/W3132234403","https://openalex.org/W3166649773","https://openalex.org/W4210863326","https://openalex.org/W4221150811","https://openalex.org/W4250705075","https://openalex.org/W4284964190","https://openalex.org/W4384705435"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W3138386522","https://openalex.org/W2499279132"],"abstract_inverted_index":{"MPI":[0,20],"neighborhood":[1,76,96,126],"collectives":[2],"were":[3],"introduced":[4],"in":[5],"the":[6,31,63,84,87,115,124,134],"MPI-3.0":[7],"standard":[8],"to":[9,49,71,111,121,130],"support":[10],"sparse":[11],"communication":[12,21,51],"patterns":[13],"used":[14],"by":[15],"many":[16],"applications.":[17],"Simultaneously,":[18],"GPU-Aware":[19],"has":[22,46],"become":[23,47],"a":[24],"prominent":[25],"part":[26],"of":[27,33,62,68,86],"modern":[28],"systems.":[29],"With":[30],"rise":[32],"AMD":[34,54,69],"GPUs":[35,70],"and":[36,65,74,80,94,128],"their":[37],"incorporation":[38],"into":[39],"upcoming":[40],"exascale":[41],"systems":[42],"like":[43],"Frontier,":[44],"it":[45],"essential":[48],"optimize":[50],"libraries":[52],"for":[53,90,114,123,133],"platforms.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,108],"take":[60],"advantage":[61],"hardware":[64],"networking":[66],"features":[67],"design":[72,89],"efficient":[73],"scalable":[75],"collective":[77],"operations:":[78],"allgather":[79],"allgatherv.":[81],"We":[82],"evaluate":[83],"performance":[85],"proposed":[88],"Random":[91,116],"Sparse":[92,117],"Graph":[93,118],"Moore":[95,125],"micro-benchmarks":[97],"as":[98,100],"well":[99],"an":[101],"SpMM":[102,135],"kernel.":[103,136],"The":[104],"results":[105],"show":[106],"that":[107],"obtain":[109],"up":[110,120,129],"7.03x":[112],"speedup":[113,132],"micro-benchmark,":[119,127],"3.82x":[122],"2.29x":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
