{"id":"https://openalex.org/W4416146765","doi":"https://doi.org/10.1145/3712285.3759774","title":"CPU- and GPU-initiated Communication Strategies for Conjugate Gradient Methods on Large GPU Clusters","display_name":"CPU- and GPU-initiated Communication Strategies for Conjugate Gradient Methods on Large GPU Clusters","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416146765","doi":"https://doi.org/10.1145/3712285.3759774"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759774","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759774","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/10.1145/3712285.3759774","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003537956","display_name":"James Trotter","orcid":"https://orcid.org/0000-0003-4498-020X"},"institutions":[{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"James D. Trotter","raw_affiliation_strings":["Simula Research Laboratory, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Simula Research Laboratory, Oslo, Norway","institution_ids":["https://openalex.org/I2799829267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119879249","display_name":"Sinan Ekmek\u00e7iba\u015f\u0131","orcid":"https://orcid.org/0009-0003-5377-6339"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Sinan Ekmek\u00e7iba\u015f\u0131","raw_affiliation_strings":["Ko\u00e7 University, Istanbul, Turkiye"],"affiliations":[{"raw_affiliation_string":"Ko\u00e7 University, Istanbul, Turkiye","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092212134","display_name":"Do\u011fan Sa\u011fbili","orcid":"https://orcid.org/0000-0002-9603-2466"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Do\u011fan Sa\u011fbili","raw_affiliation_strings":["Ko\u00e7 University, Istanbul, Turkiye"],"affiliations":[{"raw_affiliation_string":"Ko\u00e7 University, Istanbul, Turkiye","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087562583","display_name":"Johannes Langguth","orcid":"https://orcid.org/0000-0003-4200-511X"},"institutions":[{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Johannes Langguth","raw_affiliation_strings":["Simula Research Laboratory, Oslo, Norway and University of Bergen, Bergen, Norway"],"affiliations":[{"raw_affiliation_string":"Simula Research Laboratory, Oslo, Norway and University of Bergen, Bergen, Norway","institution_ids":["https://openalex.org/I2799829267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084482336","display_name":"Xing Cai","orcid":"https://orcid.org/0000-0003-3706-4414"},"institutions":[{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Xing Cai","raw_affiliation_strings":["University of Oslo, Oslo, Norway and Simula Research Laboratory, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"University of Oslo, Oslo, Norway and Simula Research Laboratory, Oslo, Norway","institution_ids":["https://openalex.org/I2799829267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040713791","display_name":"Didem Unat","orcid":"https://orcid.org/0000-0002-2351-0770"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Didem Unat","raw_affiliation_strings":["Ko\u00e7 University, Istanbul, Turkiye"],"affiliations":[{"raw_affiliation_string":"Ko\u00e7 University, Istanbul, Turkiye","institution_ids":["https://openalex.org/I1351752"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003537956"],"corresponding_institution_ids":["https://openalex.org/I2799829267"],"apc_list":null,"apc_paid":null,"fwci":1.42,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87606619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"298","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.3702000081539154,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.3702000081539154,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.31150001287460327,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.12849999964237213,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.7789000272750854},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5281999707221985},{"id":"https://openalex.org/keywords/biconjugate-gradient-method","display_name":"Biconjugate gradient method","score":0.5163000226020813},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5112000107765198},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.49959999322891235},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4982999861240387},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4909999966621399}],"concepts":[{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.7789000272750854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7138000130653381},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5281999707221985},{"id":"https://openalex.org/C89408827","wikidata":"https://www.wikidata.org/wiki/Q855169","display_name":"Biconjugate gradient method","level":5,"score":0.5163000226020813},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5112000107765198},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.49959999322891235},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4909999966621399},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49070000648498535},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43689998984336853},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.40619999170303345},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C197336794","wikidata":"https://www.wikidata.org/wiki/Q5161150","display_name":"Conjugate","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C91394653","wikidata":"https://www.wikidata.org/wiki/Q5161159","display_name":"Conjugate residual method","level":4,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759774","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759774","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:10.1145/3712285.3759774","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759774","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/G5244242995","display_name":null,"funder_award_id":"270053","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"},{"id":"https://openalex.org/G7057791530","display_name":null,"funder_award_id":"949587","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1525132831","https://openalex.org/W1991709203","https://openalex.org/W2002054778","https://openalex.org/W2024565525","https://openalex.org/W2025388037","https://openalex.org/W2035080386","https://openalex.org/W2054522323","https://openalex.org/W2070232376","https://openalex.org/W2070940137","https://openalex.org/W2082007415","https://openalex.org/W2087417231","https://openalex.org/W2096714979","https://openalex.org/W2109977639","https://openalex.org/W2134427337","https://openalex.org/W2316564661","https://openalex.org/W2577617996","https://openalex.org/W2753515784","https://openalex.org/W2778540992","https://openalex.org/W2785822536","https://openalex.org/W2897248362","https://openalex.org/W2964082713","https://openalex.org/W2998812396","https://openalex.org/W3046421657","https://openalex.org/W3122949375","https://openalex.org/W3170377433","https://openalex.org/W3199181189","https://openalex.org/W4247828381","https://openalex.org/W4362566357","https://openalex.org/W4381327256","https://openalex.org/W4384705435","https://openalex.org/W4401704869","https://openalex.org/W4402702025","https://openalex.org/W4403351599","https://openalex.org/W4406574673","https://openalex.org/W4410087793","https://openalex.org/W4414105453"],"related_works":[],"abstract_inverted_index":{"The":[0],"Conjugate":[1],"Gradient":[2],"(CG)":[3],"method":[4],"is":[5],"a":[6],"key":[7],"building":[8],"block":[9],"in":[10,37],"numerous":[11],"applications,":[12],"yet":[13],"its":[14],"low":[15],"computational":[16],"intensity":[17],"and":[18],"sensitivity":[19],"to":[20,26],"communication":[21,39],"overhead":[22],"make":[23],"it":[24],"difficult":[25],"scale":[27],"efficiently":[28],"on":[29],"multi-GPU":[30,38],"systems.":[31],"In":[32],"light":[33],"of":[34],"recent":[35],"advances":[36],"technologies,":[40],"we":[41],"revisit":[42],"CG":[43],"parallelization":[44],"for":[45],"large-scale":[46],"GPU":[47],"clusters.":[48]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-12T00:00:00"}