{"id":"https://openalex.org/W4401408715","doi":"https://doi.org/10.1145/3673038.3673040","title":"FP16 Acceleration in Structured Multigrid Preconditioner for Real-World Applications","display_name":"FP16 Acceleration in Structured Multigrid Preconditioner for Real-World Applications","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4401408715","doi":"https://doi.org/10.1145/3673038.3673040"},"language":"en","primary_location":{"id":"doi:10.1145/3673038.3673040","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673040","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673040","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 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/10.1145/3673038.3673040","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053505635","display_name":"Yi Zong","orcid":"https://orcid.org/0000-0001-7179-6593"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zong","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0001-7179-6593","affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101338623","display_name":"Peinan Yu","orcid":"https://orcid.org/0009-0003-3801-2832"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peinan Yu","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":"https://orcid.org/0009-0003-3801-2832","affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054211464","display_name":"Haopeng Huang","orcid":"https://orcid.org/0009-0002-1786-9821"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haopeng Huang","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":"https://orcid.org/0009-0002-1786-9821","affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091437474","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0001-9740-6581"},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Tsinghua University, China and Qinghai University, Qinghai Provincial Laboratory for Intelligent Computing and Application, China"],"raw_orcid":"https://orcid.org/0000-0001-9740-6581","affiliations":[{"raw_affiliation_string":"Tsinghua University, China and Qinghai University, Qinghai Provincial Laboratory for Intelligent Computing and Application, China","institution_ids":["https://openalex.org/I116265982","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.257,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88662656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.982699990272522,"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/preconditioner","display_name":"Preconditioner","score":0.8461165428161621},{"id":"https://openalex.org/keywords/multigrid-method","display_name":"Multigrid method","score":0.8048146367073059},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.7305763959884644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6837344765663147},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32920071482658386},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11356517672538757},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11224189400672913},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07840242981910706},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.07689669728279114}],"concepts":[{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.8461165428161621},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.8048146367073059},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.7305763959884644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6837344765663147},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32920071482658386},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11356517672538757},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11224189400672913},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07840242981910706},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.07689669728279114},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3673038.3673040","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673040","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673040","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 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3673038.3673040","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673040","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673040","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 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6253243365","display_name":null,"funder_award_id":"U2242210","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401408715.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1974312429","https://openalex.org/W2048748322","https://openalex.org/W2060497191","https://openalex.org/W2064866134","https://openalex.org/W2070081916","https://openalex.org/W2075463061","https://openalex.org/W2473076915","https://openalex.org/W2484592867","https://openalex.org/W2561555269","https://openalex.org/W3130000720","https://openalex.org/W3210190478","https://openalex.org/W4238309452","https://openalex.org/W4287723806","https://openalex.org/W4381328331","https://openalex.org/W4385164339","https://openalex.org/W4391952019"],"related_works":["https://openalex.org/W4389317411","https://openalex.org/W1492522302","https://openalex.org/W2096454229","https://openalex.org/W2042199958","https://openalex.org/W2120298265","https://openalex.org/W2103149966","https://openalex.org/W2177482563","https://openalex.org/W2016008514","https://openalex.org/W2464766188","https://openalex.org/W2182869042"],"abstract_inverted_index":{"Half-precision":[0],"hardware":[1],"support":[2],"is":[3,16,133],"now":[4],"almost":[5],"ubiquitous.":[6],"In":[7],"contrast":[8],"to":[9,90,171],"its":[10],"active":[11],"use":[12],"in":[13,20,44,54,83,130,178,190],"AI,":[14],"half-precision":[15,34],"less":[17],"commonly":[18],"employed":[19],"scientific":[21,30,45,67],"and":[22,69,103,141,153,159,167,188,192],"engineering":[23],"computing.":[24],"The":[25,85,126,182],"valuable":[26],"proposition":[27],"of":[28,51,60,66,73,123,138,150,175],"accelerating":[29],"computing":[31],"applications":[32],"using":[33],"prompted":[35],"this":[36,75],"study.":[37],"Focusing":[38],"on":[39,58,116,157],"solving":[40],"sparse":[41,61],"linear":[42],"systems":[43],"computing,":[46],"we":[47],"explore":[48],"the":[49,70,109,117,120,136,148,173],"technique":[50],"utilizing":[52,176],"FP16":[53,81,92,177],"multigrid":[55,180],"preconditioners.":[56],"Based":[57],"observations":[59],"matrix":[62],"formats,":[63],"numerical":[64,111],"features":[65],"applications,":[68],"performance":[71],"characteristics":[72],"multigrid,":[74],"study":[76],"formulates":[77],"four":[78],"guidelines":[79],"for":[80],"utilization":[82],"multigrid.":[84],"proposed":[86],"algorithm":[87,152],"demonstrates":[88],"how":[89],"avoid":[91],"overflow":[93],"through":[94],"scaling.":[95],"A":[96],"setup-then-scale":[97],"strategy":[98],"prevents":[99],"FP16\u2019s":[100],"limited":[101],"accuracy":[102],"narrow":[104],"range":[105],"from":[106],"interfering":[107],"with":[108],"multigrid\u2019s":[110],"properties.":[112],"Another":[113],"strategy,":[114],"recover-and-rescale":[115],"fly,":[118],"reduces":[119],"memory":[121],"footprint":[122],"hotspot":[124],"kernels.":[125],"extra":[127],"precision-conversion":[128],"overhead":[129],"mix-precision":[131],"kernels":[132],"addressed":[134],"by":[135],"transformation":[137],"storage":[139],"formats":[140],"SIMD":[142],"implementation.":[143],"Two":[144],"ablation":[145],"experiments":[146],"validate":[147],"effectiveness":[149],"our":[151],"parallel":[154],"kernel":[155],"implementation":[156],"ARM":[158],"X86":[160],"architectures.":[161],"We":[162],"further":[163],"evaluate":[164],"three":[165],"idealized":[166],"five":[168],"real-world":[169],"problems":[170],"demonstrate":[172],"advantage":[174],"a":[179],"preconditioner.":[181],"average":[183],"speedups":[184],"are":[185],"approximately":[186],"2.75x":[187],"1.95x":[189],"preconditioner":[191],"end-to-end":[193],"workflow,":[194],"respectively.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
