{"id":"https://openalex.org/W3115793066","doi":"https://doi.org/10.1109/hpec43674.2020.9286152","title":"On the Feasibility of Using Reduced-Precision Tensor Core Operations for Graph Analytics","display_name":"On the Feasibility of Using Reduced-Precision Tensor Core Operations for Graph Analytics","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3115793066","doi":"https://doi.org/10.1109/hpec43674.2020.9286152","mag":"3115793066"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063476184","display_name":"Jesun Firoz","orcid":"https://orcid.org/0000-0002-8174-2545"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jesun Sahariar Firoz","raw_affiliation_strings":["Pacific Northwest National Laboratory, Washington, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Washington, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413657","display_name":"Ang Li","orcid":"https://orcid.org/0000-0003-3734-9137"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ang Li","raw_affiliation_strings":["Pacific Northwest National Laboratory, Washington, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Washington, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454305","display_name":"Jiajia Li","orcid":"https://orcid.org/0000-0003-1270-4147"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajia Li","raw_affiliation_strings":["Pacific Northwest National Laboratory, Washington, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Washington, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038062469","display_name":"Kevin Barker","orcid":"https://orcid.org/0000-0003-4947-0559"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Barker","raw_affiliation_strings":["Pacific Northwest National Laboratory, Washington, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Washington, USA","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063476184"],"corresponding_institution_ids":["https://openalex.org/I142606810"],"apc_list":null,"apc_paid":null,"fwci":1.1552,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78353659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9991000294685364,"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":0.998199999332428,"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":0.7974066734313965},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.605661928653717},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6055382490158081},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5623478293418884},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5307785272598267},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49045178294181824},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.48347049951553345},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.48066723346710205},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.43711382150650024},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4322616457939148},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.40320125222206116},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.20028826594352722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18858858942985535},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17498114705085754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09197551012039185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7974066734313965},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.605661928653717},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6055382490158081},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5623478293418884},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5307785272598267},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49045178294181824},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.48347049951553345},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.48066723346710205},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.43711382150650024},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4322616457939148},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.40320125222206116},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.20028826594352722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18858858942985535},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17498114705085754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09197551012039185},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1665157575","https://openalex.org/W1783256592","https://openalex.org/W1985291160","https://openalex.org/W2035080386","https://openalex.org/W2041470524","https://openalex.org/W2042545849","https://openalex.org/W2141380216","https://openalex.org/W2249637006","https://openalex.org/W2581090187","https://openalex.org/W2765934619","https://openalex.org/W2791673912","https://openalex.org/W2796649226","https://openalex.org/W2901549770","https://openalex.org/W2920798074","https://openalex.org/W2947061677","https://openalex.org/W2951135776","https://openalex.org/W3006582303","https://openalex.org/W3043303806","https://openalex.org/W3101543398","https://openalex.org/W3104528661","https://openalex.org/W3108141724","https://openalex.org/W4245208434","https://openalex.org/W4294761111"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W3121314575","https://openalex.org/W3147497457","https://openalex.org/W4206336957","https://openalex.org/W4225552076","https://openalex.org/W1973961853","https://openalex.org/W3004823601"],"abstract_inverted_index":{"Today's":[0],"data-driven":[1],"analytics":[2],"and":[3,42,91,133],"machine":[4],"learning":[5],"workload":[6],"have":[7,30],"been":[8,31],"largely":[9],"driven":[10],"by":[11],"the":[12,24,50,66,78,86,89,101,110,125],"General-Purpose":[13],"Graphics":[14],"Processing":[15],"Units":[16,28],"(GPGPUs).":[17],"To":[18],"accelerate":[19],"dense":[20],"matrix":[21,97],"multiplications":[22],"on":[23,49,77,100,109,124,129],"GPUs,":[25],"Tensor":[26,79],"Core":[27,80],"(TCUs)":[29],"introduced":[32],"in":[33,69,94,119],"recent":[34],"years.":[35],"In":[36,82],"this":[37,57],"paper,":[38],"we":[39,84],"study":[40],"linear-algebra-based":[41],"vertex-centric":[43],"algorithms":[44],"for":[45,139],"various":[46,140],"graph":[47,62,71,115,141],"kernels":[48,72],"GPUs":[51],"with":[52],"an":[53,121],"objective":[54],"of":[55,88,96],"applying":[56],"new":[58],"hardware":[59],"feature":[60],"to":[61],"applications.":[63],"We":[64,103],"identify":[65],"potential":[67],"stages":[68],"these":[70,107],"that":[73,105],"can":[74,117,135],"be":[75],"executed":[76],"Units.":[81],"particular,":[83],"leverage":[85],"reformulation":[87],"reduction":[90],"scan":[92],"operations":[93,108],"terms":[95],"multiplication":[98],"[1]":[99],"TCUs.":[102],"demonstrate":[104],"executing":[106],"TCUs,":[111],"available":[112],"inside":[113],"different":[114],"kernels,":[116],"assist":[118],"establishing":[120],"end-to-end":[122],"pipeline":[123],"GPGPUs":[126],"without":[127],"depending":[128],"hand-tuned":[130],"external":[131],"libraries":[132],"still":[134],"deliver":[136],"comparable":[137],"performance":[138],"analytics.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}