{"id":"https://openalex.org/W4404954854","doi":"https://doi.org/10.1109/micro61859.2024.00054","title":"Azul: An Accelerator for Sparse Iterative Solvers Leveraging Distributed On-Chip Memory","display_name":"Azul: An Accelerator for Sparse Iterative Solvers Leveraging Distributed On-Chip Memory","publication_year":2024,"publication_date":"2024-11-02","ids":{"openalex":"https://openalex.org/W4404954854","doi":"https://doi.org/10.1109/micro61859.2024.00054"},"language":"en","primary_location":{"id":"doi:10.1109/micro61859.2024.00054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/micro61859.2024.00054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 57th IEEE/ACM International Symposium on Microarchitecture (MICRO)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5051280931","display_name":"Axel Feldmann","orcid":"https://orcid.org/0000-0002-8797-7476"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Axel Feldmann","raw_affiliation_strings":["MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065082293","display_name":"Courtney Golden","orcid":"https://orcid.org/0009-0009-8874-7873"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Courtney Golden","raw_affiliation_strings":["MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100629263","display_name":"Yifan Yang","orcid":"https://orcid.org/0000-0003-2275-827X"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024384625","display_name":"Joel Emer","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Joel S. Emer","raw_affiliation_strings":["MIT CSAIL/NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL/NVIDIA","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I4405258931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023312480","display_name":"Daniel S\u00e1nchez","orcid":"https://orcid.org/0000-0002-2453-2904"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Sanchez","raw_affiliation_strings":["MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":["https://openalex.org/I4405258931"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9631,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92921582,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"643","last_page":"656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9939000010490417,"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":0.9939000010490417,"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":0.9758999943733215,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9672999978065491,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7618966102600098},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5985106229782104},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.530949056148529},{"id":"https://openalex.org/keywords/system-on-a-chip","display_name":"System on a chip","score":0.48660576343536377},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.44122177362442017},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3816390037536621},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3561008870601654}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7618966102600098},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5985106229782104},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.530949056148529},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.48660576343536377},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.44122177362442017},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3816390037536621},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3561008870601654},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/micro61859.2024.00054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/micro61859.2024.00054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 57th IEEE/ACM International Symposium on Microarchitecture (MICRO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8598912940","display_name":"Collaborative Research: PPoSS: LARGE: A Full-Stack Architecture for Sparse Computation","funder_award_id":"2217099","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1489951562","https://openalex.org/W1506342804","https://openalex.org/W1575701986","https://openalex.org/W1584753249","https://openalex.org/W1969468690","https://openalex.org/W1976033099","https://openalex.org/W1977631509","https://openalex.org/W1985818188","https://openalex.org/W2008940670","https://openalex.org/W2035080386","https://openalex.org/W2046224229","https://openalex.org/W2061919600","https://openalex.org/W2072132691","https://openalex.org/W2080114591","https://openalex.org/W2083868341","https://openalex.org/W2095473989","https://openalex.org/W2108632898","https://openalex.org/W2128765420","https://openalex.org/W2132022337","https://openalex.org/W2140153041","https://openalex.org/W2153024623","https://openalex.org/W2346205343","https://openalex.org/W2435668395","https://openalex.org/W2477447826","https://openalex.org/W2498157954","https://openalex.org/W2537959404","https://openalex.org/W2625052843","https://openalex.org/W2725159389","https://openalex.org/W2793142072","https://openalex.org/W2887674375","https://openalex.org/W2898706692","https://openalex.org/W3015783148","https://openalex.org/W3038558128","https://openalex.org/W3048906546","https://openalex.org/W3133682419","https://openalex.org/W3140062895","https://openalex.org/W3190062760","https://openalex.org/W3199181189","https://openalex.org/W4206097460","https://openalex.org/W4214734582","https://openalex.org/W4226435553","https://openalex.org/W4231369534","https://openalex.org/W4244565703","https://openalex.org/W4245143813","https://openalex.org/W4247434968","https://openalex.org/W4297097318","https://openalex.org/W4297097345","https://openalex.org/W4300171661","https://openalex.org/W4301491118","https://openalex.org/W4360831959","https://openalex.org/W4380875568","https://openalex.org/W4380881167","https://openalex.org/W4381743302","https://openalex.org/W4388292706","https://openalex.org/W4389476354","https://openalex.org/W6678665702","https://openalex.org/W6730147603","https://openalex.org/W6776144682","https://openalex.org/W6841541013","https://openalex.org/W6844339464","https://openalex.org/W6858145189"],"related_works":["https://openalex.org/W2065289416","https://openalex.org/W2017236304","https://openalex.org/W3142211975","https://openalex.org/W2115579119","https://openalex.org/W2136854845","https://openalex.org/W1879443270","https://openalex.org/W2018912978","https://openalex.org/W2130914040","https://openalex.org/W2119122672","https://openalex.org/W4292904049"],"abstract_inverted_index":{"Solving":[0],"sparse":[1,24,146,168],"systems":[2],"of":[3,20,81,134,143],"linear":[4],"equations":[5],"is":[6,76,150],"a":[7,60,79,85,89,107,127,140,163,176],"fundamental":[8],"primitive":[9],"in":[10,71],"many":[11],"numeric":[12],"algorithms.":[13],"Iterative":[14],"solvers":[15,28],"provide":[16],"an":[17],"efficient":[18],"way":[19],"solving":[21],"large,":[22],"highly":[23],"systems.":[25],"However,":[26],"iterative":[27,147,169],"are":[29],"inefficient":[30],"on":[31,139],"existing":[32],"architectures":[33],"because":[34],"they":[35],"perform":[36],"computations":[37],"with":[38,84],"(1)":[39],"poor":[40],"short-term":[41],"reuse,":[42],"which":[43,54],"causes":[44],"frequent":[45],"off-chip":[46],"memory":[47,87],"traffic;":[48],"and":[49,88,114,126,171],"(2)":[50],"challenaing":[51],"data":[52,70,98,113],"dependences,":[53],"limit":[55],"parallelism.":[56],"We":[57,105],"present":[58,106],"Azul,":[59],"hardware":[61],"accelerator":[62,166],"that":[63,111,130],"achieves":[64,131],"high":[65,103,124,132],"arithmetic":[66,135],"intensity":[67],"by":[68],"keeping":[69,96],"distributed":[72],"on-chip":[73,99],"SRAM.":[74],"Azul":[75,149],"organized":[77],"as":[78],"grid":[80],"tiles,":[82],"each":[83],"small":[86],"simple":[90],"processing":[91],"element":[92],"(PE).":[93],"This":[94],"enables":[95],"solver":[97],"across":[100,116],"iterations,":[101],"achieving":[102,123],"reuse.":[104],"novel":[108],"scheduling":[109],"algorithm":[110],"maps":[112],"computation":[115],"PEs":[117],"to":[118],"avoid":[119],"communication":[120],"bottlenecks":[121],"while":[122],"parallelism,":[125],"specialized":[128],"PE":[129],"utilization":[133],"units.":[136],"When":[137],"tested":[138],"representative":[141],"set":[142],"matrices":[144],"for":[145,167],"solvers,":[148,170],"gmean":[151],"217":[152],"\u00d7":[153,173],"faster":[154,161,174],"than":[155,162,175],"state-of-the":[156],"art":[157],"GPU":[158],"implementations,":[159],"159\u00d7":[160],"previously":[164,177],"proposed":[165,178],"90":[172],"distributed-SRAM":[179],"accelerator.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}