{"id":"https://openalex.org/W4407857172","doi":"https://doi.org/10.1145/3696443.3708918","title":"Stardust: Compiling Sparse Tensor Algebra to a Reconfigurable Dataflow Architecture","display_name":"Stardust: Compiling Sparse Tensor Algebra to a Reconfigurable Dataflow Architecture","publication_year":2025,"publication_date":"2025-02-22","ids":{"openalex":"https://openalex.org/W4407857172","doi":"https://doi.org/10.1145/3696443.3708918"},"language":"en","primary_location":{"id":"doi:10.1145/3696443.3708918","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696443.3708918","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 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3696443.3708918","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039681071","display_name":"Olivia Hsu","orcid":"https://orcid.org/0000-0002-4195-8106"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Olivia Hsu","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068091924","display_name":"Alexander Rucker","orcid":"https://orcid.org/0000-0002-1928-0845"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Rucker","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100300092","display_name":"Tian Zhao","orcid":"https://orcid.org/0000-0001-6702-2114"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Zhao","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087530766","display_name":"Varun Bhavin Desai","orcid":"https://orcid.org/0009-0003-9936-2422"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Varun Desai","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023857198","display_name":"Kunle Olukotun","orcid":"https://orcid.org/0000-0002-8779-0636"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunle Olukotun","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041886781","display_name":"Fredrik Kj\u00f8lstad","orcid":"https://orcid.org/0000-0002-2267-903X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fredrik Kjolstad","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5039681071"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":6.8108,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95732471,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"628","last_page":"643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9961000084877014,"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/dataflow","display_name":"Dataflow","score":0.9148737192153931},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7032254934310913},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5677921772003174},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5113019943237305},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4970722496509552},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4669037461280823},{"id":"https://openalex.org/keywords/tensor-algebra","display_name":"Tensor algebra","score":0.4453226923942566},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.39762017130851746},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.37491026520729065},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.34088942408561707},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19217342138290405},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.11622875928878784},{"id":"https://openalex.org/keywords/algebra-representation","display_name":"Algebra representation","score":0.0819181501865387},{"id":"https://openalex.org/keywords/cellular-algebra","display_name":"Cellular algebra","score":0.048443615436553955}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9148737192153931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7032254934310913},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5677921772003174},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5113019943237305},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4970722496509552},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4669037461280823},{"id":"https://openalex.org/C1680195","wikidata":"https://www.wikidata.org/wiki/Q2296021","display_name":"Tensor algebra","level":5,"score":0.4453226923942566},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.39762017130851746},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.37491026520729065},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34088942408561707},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19217342138290405},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.11622875928878784},{"id":"https://openalex.org/C14394260","wikidata":"https://www.wikidata.org/wiki/Q4723980","display_name":"Algebra representation","level":3,"score":0.0819181501865387},{"id":"https://openalex.org/C100899422","wikidata":"https://www.wikidata.org/wiki/Q5058347","display_name":"Cellular algebra","level":4,"score":0.048443615436553955},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696443.3708918","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696443.3708918","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 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696443.3708918","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696443.3708918","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 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1537260300","https://openalex.org/W1538707437","https://openalex.org/W2034861439","https://openalex.org/W2035080386","https://openalex.org/W2039795558","https://openalex.org/W2082533328","https://openalex.org/W2148570406","https://openalex.org/W2153204928","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2590246587","https://openalex.org/W2794952988","https://openalex.org/W2798482398","https://openalex.org/W2898123186","https://openalex.org/W2925491732","https://openalex.org/W2979310060","https://openalex.org/W2980270412","https://openalex.org/W3016832937","https://openalex.org/W3103168911","https://openalex.org/W3108012228","https://openalex.org/W3121402054","https://openalex.org/W3155922894","https://openalex.org/W3158233278","https://openalex.org/W3190681843","https://openalex.org/W3207857196","https://openalex.org/W4220690649","https://openalex.org/W4229485246","https://openalex.org/W4240061986","https://openalex.org/W4245643018","https://openalex.org/W4255450819","https://openalex.org/W4285049632","https://openalex.org/W4286571734","https://openalex.org/W4287755308","https://openalex.org/W4290648346","https://openalex.org/W4310251122","https://openalex.org/W4327911434","https://openalex.org/W4327911471","https://openalex.org/W4365800001","https://openalex.org/W6660308306"],"related_works":["https://openalex.org/W1998888015","https://openalex.org/W2914322253","https://openalex.org/W2767274246","https://openalex.org/W2590246587","https://openalex.org/W3160402525","https://openalex.org/W4387667068","https://openalex.org/W4309795463","https://openalex.org/W2050785904","https://openalex.org/W2467190317","https://openalex.org/W2108207327"],"abstract_inverted_index":{"We":[0],"introduce":[1],"Stardust,":[2],"a":[3,11,17],"compiler":[4],"from":[5,33,64],"sparse":[6,12,97],"tensor":[7,90],"algebra":[8,91],"languages":[9],"to":[10,57,75],"reconfigurable":[13],"dataflow":[14],"architecture":[15],"via":[16],"parallel-patterns":[18],"programming":[19],"model.":[20],"Stardust":[21,53,67,86],"lets":[22],"performance":[23],"engineers":[24],"specify":[25],"the":[26,34,76,94],"placement":[27,35,45],"of":[28,36],"data":[29,44,56,73],"into":[30],"memories":[31],"separately":[32],"computation":[37,69],"onto":[38,46],"compute":[39],"units.":[40],"Users":[41],"first":[42],"schedule":[43],"an":[47],"abstract":[48],"memory":[49],"model,":[50],"and":[51,112],"then":[52],"binds":[54,68],"that":[55,85],"complex,":[58],"on-chip":[59,72],"physical":[60],"memories.":[61],"With":[62],"guidance":[63],"user":[65],"schedules,":[66],"using":[70],"these":[71],"structures":[74],"appropriate":[77],"parallel":[78],"patterns.":[79],"Through":[80],"cycle-accurate":[81],"simulation,":[82],"we":[83],"show":[84],"generates":[87],"nine":[88],"more":[89],"kernels":[92,102,111],"than":[93,108,115],"original":[95],"Capstan":[96],"RDA":[98],"work.":[99],"The":[100],"generated":[101,109,116],"perform,":[103],"on":[104],"average,":[105],"138\u00d7":[106],"better":[107,114],"CPU":[110],"41\u00d7":[113],"GPU":[117],"kernels.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}