{"id":"https://openalex.org/W4389476354","doi":"https://doi.org/10.1145/3613424.3623783","title":"Spatula: A Hardware Accelerator for Sparse Matrix Factorization","display_name":"Spatula: A Hardware Accelerator for Sparse Matrix Factorization","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4389476354","doi":"https://doi.org/10.1145/3613424.3623783"},"language":"en","primary_location":{"id":"doi:10.1145/3613424.3623783","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3623783","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623783","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","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/10.1145/3613424.3623783","any_repository_has_fulltext":true},"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/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Axel Feldmann","raw_affiliation_strings":["Massachusetts Institute of Technology, USA"],"raw_orcid":"https://orcid.org/0000-0002-8797-7476","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"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/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Sanchez","raw_affiliation_strings":["Massachusetts Institute of Technology, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-2453-2904","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, United States of America","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":1.8188,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90478826,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991000294685364,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9962999820709229,"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/sparse-matrix","display_name":"Sparse matrix","score":0.7513598203659058},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7300863862037659},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.7063538432121277},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.6684018969535828},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.662519097328186},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5577723979949951},{"id":"https://openalex.org/keywords/incomplete-lu-factorization","display_name":"Incomplete LU factorization","score":0.5427894592285156},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5239924788475037},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5184575915336609},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.517966628074646},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48409879207611084},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.46851658821105957},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4272632300853729},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3491000831127167},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2904483675956726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22984063625335693},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.16448909044265747},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1563425064086914},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.08092641830444336},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.07465225458145142},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06459349393844604}],"concepts":[{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7513598203659058},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300863862037659},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.7063538432121277},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.6684018969535828},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.662519097328186},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5577723979949951},{"id":"https://openalex.org/C134978465","wikidata":"https://www.wikidata.org/wiki/Q1654069","display_name":"Incomplete LU factorization","level":4,"score":0.5427894592285156},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5239924788475037},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5184575915336609},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.517966628074646},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48409879207611084},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.46851658821105957},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4272632300853729},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3491000831127167},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2904483675956726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22984063625335693},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.16448909044265747},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1563425064086914},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.08092641830444336},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.07465225458145142},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06459349393844604},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3613424.3623783","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3623783","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623783","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/153276","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/153276","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/153276/1/3613424.3623783.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"doi:10.1145/3613424.3623783","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3623783","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623783","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389476354.pdf","grobid_xml":"https://content.openalex.org/works/W4389476354.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W53967744","https://openalex.org/W122884203","https://openalex.org/W626673124","https://openalex.org/W1520511539","https://openalex.org/W1959955997","https://openalex.org/W1970009422","https://openalex.org/W1975489482","https://openalex.org/W2020561008","https://openalex.org/W2021869025","https://openalex.org/W2030909247","https://openalex.org/W2035080386","https://openalex.org/W2041999884","https://openalex.org/W2051917325","https://openalex.org/W2063675347","https://openalex.org/W2089024363","https://openalex.org/W2089898547","https://openalex.org/W2118076222","https://openalex.org/W2130408605","https://openalex.org/W2133313078","https://openalex.org/W2157229523","https://openalex.org/W2160106215","https://openalex.org/W2169339215","https://openalex.org/W2208934446","https://openalex.org/W2325556328","https://openalex.org/W2444544770","https://openalex.org/W2502797786","https://openalex.org/W2588282852","https://openalex.org/W2794952988","https://openalex.org/W2898123186","https://openalex.org/W2979310060","https://openalex.org/W2979747168","https://openalex.org/W3015783148","https://openalex.org/W3016735325","https://openalex.org/W3016769527","https://openalex.org/W3016832937","https://openalex.org/W3016904661","https://openalex.org/W3040024858","https://openalex.org/W3121402054","https://openalex.org/W3155922894","https://openalex.org/W3158275024","https://openalex.org/W3187908937","https://openalex.org/W3207878884","https://openalex.org/W4210574274","https://openalex.org/W4214718338","https://openalex.org/W4214725219","https://openalex.org/W4236433846","https://openalex.org/W4300171661","https://openalex.org/W4318540786","https://openalex.org/W4327930477","https://openalex.org/W4360831992"],"related_works":["https://openalex.org/W1835670156","https://openalex.org/W1987177655","https://openalex.org/W2964496048","https://openalex.org/W2904573237","https://openalex.org/W4381050447","https://openalex.org/W4289119257","https://openalex.org/W1543309964","https://openalex.org/W2898722594","https://openalex.org/W4296405127","https://openalex.org/W3014000538"],"abstract_inverted_index":{"Solving":[0],"sparse":[1,74],"systems":[2],"of":[3,27,46,59],"linear":[4,75],"equations":[5],"is":[6],"a":[7,24],"crucial":[8],"component":[9],"in":[10],"many":[11],"science":[12],"and":[13,52,54,72],"engineering":[14],"problems,":[15],"like":[16],"simulating":[17],"physical":[18],"systems.":[19],"Sparse":[20],"matrix":[21],"factorization":[22,31],"dominates":[23],"large":[25],"class":[26],"these":[28,63],"solvers.":[29],"Efficient":[30],"algorithms":[32],"have":[33],"two":[34],"key":[35],"properties":[36],"that":[37,49],"make":[38,67],"them":[39],"challenging":[40],"for":[41],"existing":[42],"architectures:":[43],"they":[44],"consist":[45],"small":[47],"tasks":[48],"are":[50],"structured":[51],"compute-intensive,":[53],"sparsity":[55],"induces":[56],"long":[57],"chains":[58],"data":[60],"dependences":[61,66],"among":[62],"tasks.":[64],"Data":[65],"GPUs":[68],"struggle,":[69],"while":[70],"CPUs":[71],"prior":[73],"algebra":[76],"accelerators":[77],"also":[78],"suffer":[79],"from":[80],"low":[81],"compute":[82],"throughput.":[83]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}