{"id":"https://openalex.org/W4401568823","doi":"https://doi.org/10.23919/date58400.2024.10546797","title":"Near-Memory Parallel Indexing and Coalescing: Enabling Highly Efficient Indirect Access for SpMV","display_name":"Near-Memory Parallel Indexing and Coalescing: Enabling Highly Efficient Indirect Access for SpMV","publication_year":2024,"publication_date":"2024-03-25","ids":{"openalex":"https://openalex.org/W4401568823","doi":"https://doi.org/10.23919/date58400.2024.10546797"},"language":"en","primary_location":{"id":"doi:10.23919/date58400.2024.10546797","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date58400.2024.10546797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation &amp;amp; Test in Europe Conference &amp;amp; Exhibition (DATE)","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/A5100458165","display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0002-2503-857X"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["ETH Zurich,Integrated Systems Laboratory,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Integrated Systems Laboratory,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052998498","display_name":"Paul Scheffler","orcid":"https://orcid.org/0000-0003-4230-1381"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Paul Scheffler","raw_affiliation_strings":["ETH Zurich,Integrated Systems Laboratory,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Integrated Systems Laboratory,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038724044","display_name":"Thomas Benz","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Thomas Benz","raw_affiliation_strings":["ETH Zurich,Integrated Systems Laboratory,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Integrated Systems Laboratory,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039942285","display_name":"Matteo Perotti","orcid":"https://orcid.org/0000-0003-2413-8592"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Matteo Perotti","raw_affiliation_strings":["ETH Zurich,Integrated Systems Laboratory,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Integrated Systems Laboratory,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043408422","display_name":"Luca Benini","orcid":"https://orcid.org/0000-0001-8068-3806"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["University of Bologna,Department of Electrical, Electronic, and Information Engineering,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bologna,Department of Electrical, Electronic, and Information Engineering,Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3159,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85333091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.980400025844574,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.980400025844574,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9613000154495239,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7983779907226562},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7003284692764282},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5275118947029114},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.47244885563850403},{"id":"https://openalex.org/keywords/random-access-memory","display_name":"Random access memory","score":0.4224604368209839},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.4126374125480652},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1789679229259491},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.14064720273017883},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1117347776889801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983779907226562},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7003284692764282},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5275118947029114},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.47244885563850403},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.4224604368209839},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.4126374125480652},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1789679229259491},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.14064720273017883},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1117347776889801}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/date58400.2024.10546797","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date58400.2024.10546797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation &amp;amp; Test in Europe Conference &amp;amp; Exhibition (DATE)","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/1004736","is_oa":false,"landing_page_url":"https://hdl.handle.net/11585/1004736","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1133087070","https://openalex.org/W1191365092","https://openalex.org/W1588915715","https://openalex.org/W1844274058","https://openalex.org/W2035080386","https://openalex.org/W2036953536","https://openalex.org/W2097215759","https://openalex.org/W2412759392","https://openalex.org/W2624789998","https://openalex.org/W2936567838","https://openalex.org/W2951631461","https://openalex.org/W3089579782","https://openalex.org/W3122403434","https://openalex.org/W3130024571","https://openalex.org/W4281685651","https://openalex.org/W4281719209","https://openalex.org/W4287363917","https://openalex.org/W4307079523","https://openalex.org/W4379116055","https://openalex.org/W4379116149","https://openalex.org/W6790503700"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W4237510188","https://openalex.org/W2130160813","https://openalex.org/W2054476758","https://openalex.org/W2350613701","https://openalex.org/W2130597667"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"multiplication":[2],"(SpMV)":[3],"is":[4,48],"central":[5],"to":[6,83,115],"numerous":[7],"data-intensive":[8],"applications,":[9],"but":[10,40],"requires":[11],"streaming":[12,77,107],"indirect":[13,31,76,108,137],"memory":[14,22,95,125,143],"accesses":[15,109],"that":[16],"severely":[17],"degrade":[18],"both":[19],"processing":[20,34],"and":[21,57,104,119,171],"throughput":[23],"in":[24,110,135],"state-of-the-art":[25],"architectures.":[26],"Near-memory":[27],"hardware":[28],"units,":[29],"decoupling":[30],"streams":[32],"from":[33],"elements,":[35],"partially":[36],"alleviate":[37],"the":[38,62,84,101,117,141],"bottleneck,":[39],"rely":[41],"on":[42,123,154],"low":[43],"DRAM":[44,53],"access":[45],"granularity,":[46],"which":[47],"highly":[49],"inefficient":[50],"for":[51,79],"modern":[52],"standards":[54],"like":[55,113],"HBM":[56],"LPDDR.":[58],"To":[59],"fully":[60],"address":[61],"end-to-end":[63,152],"challenge,":[64],"we":[65,148],"propose":[66],"a":[67,74,146,172,179],"low-overhead":[68],"data":[69],"coa-":[70],"lescer":[71],"combined":[72,98],"with":[73],"near-memory":[75],"unit":[78],"AXI-Pack,":[80],"an":[81,130,150],"extension":[82],"widespread":[85],"AXI4":[86],"protocol":[87],"packing":[88],"narrow":[89],"irregular":[90,111],"stream":[91],"elements":[92],"onto":[93],"wide":[94,124],"buses.":[96],"Our":[97,127],"solution":[99,128],"leverages":[100],"memory-level":[102],"parallelism":[103],"coalescence":[105],"of":[106,133,156,168,177],"applications":[112],"SpMV":[114,155],"maximize":[116],"performance":[118],"bandwidth":[120],"efficiency":[121],"attained":[122],"interfaces.":[126],"delivers":[129],"average":[131,151],"speedup":[132,153],"8x":[134],"effective":[136],"access,":[138],"often":[139],"reaching":[140],"full":[142],"bandwidth.":[144],"As":[145],"result,":[147],"achieve":[149],"3x.":[157],"Moreover,":[158],"our":[159],"approach":[160],"demonstrates":[161],"remarkable":[162],"on-chip":[163,169],"efficiency,":[164],"requiring":[165],"merely":[166],"27kB":[167],"storage":[170],"very":[173],"compact":[174],"implementation":[175],"area":[176],"O.2-0.3mm2in":[178],"12nm":[180],"node.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2024-08-15T00:00:00"}
