{"id":"https://openalex.org/W3098608703","doi":"https://doi.org/10.23919/date51398.2021.9474230","title":"Indirection Stream Semantic Register Architecture for Efficient Sparse-Dense Linear Algebra","display_name":"Indirection Stream Semantic Register Architecture for Efficient Sparse-Dense Linear Algebra","publication_year":2021,"publication_date":"2021-02-01","ids":{"openalex":"https://openalex.org/W3098608703","doi":"https://doi.org/10.23919/date51398.2021.9474230","mag":"3098608703"},"language":"en","primary_location":{"id":"doi:10.23919/date51398.2021.9474230","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date51398.2021.9474230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.08070","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Integrated Systems Laboratory, ETH Zurich, Switzerland","ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058655278","display_name":"Florian Zaruba","orcid":"https://orcid.org/0000-0002-8194-6521"},"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":"Florian Zaruba","raw_affiliation_strings":["Integrated Systems Laboratory, ETH Zurich, Switzerland","ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024145677","display_name":"Fabian Schuiki","orcid":"https://orcid.org/0000-0002-9923-5031"},"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":"Fabian Schuiki","raw_affiliation_strings":["Integrated Systems Laboratory, ETH Zurich, Switzerland","ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"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":"Torsten Hoefler","raw_affiliation_strings":["Scalable Parallel Computing Laboratory, ETH Zurich, Switzerland","ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scalable Parallel Computing Laboratory, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Z\u00fcrich","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/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":"Luca Benini","raw_affiliation_strings":["Integrated Systems Laboratory, ETH Zurich, Switzerland","ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00980092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1787","last_page":"1792"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980000257492065,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.7975413799285889},{"id":"https://openalex.org/keywords/indirection","display_name":"Indirection","score":0.7032126188278198},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6707441210746765},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.561159610748291},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.533896803855896},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.5266396999359131},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.49851489067077637},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4339287579059601},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.42975419759750366},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.41972577571868896},{"id":"https://openalex.org/keywords/dot-product","display_name":"Dot product","score":0.4154033958911896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2195969521999359},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20344901084899902},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.12286928296089172},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1134309470653534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7975413799285889},{"id":"https://openalex.org/C89377073","wikidata":"https://www.wikidata.org/wiki/Q1171224","display_name":"Indirection","level":2,"score":0.7032126188278198},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6707441210746765},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.561159610748291},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.533896803855896},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.5266396999359131},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.49851489067077637},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4339287579059601},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.42975419759750366},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.41972577571868896},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.4154033958911896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2195969521999359},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20344901084899902},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.12286928296089172},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1134309470653534},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.23919/date51398.2021.9474230","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date51398.2021.9474230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.08070","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.08070","pdf_url":"https://arxiv.org/pdf/2011.08070","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2011.08070","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.08070","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3098608703","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.08070","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.08070","pdf_url":"https://arxiv.org/pdf/2011.08070","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3098608703.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2035080386","https://openalex.org/W2112482011","https://openalex.org/W2130187411","https://openalex.org/W2142820603","https://openalex.org/W2147542748","https://openalex.org/W2153754850","https://openalex.org/W2245094585","https://openalex.org/W2285660444","https://openalex.org/W2340076492","https://openalex.org/W2559809597","https://openalex.org/W2613264175","https://openalex.org/W2791012218","https://openalex.org/W2915589364","https://openalex.org/W2979310060","https://openalex.org/W2980186997","https://openalex.org/W3013692244","https://openalex.org/W3016309475","https://openalex.org/W3032491185","https://openalex.org/W3040646053","https://openalex.org/W3085021637","https://openalex.org/W4247828381","https://openalex.org/W6770859363"],"related_works":["https://openalex.org/W2128853364","https://openalex.org/W2168931017","https://openalex.org/W2952625562","https://openalex.org/W2535419693","https://openalex.org/W1965094665","https://openalex.org/W2040556424","https://openalex.org/W1973542104","https://openalex.org/W1572929506","https://openalex.org/W2124007994","https://openalex.org/W2968028996","https://openalex.org/W2963371212","https://openalex.org/W2999652941","https://openalex.org/W3016904661","https://openalex.org/W3107938009","https://openalex.org/W2791204867","https://openalex.org/W1972783048","https://openalex.org/W2782176700","https://openalex.org/W1989568755","https://openalex.org/W2727717548","https://openalex.org/W1981718088"],"abstract_inverted_index":{"Sparse-dense":[0],"linear":[1],"algebra":[2],"is":[3,87],"crucial":[4],"in":[5,136],"many":[6],"domains,":[7],"but":[8],"challenging":[9],"to":[10,41,66,72,89,122],"handle":[11],"efficiently":[12],"on":[13,83],"CPUs,":[14],"GPUs,":[15],"and":[16,25,53,68,92,115,118,126],"accelerators":[17],"alike;":[18],"multiplications":[19],"with":[20,96],"sparse":[21],"formats":[22],"like":[23],"CSR":[24,137],"CSF":[26],"require":[27],"indirect":[28],"memory":[29],"lookups.":[30],"In":[31],"this":[32],"work,":[33],"we":[34],"enhance":[35],"a":[36,84,130,141,147],"memory-streaming":[37],"RISC-V":[38],"ISA":[39],"extension":[40],"accelerate":[42],"sparse-dense":[43],"products":[44],"through":[45],"streaming":[46],"indirection.":[47],"We":[48,103],"present":[49],"efficient":[50],"dot,":[51],"matrix-vector,":[52],"matrix-matrix":[54],"product":[55],"kernels":[56,98],"using":[57],"our":[58,97,108,120],"hardware,":[59,110],"enabling":[60],"single-core":[61],"FPU":[62],"utilizations":[63],"of":[64,70],"up":[65,71,88],"80%":[67],"speedups":[69],"7.2x":[73],"over":[74],"an":[75,100],"optimized":[76,101],"baseline":[77],"without":[78],"extensions.":[79],"A":[80],"matrix-vector":[81,138],"implementation":[82],"multicore":[85],"cluster":[86],"5.8x":[90],"faster":[91],"2.7x":[93],"more":[94],"energy-efficient":[95],"than":[99,140],"baseline.":[102],"propose":[104],"further":[105],"uses":[106],"for":[107],"indirection":[109],"such":[111],"as":[112],"scatter-gather":[113],"operations":[114],"codebook":[116],"decoding,":[117],"compare":[119],"work":[121],"state-of-the-art":[123],"CPU,":[124],"GPU,":[125],"accelerator":[127],"approaches,":[128],"measuring":[129],"2.8x":[131],"higher":[132],"peak":[133],"FP64":[134],"utilization":[135],"multiplication":[139],"GTX":[142],"1080":[143],"Ti":[144],"GPU":[145],"running":[146],"cuSPARSE":[148],"kernel.":[149]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}