{"id":"https://openalex.org/W4376123125","doi":"https://doi.org/10.1109/tpds.2023.3322029","title":"Sparse Stream Semantic Registers: A Lightweight ISA Extension Accelerating General Sparse Linear Algebra","display_name":"Sparse Stream Semantic Registers: A Lightweight ISA Extension Accelerating General Sparse Linear Algebra","publication_year":2023,"publication_date":"2023-10-04","ids":{"openalex":"https://openalex.org/W4376123125","doi":"https://doi.org/10.1109/tpds.2023.3322029"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2023.3322029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3322029","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.05559","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 (IIS), ETH Zurich, Zürich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-4230-1381","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory (IIS), ETH Zurich, Zürich, Switzerland","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Zaruba","raw_affiliation_strings":["Zurich branch of Axelera AI, Zürich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-8194-6521","affiliations":[{"raw_affiliation_string":"Zurich branch of Axelera AI, Zürich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024145677","display_name":"Fabian Schuiki","orcid":"https://orcid.org/0000-0002-9923-5031"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabian Schuiki","raw_affiliation_strings":["SiFive, San Mateo, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9923-5031","affiliations":[{"raw_affiliation_string":"SiFive, San Mateo, CA, USA","institution_ids":[]}]},{"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 (SPCL), ETH Zurich, Zürich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-1333-9797","affiliations":[{"raw_affiliation_string":"Scalable Parallel Computing Laboratory (SPCL), ETH Zurich, Zürich, 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/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"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":["CH","IT"],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["Integrated Systems Laboratory (IIS), ETH Zurich, Zürich, Switzerland","Department of Electrical, Electronic, and Information Engineering (DEI), University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8068-3806","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory (IIS), ETH Zurich, Zürich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Electrical, Electronic, and Information Engineering (DEI), University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0367,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94524715,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"34","issue":"12","first_page":"3147","last_page":"3161"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9972000122070312,"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/T10829","display_name":"Interconnection Networks and 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/computer-science","display_name":"Computer science","score":0.7952296733856201},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7026796936988831},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6642751693725586},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.6593702435493469},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.5157175660133362},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.44715213775634766},{"id":"https://openalex.org/keywords/dense-graph","display_name":"Dense graph","score":0.4419839382171631},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33582502603530884},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3041865825653076},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.26972439885139465},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.17402967810630798},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.1429426372051239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952296733856201},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7026796936988831},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6642751693725586},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.6593702435493469},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5157175660133362},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.44715213775634766},{"id":"https://openalex.org/C13251829","wikidata":"https://www.wikidata.org/wiki/Q3085841","display_name":"Dense graph","level":5,"score":0.4419839382171631},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33582502603530884},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3041865825653076},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.26972439885139465},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.17402967810630798},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.1429426372051239},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.0},{"id":"https://openalex.org/C102192266","wikidata":"https://www.wikidata.org/wiki/Q4545823","display_name":"1-planar graph","level":4,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tpds.2023.3322029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3322029","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2305.05559","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05559","pdf_url":"https://arxiv.org/pdf/2305.05559","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:cris.unibo.it:11585/956614","is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/956614","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/636014","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/636014","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems, 34 (12)","raw_type":"info:eu-repo/semantics/acceptedVersion"},{"id":"doi:10.3929/ethz-b-000636014","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000636014","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.05559","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05559","pdf_url":"https://arxiv.org/pdf/2305.05559","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8899999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4376123125.pdf","grobid_xml":"https://content.openalex.org/works/W4376123125.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1191365092","https://openalex.org/W1969648707","https://openalex.org/W1987692736","https://openalex.org/W2026121678","https://openalex.org/W2035080386","https://openalex.org/W2112482011","https://openalex.org/W2114977680","https://openalex.org/W2130187411","https://openalex.org/W2142820603","https://openalex.org/W2147542748","https://openalex.org/W2153754850","https://openalex.org/W2245094585","https://openalex.org/W2340076492","https://openalex.org/W2613264175","https://openalex.org/W2791012218","https://openalex.org/W2794952988","https://openalex.org/W2887161653","https://openalex.org/W2950656546","https://openalex.org/W2979310060","https://openalex.org/W2979439447","https://openalex.org/W2979747168","https://openalex.org/W2980186997","https://openalex.org/W2980270412","https://openalex.org/W3013692244","https://openalex.org/W3016309475","https://openalex.org/W3035047393","https://openalex.org/W3040646053","https://openalex.org/W3082779563","https://openalex.org/W3089579782","https://openalex.org/W3091170309","https://openalex.org/W3100023286","https://openalex.org/W3103168911","https://openalex.org/W3105514082","https://openalex.org/W3110597019","https://openalex.org/W3122403434","https://openalex.org/W3123542955","https://openalex.org/W3134223578","https://openalex.org/W3150538041","https://openalex.org/W3152508978","https://openalex.org/W3175189837","https://openalex.org/W3175878603","https://openalex.org/W3187908937","https://openalex.org/W3188321821","https://openalex.org/W3191906639","https://openalex.org/W3202552726","https://openalex.org/W3206117777","https://openalex.org/W4214718338","https://openalex.org/W4247828381","https://openalex.org/W4285104934","https://openalex.org/W4287363917","https://openalex.org/W6639055396","https://openalex.org/W6764770523","https://openalex.org/W6790503700"],"related_works":["https://openalex.org/W2091883426","https://openalex.org/W2174948646","https://openalex.org/W3173235360","https://openalex.org/W2024017047","https://openalex.org/W4318256793","https://openalex.org/W2051410394","https://openalex.org/W2594370889","https://openalex.org/W2390720471","https://openalex.org/W1600789676","https://openalex.org/W2134327945"],"abstract_inverted_index":{"Sparse":[0],"linear":[1],"algebra":[2],"is":[3],"crucial":[4],"in":[5,14,183],"many":[6],"application":[7],"domains,":[8],"but":[9],"challenging":[10],"to":[11,40,86,106,125,132,155,185],"handle":[12],"efficiently":[13],"both":[15,42],"software":[16],"and":[17,21,44,58,72,89,96,100,116,127,130,134,150,159,173,200,213,217,228,232],"hardware,":[18],"with":[19,26,191],"one-":[20,43],"two-sided":[22,45],"operand":[23,46],"sparsity":[24,47],"handled":[25],"distinct":[27],"approaches.":[28],"In":[29],"this":[30],"work,":[31],"we":[32],"enhance":[33],"an":[34,80,112],"existing":[35],"memory-streaming":[36],"RISC-V":[37,82],"ISA":[38],"extension":[39],"accelerate":[41],"on":[48,91,108,167],"widespread":[49],"sparse":[50,55,60,210],"tensor":[51],"formats":[52],"like":[53],"compressed":[54,59],"row":[56],"(CSR)":[57],"fiber":[61],"(CSF)":[62],"by":[63],"accelerating":[64],"the":[65],"underlying":[66],"operations":[67],"of":[68,84,104,171],"streaming":[69],"indirection,":[70],"intersection,":[71],"union.":[73],"Our":[74],"extensions":[75,163,193],"enable":[76,164],"single-core":[77],"speedups":[78],"over":[79],"optimized":[81,209],"baseline":[83],"up":[85,105,124,131],"7.0x,":[87],"7.7x,":[88],"9.8x":[90],"sparse-dense":[92,109,115],"multiply,":[93,95],"sparse-sparse":[94,97,117],"addition,":[98],"respectively,":[99,219],"peak":[101,203],"FPU":[102],"utilizations":[103,205],"80%":[107],"problems.":[110],"On":[111],"eight-core":[113],"cluster,":[114],"matrix-vector":[118,196],"multiply":[119],"using":[120],"real-world":[121],"matrices":[122],"are":[123],"4.9x":[126],"5.9x":[128],"faster":[129],"2.9x":[133],"3.0x":[135],"more":[136],"energy":[137],"efficient.":[138],"We":[139],"explore":[140],"further":[141],"applications":[142],"for":[143,215,223],"our":[144,162,192],"extensions,":[145],"such":[146],"as":[147],"stencil":[148],"codes":[149],"graph":[151],"pattern":[152],"matching.":[153],"Compared":[154],"recent":[156,207],"CPU,":[157],"GPU,":[158,218],"accelerator":[160],"approaches,":[161],"higher":[165,202],"flexibility":[166],"data":[168,211],"representation,":[169],"degree":[170],"sparsity,":[172],"dataflow":[174],"at":[175],"a":[176,186],"minimal":[177],"hardware":[178],"footprint,":[179],"adding":[180],"only":[181],"1.8%":[182],"area":[184],"compute":[187],"cluster.":[188],"A":[189],"cluster":[190],"running":[194],"CSR":[195],"multiplication":[197],"achieves":[198],"9.9x":[199],"1.7x":[201],"floating-point":[204],"than":[206],"highly":[208],"structures":[212],"libraries":[214],"CPU":[216],"even":[220],"when":[221],"accounting":[222],"off-chip":[224],"main":[225],"memory":[226],"(HBM)":[227],"on-chip":[229],"interconnect":[230],"latency":[231],"bandwidth":[233],"effects.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-05-12T00:00:00"}