{"id":"https://openalex.org/W7116404693","doi":"https://doi.org/10.1145/3754598.3754613","title":"VES: Vectorized Sparse General Matrix-Matrix Multiplication on Multi-Core DSPs","display_name":"VES: Vectorized Sparse General Matrix-Matrix Multiplication on Multi-Core DSPs","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7116404693","doi":"https://doi.org/10.1145/3754598.3754613"},"language":null,"primary_location":{"id":"doi:10.1145/3754598.3754613","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3754598.3754613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","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/A5113325229","display_name":"Chuhe Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chuhe Hong","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0000-5746-164X","affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120929812","display_name":"Qinglin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinglin Wang","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-8286-6566","affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120930531","display_name":"Xing Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Peng","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0008-2113-301X","affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057059099","display_name":"Gencheng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gencheng Liu","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0007-5015-4736","affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120918606","display_name":"Qingyang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Zhang","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-7396-874X","affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120909074","display_name":"Xinhai Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhai Chen","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-2931-4893","affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jie Liu","orcid":"https://orcid.org/0000-0003-3745-7541"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3745-7541","affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113325229"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64699229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"135","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5508000254631042,"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":0.5508000254631042,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.10119999945163727,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.10109999775886536,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6890000104904175},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6607000231742859},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.560699999332428},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.46140000224113464},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.40139999985694885},{"id":"https://openalex.org/keywords/sorting-algorithm","display_name":"Sorting algorithm","score":0.38179999589920044},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.3605000078678131},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.35260000824928284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573999762535095},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6890000104904175},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.667900025844574},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6607000231742859},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.560699999332428},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4683000147342682},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.40139999985694885},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.38179999589920044},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.35659998655319214},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C161824985","wikidata":"https://www.wikidata.org/wiki/Q919509","display_name":"Vector processor","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3754598.3754613","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3754598.3754613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1969705590","display_name":null,"funder_award_id":"2023YFA1011704","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6714216625","display_name":null,"funder_award_id":"2021YFB0300101","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1973918431","https://openalex.org/W1985263109","https://openalex.org/W2007259720","https://openalex.org/W2025890876","https://openalex.org/W2026326255","https://openalex.org/W2035080386","https://openalex.org/W2051291879","https://openalex.org/W2082238959","https://openalex.org/W2089437293","https://openalex.org/W2095249664","https://openalex.org/W2168931017","https://openalex.org/W2235832317","https://openalex.org/W2751658790","https://openalex.org/W2781869913","https://openalex.org/W2791012218","https://openalex.org/W2808128431","https://openalex.org/W2891325938","https://openalex.org/W2921704024","https://openalex.org/W2923126305","https://openalex.org/W2964337156","https://openalex.org/W2970435804","https://openalex.org/W3000305333","https://openalex.org/W3047050130","https://openalex.org/W3057502114","https://openalex.org/W3132695675","https://openalex.org/W3147109109","https://openalex.org/W3216606302","https://openalex.org/W4220912491","https://openalex.org/W4235295823","https://openalex.org/W4247712932","https://openalex.org/W4281390154","https://openalex.org/W4282961395","https://openalex.org/W4312947129","https://openalex.org/W4361019735","https://openalex.org/W4378227035","https://openalex.org/W4379644415","https://openalex.org/W4385555251","https://openalex.org/W4386570406","https://openalex.org/W4386709563","https://openalex.org/W4389265965","https://openalex.org/W4393186017","https://openalex.org/W4400411561","https://openalex.org/W4401408518","https://openalex.org/W4401408752","https://openalex.org/W4401408765"],"related_works":[],"abstract_inverted_index":{"The":[0],"Sparse":[1],"General":[2],"Matrix-Matrix":[3],"Multiplication":[4],"(SpGEMM)":[5],"is":[6],"widely":[7],"used":[8],"in":[9,77],"a":[10,31,44,60],"variety":[11],"of":[12,74,108,120],"applications.":[13],"However,":[14],"research":[15],"on":[16,36,48,113],"optimizing":[17],"SpGEMM":[18,35],"for":[19],"high-performance":[20],"digital":[21],"signal":[22],"processors":[23],"(DSPs)":[24],"has":[25],"been":[26],"limited.":[27],"We":[28,69],"present":[29],"VES,":[30],"method":[32,86],"to":[33],"accelerate":[34],"multi-core":[37],"DSPs,":[38],"using":[39],"the":[40,49,75],"FT-M7032":[41],"platform":[42],"as":[43],"case":[45],"study.":[46],"Based":[47],"ESC":[50],"algorithm,":[51],"VES":[52,97],"enhances":[53],"computational":[54],"efficiency":[55],"through":[56],"vectorized":[57,66,78,84],"expansion":[58],"operations,":[59],"double-buffering":[61],"strategy,":[62],"and":[63,80,103,111,123],"an":[64,71,82,106],"optimized":[65],"sorting":[67,79],"method.":[68],"provide":[70],"in-depth":[72],"analysis":[73],"bottlenecks":[76],"introduce":[81],"efficient":[83],"reduction":[85],"that":[87,96],"significantly":[88],"improves":[89],"instruction-level":[90],"pipeline":[91],"throughput.":[92],"Experimental":[93],"results":[94],"show":[95],"outperforms":[98],"existing":[99],"methods":[100],"HASH,":[101],"ESC,":[102],"SPA":[104],"by":[105],"average":[107],"1.12\u00d7,":[109],"1.90\u00d7,":[110],"22.34\u00d7":[112],"1,931":[114],"sparse":[115],"matrices,":[116],"with":[117],"maximum":[118],"speedups":[119],"8.69\u00d7,":[121],"65.9\u00d7,":[122],"821.6\u00d7,":[124],"respectively.":[125]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-21T00:00:00"}