{"id":"https://openalex.org/W4401408765","doi":"https://doi.org/10.1145/3673038.3673061","title":"Optimizing SpMV on Heterogeneous Multi-Core DSPs through Improved Locality and Vectorization","display_name":"Optimizing SpMV on Heterogeneous Multi-Core DSPs through Improved Locality and Vectorization","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4401408765","doi":"https://doi.org/10.1145/3673038.3673061"},"language":"en","primary_location":{"id":"doi:10.1145/3673038.3673061","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673061","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673061","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673061","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101323434","display_name":"Deshun Bi","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":"Deshun Bi","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087730416","display_name":"Shengguo Li","orcid":"https://orcid.org/0000-0001-7827-6304"},"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":"Shengguo Li","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006729432","display_name":"Dezun Dong","orcid":"https://orcid.org/0000-0001-6243-8479"},"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":"Dezun Dong","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092019932","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0001-8364-9793"},"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":"Peng Zhang","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083171604","display_name":"Jianbin Fang","orcid":"https://orcid.org/0000-0003-3542-4869"},"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":"Jianbin Fang","raw_affiliation_strings":["National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101323434"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.4449,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62312467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1145","last_page":"1155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9976999759674072,"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"}},{"id":"https://openalex.org/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9854999780654907,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9830999970436096,"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/locality","display_name":"Locality","score":0.8169888257980347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7833163142204285},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.7515726089477539},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.638877272605896},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4707888960838318}],"concepts":[{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.8169888257980347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833163142204285},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.7515726089477539},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.638877272605896},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4707888960838318},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3673038.3673061","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673061","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673061","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3673038.3673061","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673061","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673061","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401408765.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1588915715","https://openalex.org/W1987840949","https://openalex.org/W2035080386","https://openalex.org/W2051291879","https://openalex.org/W2101511474","https://openalex.org/W2891832717","https://openalex.org/W2921704024","https://openalex.org/W3009233884","https://openalex.org/W3147109109","https://openalex.org/W3213457265","https://openalex.org/W4242759096","https://openalex.org/W4309002766","https://openalex.org/W4321466355","https://openalex.org/W4385555251","https://openalex.org/W4388101094"],"related_works":["https://openalex.org/W2035419609","https://openalex.org/W343461076","https://openalex.org/W2601539487","https://openalex.org/W1993191611","https://openalex.org/W2023938924","https://openalex.org/W185650049","https://openalex.org/W2787898679","https://openalex.org/W2918840249","https://openalex.org/W1991859582","https://openalex.org/W2110053126"],"abstract_inverted_index":{"The":[0],"sparse":[1,85],"matrix-vector":[2],"multiplication":[3],"(SpMV)":[4],"is":[5],"widely":[6],"used":[7],"in":[8],"large-scale":[9],"scientific":[10],"computing":[11],"and":[12,55,106,123,133],"engineering.":[13],"However,":[14],"optimizing":[15],"SpMV":[16,34],"for":[17,71],"high-performance":[18],"digital":[19],"signal":[20],"processors":[21],"(DSPs)":[22],"has":[23],"received":[24],"limited":[25],"attention.":[26],"We":[27,98],"present":[28],"HaLAV,":[29],"a":[30,45],"method":[31],"to":[32,73,87],"accelerate":[33],"on":[35,75,102,130],"CPU-DSP":[36],"heterogeneous":[37],"platforms,":[38],"using":[39,93],"the":[40,50,62,76,79,84,91,94,103,127,131,134],"FT-M7032":[41,104,132],"DSP":[42],"platform":[43,105],"as":[44],"case":[46],"study.":[47],"HaLAV":[48,65],"partitions":[49],"input":[51],"matrix":[52],"into":[53],"\u2018dense\u2019":[54],"\u2018sparse\u2019":[56],"parts":[57],"through":[58],"column":[59],"reordering.":[60],"For":[61],"dense":[63],"part,":[64],"automatically":[66],"selects":[67],"storage":[68],"formats":[69],"optimized":[70],"vectorization":[72],"run":[74],"DSP.":[77],"At":[78],"same":[80],"time,":[81],"it":[82],"offloads":[83],"component":[86],"be":[88],"processed":[89],"by":[90],"CPU":[92],"standard":[95],"CSR":[96],"algorithm.":[97],"evaluate":[99],"our":[100,115],"approach":[101],"an":[107],"Intel":[108],"Xeon":[109,135],"CPU.":[110],"Experimental":[111],"results":[112],"show":[113],"that":[114],"techniques":[116],"achieve":[117],"average":[118],"speedups":[119],"of":[120],"2.09":[121],"\u00d7":[122,125],"1.66":[124],"over":[126],"competing":[128],"baselines":[129],"platform,":[136],"respectively.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
