{"id":"https://openalex.org/W4401408861","doi":"https://doi.org/10.1145/3673038.3673101","title":"Detailed Analysis and Optimization of Irregular-Shaped Matrix Multiplication on Multi-Core DSPs","display_name":"Detailed Analysis and Optimization of Irregular-Shaped Matrix Multiplication on Multi-Core DSPs","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4401408861","doi":"https://doi.org/10.1145/3673038.3673101"},"language":"en","primary_location":{"id":"doi:10.1145/3673038.3673101","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673101","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673101","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/10.1145/3673038.3673101","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106355572","display_name":"Haotian Mo","orcid":"https://orcid.org/0009-0008-9807-4062"},"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":"Haotian Mo","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101913669","display_name":"Qinglin Wang","orcid":"https://orcid.org/0000-0002-8286-6566"},"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, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111673360","display_name":"Linyu Liao","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":"Linyu Liao","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089323508","display_name":"Biao Li","orcid":"https://orcid.org/0000-0001-5007-9421"},"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":"Biao Li","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023113072","display_name":"Lihua Chi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lihua Chi","raw_affiliation_strings":["Hunan GuoKe Computility Technology Co., Ltd, China"],"affiliations":[{"raw_affiliation_string":"Hunan GuoKe Computility Technology Co., Ltd, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454211","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, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5106355572"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":1.047,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77921014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1176","last_page":"1186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9980999827384949,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9968000054359436,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9807000160217285,"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":0.6335759162902832},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5777687430381775},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5420587062835693},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5042809247970581},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4635756313800812},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.41923248767852783},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21804076433181763},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11299508810043335},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10132789611816406},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07751038670539856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6335759162902832},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5777687430381775},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5420587062835693},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5042809247970581},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4635756313800812},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.41923248767852783},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21804076433181763},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11299508810043335},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10132789611816406},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07751038670539856},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3673038.3673101","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673101","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673101","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:10.1145/3673038.3673101","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673101","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673101","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401408861.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2065321717","https://openalex.org/W2084379367","https://openalex.org/W2485331474","https://openalex.org/W2924040443","https://openalex.org/W2951894856","https://openalex.org/W2973166032","https://openalex.org/W2978452617","https://openalex.org/W3044796228","https://openalex.org/W3091995851","https://openalex.org/W3112453875","https://openalex.org/W3147109109","https://openalex.org/W3182339906","https://openalex.org/W3210601829","https://openalex.org/W4242759096","https://openalex.org/W4313245068"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W1925544630","https://openalex.org/W2596457687","https://openalex.org/W3212757063"],"abstract_inverted_index":{"Irregular-shaped":[0],"General":[1],"Matrix":[2],"Multiplication":[3],"(GEMM)":[4],"is":[5],"extensively":[6],"used":[7],"in":[8,37,60,70,124,141],"diverse":[9],"workloads,":[10],"such":[11],"as":[12,32],"scientific":[13],"simulation":[14],"and":[15,53,63,111,120,143],"deep":[16],"learning.":[17],"In":[18],"response":[19],"to":[20,58,155],"energy":[21],"efficiency":[22],"constraints,":[23],"low-power":[24],"multi-core":[25,68,84],"digital":[26],"signal":[27],"processors":[28],"(DSPs)":[29],"have":[30],"emerged":[31],"a":[33,72,82,93,102],"viable":[34],"alternative":[35],"architecture":[36],"HPC":[38],"systems.":[39],"This":[40],"study":[41],"examines":[42],"the":[43,121,131,137,144],"performance":[44,139],"of":[45,147],"existing":[46],"GEMM":[47],"implementations":[48,151],"working":[49],"on":[50],"irregular-shaped":[51,88,125],"matrices":[52],"observes":[54],"sub-optimal":[55],"outcomes":[56],"due":[57],"deficiencies":[59],"memory":[61,118],"optimization":[62,135],"core-level":[64,100,122],"parallelism":[65,123],"extraction.":[66],"For":[67],"DSPs":[69],"FT-M7032,":[71],"CPU-DSP":[73],"heterogeneous":[74],"processor":[75],"for":[76,87],"HPC,":[77],"we":[78],"introduce":[79],"dspIMM":[80,91,148],"-":[81],"new":[83,94],"parallel":[85],"implementation":[86,105],"matrix":[89],"multiplications.":[90],"incorporates":[92],"loop":[95],"ordering,":[96],"stack-space":[97],"optimization,":[98],"multi-dimensional":[99],"parallelization,":[101],"communication-computation":[103,133],"overlap":[104,134],"with":[106],"data":[107],"prefetch":[108],"across":[109],"loops,":[110],"blocking":[112],"optimization.":[113],"These":[114],"optimizations":[115],"effectively":[116],"enhance":[117],"access":[119],"GEMMs.":[126],"Experimental":[127],"results":[128],"demonstrate":[129],"that":[130],"proposed":[132],"achieves":[136,153],"highest":[138],"improvement":[140],"dspIMM,":[142],"average":[145],"speedup":[146],"over":[149],"previous":[150],"finally":[152],"up":[154],"3.34":[156],"times.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}