{"id":"https://openalex.org/W4408792485","doi":"https://doi.org/10.1109/tcad.2025.3554144","title":"PTPS: Precision-Aware Task Partitioning and Scheduling for SpMV on CPU-FPGA Heterogeneous Platforms","display_name":"PTPS: Precision-Aware Task Partitioning and Scheduling for SpMV on CPU-FPGA Heterogeneous Platforms","publication_year":2025,"publication_date":"2025-03-24","ids":{"openalex":"https://openalex.org/W4408792485","doi":"https://doi.org/10.1109/tcad.2025.3554144"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2025.3554144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2025.3554144","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-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/A5048951405","display_name":"Jianhua Gao","orcid":"https://orcid.org/0000-0002-3828-0015"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Gao","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3828-0015","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016734581","display_name":"Zhou Zhi","orcid":"https://orcid.org/0000-0002-2181-9053"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zhou","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingze Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingze Huang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347399","display_name":"Juan Wang","orcid":"https://orcid.org/0000-0001-6017-6313"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juan Wang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100672331","display_name":"Yizhuo Wang","orcid":"https://orcid.org/0000-0002-1288-331X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhuo Wang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1288-331X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046211358","display_name":"Weixing Ji","orcid":"https://orcid.org/0000-0002-3250-0435"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixing Ji","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3250-0435","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8777,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85203565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"44","issue":"10","first_page":"3804","last_page":"3815"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9469000101089478,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9469000101089478,"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":0.7483837008476257},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6560008525848389},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6336294412612915},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5491847395896912},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4970255196094513},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4834226369857788},{"id":"https://openalex.org/keywords/cpu-shielding","display_name":"CPU shielding","score":0.42175859212875366},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.3656630516052246},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36382898688316345},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3137211203575134},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.061465561389923096},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05751869082450867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483837008476257},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6560008525848389},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6336294412612915},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5491847395896912},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4970255196094513},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4834226369857788},{"id":"https://openalex.org/C180613757","wikidata":"https://www.wikidata.org/wiki/Q5013757","display_name":"CPU shielding","level":3,"score":0.42175859212875366},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.3656630516052246},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36382898688316345},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3137211203575134},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.061465561389923096},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05751869082450867},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2025.3554144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2025.3554144","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1219308057","display_name":null,"funder_award_id":"2024M750223","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G4880384617","display_name":null,"funder_award_id":"GZC20230261","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1994515555","https://openalex.org/W2035080386","https://openalex.org/W2117752372","https://openalex.org/W2137994790","https://openalex.org/W2159937165","https://openalex.org/W2300072829","https://openalex.org/W2941763154","https://openalex.org/W2973152414","https://openalex.org/W2996522450","https://openalex.org/W3011253470","https://openalex.org/W4200197440","https://openalex.org/W4200467342","https://openalex.org/W4211147898","https://openalex.org/W4293024216","https://openalex.org/W4312068769","https://openalex.org/W4313447739","https://openalex.org/W4378804762","https://openalex.org/W4383749374","https://openalex.org/W4388214709","https://openalex.org/W4388661983","https://openalex.org/W4392639618","https://openalex.org/W4392648590","https://openalex.org/W4393576971","https://openalex.org/W4400422163","https://openalex.org/W4405421540"],"related_works":["https://openalex.org/W2387982802","https://openalex.org/W1896942098","https://openalex.org/W1991061790","https://openalex.org/W2088078730","https://openalex.org/W2400763249","https://openalex.org/W1482063109","https://openalex.org/W2043940072","https://openalex.org/W2249399447","https://openalex.org/W2745443495","https://openalex.org/W2904030423"],"abstract_inverted_index":{"The":[0,97],"CPU-FPGA":[1,92],"heterogeneous":[2,93],"computing":[3],"architecture":[4,64],"is":[5,95,102],"extensively":[6],"employed":[7],"in":[8],"the":[9,46,91,116,122,128,148,156,172,184],"embedded":[10],"domain":[11],"due":[12],"to":[13],"its":[14],"low":[15],"cost":[16],"and":[17,42,57,74,85,118,132,175],"power":[18],"efficiency,":[19],"with":[20],"numerous":[21],"sparse":[22,106],"matrix-vector":[23],"multiplication":[24],"(SpMV)":[25],"acceleration":[26],"efforts":[27],"already":[28],"targeting":[29],"this":[30],"architecture.":[31],"However,":[32],"existing":[33],"work":[34],"rarely":[35],"includes":[36],"collaborative":[37,135],"SpMV":[38,69,82,113,136],"computations":[39,114,120,137],"between":[40,144],"CPU":[41,131],"FPGA,":[43],"which":[44],"limits":[45],"exploration":[47],"of":[48,100,105,130,163],"hybrid":[49],"architectures":[50],"that":[51,66,155],"could":[52],"potentially":[53],"offer":[54],"enhanced":[55],"performance":[56],"flexibility.":[58],"This":[59],"article":[60],"introduces":[61],"an":[62,160],"FPGA":[63,117,133],"design":[65],"supports":[67],"multiprecision":[68],"computations,":[70],"including":[71],"FP16,":[72],"FP32,":[73],"FP64.":[75],"Building":[76],"on":[77,115,121],"this,":[78],"PTPS,":[79],"a":[80],"precision-aware":[81],"task":[83],"partitioning":[84,104],"dynamic":[86],"scheduling":[87],"algorithm":[88],"tailored":[89],"for":[90,134],"architecture,":[94],"proposed.":[96],"core":[98],"idea":[99],"PTPS":[101,124],"lossless":[103],"matrices":[107],"across":[108],"multiple":[109],"precisions,":[110],"prioritizing":[111],"low-precision":[112],"high-precision":[119],"CPU.":[123],"not":[125],"only":[126],"leverages":[127],"strengths":[129],"but":[138],"also":[139],"reduces":[140],"data":[141],"transmission":[142],"overhead":[143],"them,":[145],"thereby":[146],"improving":[147],"overall":[149],"computational":[150],"efficiency.":[151],"Experimental":[152],"evaluation":[153],"demonstrates":[154],"proposed":[157],"approach":[158,174],"offers":[159],"average":[161],"speedup":[162],"<inline-formula":[164,176],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[165,177],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[166,178],"<tex-math":[167,179],"notation=\"LaTeX\">$1.57\\times":[168],"$":[169,181],"</tex-math></inline-formula>":[170,182],"over":[171,183],"CPU-only":[173],"notation=\"LaTeX\">$2.58\\times":[180],"FPGA-only":[185],"approach.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
