{"id":"https://openalex.org/W4313447739","doi":"https://doi.org/10.1145/3543622.3573182","title":"Callipepla: Stream Centric Instruction Set and Mixed Precision for Accelerating Conjugate Gradient Solver","display_name":"Callipepla: Stream Centric Instruction Set and Mixed Precision for Accelerating Conjugate Gradient Solver","publication_year":2023,"publication_date":"2023-02-10","ids":{"openalex":"https://openalex.org/W4313447739","doi":"https://doi.org/10.1145/3543622.3573182"},"language":"en","primary_location":{"id":"doi:10.1145/3543622.3573182","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543622.3573182","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543622.3573182","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3543622.3573182","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036239104","display_name":"Linghao Song","orcid":"https://orcid.org/0000-0002-7450-2842"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Linghao Song","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7450-2842","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032647120","display_name":"Licheng Guo","orcid":"https://orcid.org/0000-0002-0705-9510"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Licheng Guo","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0705-9510","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065485432","display_name":"Suhail Basalama","orcid":"https://orcid.org/0000-0002-8301-8411"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suhail Basalama","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8301-8411","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074835029","display_name":"Yuze Chi","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuze Chi","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5885-0425","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025422213","display_name":"Robert F. Lucas","orcid":"https://orcid.org/0000-0003-1303-2012"},"institutions":[{"id":"https://openalex.org/I21160419","display_name":"Ansys (United States)","ror":"https://ror.org/05cf5b117","country_code":"US","type":"company","lineage":["https://openalex.org/I21160419"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert F. Lucas","raw_affiliation_strings":["Livermore Software Technology, an ANSYS Company, Livermore, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1303-2012","affiliations":[{"raw_affiliation_string":"Livermore Software Technology, an ANSYS Company, Livermore, CA, USA","institution_ids":["https://openalex.org/I21160419"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016776689","display_name":"Jason Cong","orcid":"https://orcid.org/0000-0003-2887-6963"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Cong","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2887-6963","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036239104"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":3.5909,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9323377,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"247","last_page":"258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9934999942779541,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9847000241279602,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.7887840270996094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7223820686340332},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6860424876213074},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6157956719398499},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5328387022018433},{"id":"https://openalex.org/keywords/conjugate","display_name":"Conjugate","score":0.4966903328895569},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4217239320278168},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.41784530878067017},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3897785544395447},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18730798363685608},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12265932559967041}],"concepts":[{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.7887840270996094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7223820686340332},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6860424876213074},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6157956719398499},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5328387022018433},{"id":"https://openalex.org/C197336794","wikidata":"https://www.wikidata.org/wiki/Q5161150","display_name":"Conjugate","level":2,"score":0.4966903328895569},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4217239320278168},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.41784530878067017},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3897785544395447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18730798363685608},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12265932559967041},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543622.3573182","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543622.3573182","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543622.3573182","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3543622.3573182","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543622.3573182","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543622.3573182","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1186799911","display_name":null,"funder_award_id":"CCF-1937599","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313447739.pdf","grobid_xml":"https://content.openalex.org/works/W4313447739.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1551480811","https://openalex.org/W1965512225","https://openalex.org/W1969468690","https://openalex.org/W2035080386","https://openalex.org/W2045285941","https://openalex.org/W2088899870","https://openalex.org/W2094756095","https://openalex.org/W2136897996","https://openalex.org/W2316564661","https://openalex.org/W2478429860","https://openalex.org/W2500846120","https://openalex.org/W2585560244","https://openalex.org/W2897997157","https://openalex.org/W2899644485","https://openalex.org/W2899691047","https://openalex.org/W3000310304","https://openalex.org/W3008230609","https://openalex.org/W3008730548","https://openalex.org/W3016769527","https://openalex.org/W3092394454","https://openalex.org/W3106125969","https://openalex.org/W3130920634","https://openalex.org/W3136950882","https://openalex.org/W3198975860","https://openalex.org/W4281657881","https://openalex.org/W4283270874","https://openalex.org/W4285049632","https://openalex.org/W4293024216","https://openalex.org/W4297978922","https://openalex.org/W4308083582","https://openalex.org/W6610860872"],"related_works":["https://openalex.org/W1503783781","https://openalex.org/W1604758548","https://openalex.org/W2804126825","https://openalex.org/W1549048322","https://openalex.org/W4367553810","https://openalex.org/W2104142636","https://openalex.org/W2731831065","https://openalex.org/W4283162424","https://openalex.org/W2271439649","https://openalex.org/W2011940952"],"abstract_inverted_index":{"The":[0,262],"continued":[1],"growth":[2],"in":[3,195],"the":[4,18,29,72,100,164,171,176,202,216,220,245],"processing":[5,70,82,113],"power":[6],"of":[7,32,55,166,178,226,248,254],"FPGAs":[8],"coupled":[9],"with":[10,140,257],"high":[11],"bandwidth":[12,91,154,247],"memories":[13],"(HBM),":[14],"makes":[15],"systems":[16],"like":[17],"Xilinx":[19,206,217],"U280":[20,207],"credible":[21],"platforms":[22],"for":[23,45,110,180,197],"linear":[24,50],"solvers":[25],"which":[26,242],"often":[27],"dominate":[28],"run":[30],"time":[31],"scientific":[33],"and":[34,67,84,92,114,121,133,146,191,231],"engineering":[35],"applications.":[36],"In":[37],"this":[38,169],"paper,":[39],"we":[40,103,250],"present":[41,104],"Callipepla,":[42,249],"an":[43,64,238],"accelerator":[44,203],"a":[46,106,141,148,205,224],"preconditioned":[47],"conjugate":[48],"gradient":[49],"solver":[51],"(CG).":[52],"FPGA":[53,198],"acceleration":[54,69],"CG":[56],"faces":[57],"three":[58,101],"challenges:":[59],"(1)":[60,105],"how":[61,75,86],"to":[62,76,87,126,152,174,186,215,237],"support":[63],"arbitrary":[65],"problem":[66],"terminate":[68],"on":[71,204],"fly,":[73],"(2)":[74,116],"coordinate":[77,127],"long-vector":[78],"data":[79,129,181],"flow":[80,124,130],"among":[81,131],"modules,":[83],"(3)":[85,147],"save":[88,153],"off-chip":[89,136,189],"memory":[90,137,143,246],"maintain":[93],"double":[94,142,159],"(FP64)":[95],"precision":[96,150,160],"accuracy.":[97],"To":[98,163],"tackle":[99],"challenges,":[102],"stream-centric":[107],"instruction":[108],"set":[109],"efficient":[111],"streaming":[112,118],"control,":[115],"vector":[117,123,128],"reuse":[119],"(VSR)":[120],"decentralized":[122],"scheduling":[125],"modules":[132,185,193],"further":[134],"reduce":[135,187],"access":[138],"latency":[139],"channel":[144],"design,":[145],"mixed":[149],"scheme":[151],"yet":[155],"still":[156,251],"achieve":[157,252],"effective":[158],"quality":[161],"solutions.":[162],"best":[165],"our":[167],"knowledge,":[168],"is":[170,264],"first":[172],"work":[173],"introduce":[175],"concept":[177],"VSR":[179],"reusing":[182],"between":[183],"on-chip":[184],"unnecessary":[188],"accesses":[190],"enable":[192],"working":[194],"parallel":[196],"accelerators.":[199],"We":[200],"prototype":[201],"HBM":[208],"FPGA.":[209],"Our":[210],"evaluation":[211],"shows":[212],"that":[213],"compared":[214],"HPC":[218],"product,":[219],"XcgSolver,":[221],"Callipepla":[222],"achieves":[223],"speedup":[225],"3.94x,":[227],"3.36x":[228],"higher":[229,259],"throughput,":[230],"2.94x":[232],"better":[233],"energy":[234,260],"efficiency.":[235,261],"Compared":[236],"NVIDIA":[239],"A100":[240],"GPU":[241],"has":[243],"4x":[244],"77%":[253],"its":[255],"throughput":[256],"3.34x":[258],"code":[263],"available":[265],"at":[266],"https://github.com/UCLA-VAST/Callipepla.":[267]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-01-06T00:00:00"}