{"id":"https://openalex.org/W3170642333","doi":"https://doi.org/10.1145/3447818.3460356","title":"Optimizing large-scale plasma simulations on persistent memory-based heterogeneous memory with effective data placement across memory hierarchy","display_name":"Optimizing large-scale plasma simulations on persistent memory-based heterogeneous memory with effective data placement across memory hierarchy","publication_year":2021,"publication_date":"2021-06-03","ids":{"openalex":"https://openalex.org/W3170642333","doi":"https://doi.org/10.1145/3447818.3460356","mag":"3170642333"},"language":"en","primary_location":{"id":"doi:10.1145/3447818.3460356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447818.3460356","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447818.3460356","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","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/10.1145/3447818.3460356","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056482728","display_name":"Jie Ren","orcid":"https://orcid.org/0000-0001-5541-433X"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Ren","raw_affiliation_strings":["University of California, Merced"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Merced","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062155158","display_name":"Jiaolin Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaolin Luo","raw_affiliation_strings":["University of California, Merced"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Merced","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037069204","display_name":"Ivy Peng","orcid":"https://orcid.org/0000-0003-4158-3583"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivy Peng","raw_affiliation_strings":["Lawrence Livermore National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062590263","display_name":"Kai Wu","orcid":"https://orcid.org/0000-0002-7913-8322"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Wu","raw_affiliation_strings":["University of California, Merced"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Merced","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100407387","display_name":"Dong Li","orcid":"https://orcid.org/0000-0001-9336-0694"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Li","raw_affiliation_strings":["University of California, Merced"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Merced","institution_ids":["https://openalex.org/I156087764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2154,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.79909782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"203","last_page":"214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":1.0,"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":0.9998000264167786,"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":0.996399998664856,"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":0.821583092212677},{"id":"https://openalex.org/keywords/instruction-prefetch","display_name":"Instruction prefetch","score":0.808295726776123},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.6814156770706177},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.6746039986610413},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5725486278533936},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5616661310195923},{"id":"https://openalex.org/keywords/dynamic-random-access-memory","display_name":"Dynamic random-access memory","score":0.5458011627197266},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.44661232829093933},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.40036237239837646},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3740202784538269},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25297418236732483},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.17450866103172302},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.10420402884483337}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821583092212677},{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.808295726776123},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.6814156770706177},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.6746039986610413},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5725486278533936},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5616661310195923},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.5458011627197266},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.44661232829093933},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.40036237239837646},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3740202784538269},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25297418236732483},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.17450866103172302},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.10420402884483337}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3447818.3460356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447818.3460356","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447818.3460356","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1830490","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1830490","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3447818.3460356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447818.3460356","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447818.3460356","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1308124067","display_name":"CCF:Small:Collaborative Research: Taowu: A Heterogeneous Processing-in-Memory for High Performance Scientific Applications","funder_award_id":"1718194","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2459876197","display_name":"CSR: Small: Collaborative Research: Exploring Portable Data Placement on Massively Parallel Platforms with Heterogeneous Memory Architectures","funder_award_id":"1617967","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4248083046","display_name":null,"funder_award_id":"No. DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5522089832","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"id":"https://openalex.org/G5816449448","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G765874931","display_name":null,"funder_award_id":"No. DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"id":"https://openalex.org/G7806955302","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7968365520","display_name":null,"funder_award_id":"CCF-1553645","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8374966015","display_name":null,"funder_award_id":"AC52-07NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8434336419","display_name":"CAREER: Application-centric, Reliable and Efficient High Performance Computing","funder_award_id":"1553645","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8917221840","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G991281326","display_name":null,"funder_award_id":"AC52-07NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"},{"id":"https://openalex.org/F4320338292","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3170642333.pdf","grobid_xml":"https://content.openalex.org/works/W3170642333.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1559947614","https://openalex.org/W1638716253","https://openalex.org/W2039311309","https://openalex.org/W2048211535","https://openalex.org/W2048338165","https://openalex.org/W2068710519","https://openalex.org/W2340522713","https://openalex.org/W2523003201","https://openalex.org/W2528171966","https://openalex.org/W2546716216","https://openalex.org/W2604595776","https://openalex.org/W2621795851","https://openalex.org/W2724362854","https://openalex.org/W2767918720","https://openalex.org/W2808435167","https://openalex.org/W2902981860","https://openalex.org/W2903504144","https://openalex.org/W2934584470","https://openalex.org/W2936570671","https://openalex.org/W2944412207","https://openalex.org/W2968671528","https://openalex.org/W2975438130","https://openalex.org/W2985559904","https://openalex.org/W2985656529","https://openalex.org/W2986766728","https://openalex.org/W3005534306","https://openalex.org/W3005712778","https://openalex.org/W3008885346","https://openalex.org/W3010830594","https://openalex.org/W3011389781","https://openalex.org/W3097202158","https://openalex.org/W3098393085","https://openalex.org/W3103616267","https://openalex.org/W3103902563","https://openalex.org/W3103991664","https://openalex.org/W3169244019","https://openalex.org/W3170905359","https://openalex.org/W6600062020","https://openalex.org/W6600680261"],"related_works":["https://openalex.org/W2127001124","https://openalex.org/W2518930778","https://openalex.org/W2979599569","https://openalex.org/W3007039213","https://openalex.org/W3094611732","https://openalex.org/W2944414554","https://openalex.org/W2559795407","https://openalex.org/W2000563648","https://openalex.org/W3009022466","https://openalex.org/W2036823405"],"abstract_inverted_index":{"Particle":[0],"simulations":[1,18,47],"of":[2,25,75,89,96,99,105,160],"plasma":[3,8,46,60],"are":[4],"important":[5],"for":[6,115,156],"understanding":[7],"dynamics":[9],"in":[10,132],"space":[11],"weather":[12],"and":[13,22,66,82,107,111,130,139,172,177,185],"fusion":[14],"devices.":[15],"However,":[16],"production":[17],"that":[19],"use":[20,56,88,159],"billions":[21],"even":[23],"trillions":[24],"computational":[26],"particles":[27],"require":[28],"high":[29],"memory":[30,40,80,90],"capacity.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"explore":[36],"the":[37,73,86,94,133,142,157,169],"latest":[38],"persistent":[39],"(PM)":[41],"hardware":[42],"to":[43,84,92,123,141,151,154],"enable":[44,124],"large-scale":[45],"at":[48],"unprecedented":[49],"scales":[50],"on":[51,77],"a":[52,103,120,178],"single":[53],"machine.":[54],"We":[55,71,101,118,145],"WarpX,":[57],"an":[58,148],"advanced":[59],"simulation":[61],"code":[62],"which":[63],"is":[64],"mission-critical":[65],"targets":[67],"future":[68],"exascale":[69],"systems.":[70],"analyze":[72],"performance":[74,98,116,121,166],"WarpX":[76],"PM-based":[78],"heterogeneous":[79],"systems":[81],"propose":[83],"make":[85],"best":[87,158],"hierarchy":[91],"avoid":[93],"impact":[95],"inferior":[97],"PM.":[100],"introduce":[102],"combination":[104],"static":[106],"dynamic":[108],"data":[109,126],"placement,":[110],"processor-cache":[112],"prefetch":[113,155],"mechanism":[114],"optimization.":[117],"develop":[119],"model":[122,150],"efficient":[125],"migration":[127],"between":[128],"PM":[129],"DRAM":[131],"background,":[134],"without":[135],"reducing":[136],"available":[137],"bandwidth":[138],"parallelism":[140],"application":[143],"threads.":[144],"also":[146],"build":[147],"analytical":[149],"decide":[152],"when":[153],"caches.":[161],"Our":[162],"design":[163],"achieves":[164],"66.4%":[165],"improvement":[167],"over":[168],"PM-only":[170],"baseline":[171],"outperforms":[173],"DRAM-cached,":[174],"NUMA":[175],"first-touch,":[176],"state-of-the-art":[179],"software":[180],"solution":[181],"by":[182],"38.8%,":[183],"45.1%":[184],"83.3%,":[186],"respectively.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}