{"id":"https://openalex.org/W4291908388","doi":"https://doi.org/10.1109/icccs55155.2022.9846280","title":"Highly Portable C++ Based Simulator with Dual Parallelism and Spatial Decomposition of Simulation Domain using Floating Point Operations and More Flops Per Watt for Better Time-To-Solution on Particle Simulation","display_name":"Highly Portable C++ Based Simulator with Dual Parallelism and Spatial Decomposition of Simulation Domain using Floating Point Operations and More Flops Per Watt for Better Time-To-Solution on Particle Simulation","publication_year":2022,"publication_date":"2022-04-22","ids":{"openalex":"https://openalex.org/W4291908388","doi":"https://doi.org/10.1109/icccs55155.2022.9846280"},"language":"en","primary_location":{"id":"doi:10.1109/icccs55155.2022.9846280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccs55155.2022.9846280","pdf_url":null,"source":{"id":"https://openalex.org/S4363608130","display_name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","raw_type":"proceedings-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/A5053522029","display_name":"Nisha Agrawal","orcid":"https://orcid.org/0009-0008-5908-9608"},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Nisha Agrawal","raw_affiliation_strings":["High-Performance Computing- Infrastructure and Ecosystem Centre for Development of Advanced Computing,Pune,India","High-Performance Computing- Infrastructure and Ecosystem Centre for Development of Advanced Computing, Pune, India"],"affiliations":[{"raw_affiliation_string":"High-Performance Computing- Infrastructure and Ecosystem Centre for Development of Advanced Computing,Pune,India","institution_ids":["https://openalex.org/I1331500379"]},{"raw_affiliation_string":"High-Performance Computing- Infrastructure and Ecosystem Centre for Development of Advanced Computing, Pune, India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006172745","display_name":"Abhishek Das","orcid":"https://orcid.org/0000-0002-2362-0195"},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhishek Das","raw_affiliation_strings":["High-Performance Computing- Technologies Centre for Development of Advanced Computing,Pune,India","High-Performance Computing- Technologies Centre for Development of Advanced Computing, Pune, India"],"affiliations":[{"raw_affiliation_string":"High-Performance Computing- Technologies Centre for Development of Advanced Computing,Pune,India","institution_ids":["https://openalex.org/I1331500379"]},{"raw_affiliation_string":"High-Performance Computing- Technologies Centre for Development of Advanced Computing, Pune, India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005251671","display_name":"Rishi Pathak","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rishi Pathak","raw_affiliation_strings":["High-Performance Computing- Infrastructure and Ecosystem Centre for Development of Advanced Computing,Pune,India","High-Performance Computing- Infrastructure and Ecosystem Centre for Development of Advanced Computing, Pune, India"],"affiliations":[{"raw_affiliation_string":"High-Performance Computing- Infrastructure and Ecosystem Centre for Development of Advanced Computing,Pune,India","institution_ids":["https://openalex.org/I1331500379"]},{"raw_affiliation_string":"High-Performance Computing- Infrastructure and Ecosystem Centre for Development of Advanced Computing, Pune, India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090492507","display_name":"Manish Modani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manish Modani","raw_affiliation_strings":["NVIDIA,Pune,India","NVIDIA, Pune, India"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Pune,India","institution_ids":[]},{"raw_affiliation_string":"NVIDIA, Pune, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053522029"],"corresponding_institution_ids":["https://openalex.org/I1331500379"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12060507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"130","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11367","display_name":"Particle accelerators and beam dynamics","score":0.9710999727249146,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11367","display_name":"Particle accelerators and beam dynamics","score":0.9710999727249146,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11005","display_name":"Radiation Effects in Electronics","score":0.9642000198364258,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9610000252723694,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.9047266840934753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6401836276054382},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.5294380187988281},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.5088663101196289},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47402292490005493},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4546424150466919},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4522193372249603},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4480929970741272},{"id":"https://openalex.org/keywords/watt","display_name":"Watt","score":0.4218655824661255},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4188958406448364},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32615530490875244},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.1918332576751709},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10643577575683594},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10006994009017944}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.9047266840934753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6401836276054382},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.5294380187988281},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.5088663101196289},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47402292490005493},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4546424150466919},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4522193372249603},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4480929970741272},{"id":"https://openalex.org/C44012409","wikidata":"https://www.wikidata.org/wiki/Q25236","display_name":"Watt","level":3,"score":0.4218655824661255},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4188958406448364},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32615530490875244},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.1918332576751709},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10643577575683594},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10006994009017944},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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:10.1109/icccs55155.2022.9846280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccs55155.2022.9846280","pdf_url":null,"source":{"id":"https://openalex.org/S4363608130","display_name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2019465613","https://openalex.org/W2866010014","https://openalex.org/W2921098500","https://openalex.org/W3149292517","https://openalex.org/W3201073812"],"related_works":["https://openalex.org/W2907336738","https://openalex.org/W4240959870","https://openalex.org/W2062374963","https://openalex.org/W2498907530","https://openalex.org/W2511748399","https://openalex.org/W1986359287","https://openalex.org/W2560894929","https://openalex.org/W1861262881","https://openalex.org/W2156524298","https://openalex.org/W2106942255"],"abstract_inverted_index":{"LAMMPS":[0,20,38,102,127,140,209,230,247,266],"is":[1,46,121,132,142,199,252],"a":[2,14],"classical":[3],"molecular":[4],"dynamics":[5],"(MD)":[6],"code":[7],"that":[8],"models":[9],"ensembles":[10],"of":[11,34,51,125,162,169,195],"particles":[12],"in":[13,71,217],"solid,":[15],"liquid,":[16],"or":[17],"gaseous":[18],"state.":[19],"performance":[21,45,103,131,141,211,222,267],"has":[22],"been":[23],"optimized":[24],"over":[25,129,280],"the":[26,32,40,49,52,136,185,204,249],"years.":[27],"This":[28],"paper":[29],"focuses":[30],"on":[31,39,59,117,256,277],"study":[33],"MD":[35],"simulations":[36],"using":[37],"PARAM":[41,118],"Siddhi-AI":[42,119],"system.":[43],"LAMMPS&#x2019;s":[44],"analyzed":[47,143],"with":[48],"number":[50],"latest":[53],"NVIDIA":[54],"A100":[55,278],"co-processor":[56],"(GPU)":[57],"based":[58],"Ampere":[60,72],"architecture.":[61],"The":[62],"faster":[63],"and":[64,68,113,164,172,177,182,189,197,214,225,235,254,261],"larger":[65],"L1":[66],"cache":[67],"shared":[69],"memory":[70],"architecture":[73],"(192":[74],"KB":[75],"per":[76],"Streaming":[77],"Multiprocessor":[78],"(SM))":[79],"delivers":[80],"additional":[81],"speedups":[82],"for":[83,104,134,144,202,223,259],"High-Performance":[84],"Computing":[85],"(HPC)":[86],"workloads.":[87],"In":[88,240],"this":[89],"work,":[90],"single-node":[91,210,220],"multi-GPUs":[92,97],"as":[93,95],"well":[94,232],"multi-node":[96,234],"(up":[98],"to":[99,219,242,274],"5":[100,257],"nodes)":[101],"two":[105],"input":[106,205,227,263],"datasets":[107,228,264],"LJ":[108],"2.5":[109],"(intermolecular":[110],"pair":[111],"potential)":[112],"EAM":[114,226,262],"(interatomic":[115],"potential),":[116],"system,":[120],"discussed.":[122],"Performance":[123],"improvement":[124],"GPU-enabled":[126],"run":[128],"CPU-only":[130,221],"demonstrated":[133],"both":[135,203],"inputs":[137],"data":[138],"sets.":[139],"initialization,":[145],"atoms":[146,163],"communication,":[147],"forces,":[148],"thermodynamic":[149,170],"state":[150],"(Pair":[151],"(non-bonded":[152],"force":[153],"computations),":[154],"Neigh":[155],"(neighbor":[156],"list":[157],"construction),":[158],"Comm":[159],"(inter-processor":[160],"communication":[161],"their":[165],"properties),":[166],"Output":[167],"(output":[168],"info":[171],"dump":[173],"files),":[174],"Modify":[175],"(fixes":[176],"computes":[178],"invoked":[179],"by":[180],"fixes)":[181],"others":[183],"(all":[184],"remaining":[186],"time":[187],"forces":[188],"functions)).":[190],"GPU":[191,207,245,270],"utilization":[192],"(in":[193],"terms":[194],"computing":[196],"memory)":[198],"also":[200],"discussed":[201],"datasets.":[206],"enabled":[208,246],"shows":[212,236,272],"31x":[213],"125x":[215],"speed-up":[216],"comparison":[218,241,268],"LJ2.5":[224,260],"respectively.":[229,265],"scales":[231],"across":[233,269],"almost":[237],"linear":[238],"scalability.":[239],"single":[243],"node":[244],"run,":[248],"observed":[250],"speedup":[251,276],"4.1x":[253],"3.8x":[255],"nodes,":[258],"generation":[271],"1.5x":[273],"1.9x":[275],"GPUs":[279],"V100":[281],"GPUs.":[282]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
