{"id":"https://openalex.org/W7119496909","doi":"https://doi.org/10.1145/3773656.3773664","title":"High-performance in-situ ML Inference with dalotia: A Lightweight Tensor Loader API for Science Codes","display_name":"High-performance in-situ ML Inference with dalotia: A Lightweight Tensor Loader API for Science Codes","publication_year":2026,"publication_date":"2026-01-09","ids":{"openalex":"https://openalex.org/W7119496909","doi":"https://doi.org/10.1145/3773656.3773664"},"language":null,"primary_location":{"id":"doi:10.1145/3773656.3773664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773656.3773664","pdf_url":null,"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 Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773656.3773664","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079210568","display_name":"Theresa Pollinger","orcid":"https://orcid.org/0000-0002-0186-4340"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Theresa Pollinger","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0186-4340","affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039069961","display_name":"Jens Domke","orcid":"https://orcid.org/0000-0002-5343-414X"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jens Domke","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5343-414X","affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079210568"],"corresponding_institution_ids":["https://openalex.org/I4210129730"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05787462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"384","last_page":"395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.2320999950170517,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.2320999950170517,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.1800999939441681,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.07919999957084656,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6782000064849854},{"id":"https://openalex.org/keywords/interfacing","display_name":"Interfacing","score":0.626800000667572},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5024999976158142},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49959999322891235},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.49480000138282776},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.48330000042915344},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4702000021934509},{"id":"https://openalex.org/keywords/loader","display_name":"Loader","score":0.41190001368522644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897999882698059},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6782000064849854},{"id":"https://openalex.org/C2776303644","wikidata":"https://www.wikidata.org/wiki/Q1020499","display_name":"Interfacing","level":2,"score":0.626800000667572},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49959999322891235},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.49480000138282776},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.48330000042915344},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.45559999346733093},{"id":"https://openalex.org/C2779041774","wikidata":"https://www.wikidata.org/wiki/Q650550","display_name":"Loader","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4059000015258789},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3781000077724457},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3249000012874603},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C131675550","wikidata":"https://www.wikidata.org/wiki/Q7646884","display_name":"Surrogate model","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773656.3773664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773656.3773664","pdf_url":null,"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 Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3773656.3773664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773656.3773664","pdf_url":null,"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 Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2033787161","https://openalex.org/W2064872546","https://openalex.org/W2077520285","https://openalex.org/W2910096450","https://openalex.org/W2974527409","https://openalex.org/W2980247813","https://openalex.org/W2986124642","https://openalex.org/W2998366519","https://openalex.org/W3037865181","https://openalex.org/W3042343931","https://openalex.org/W3116855372","https://openalex.org/W3125013357","https://openalex.org/W3131137184","https://openalex.org/W3134626437","https://openalex.org/W3135440110","https://openalex.org/W3159637363","https://openalex.org/W3175644086","https://openalex.org/W4205353677","https://openalex.org/W4253423191","https://openalex.org/W4280589740","https://openalex.org/W4289827711","https://openalex.org/W4312120162","https://openalex.org/W4319763984","https://openalex.org/W4378802379","https://openalex.org/W4386504217","https://openalex.org/W4386896826","https://openalex.org/W4388031352","https://openalex.org/W4400244548","https://openalex.org/W4400880443","https://openalex.org/W4400899054","https://openalex.org/W4401408763","https://openalex.org/W4402631365","https://openalex.org/W4402827736","https://openalex.org/W4405390006","https://openalex.org/W4408085550","https://openalex.org/W4408278608","https://openalex.org/W4409591484"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,8,20,42,101,150,164,168,188],"increasing":[2,45],"capabilities":[3],"of":[4,10,23,44,68,143,158],"machine-learning":[5],"(ML)":[6],"systems,":[7],"domains":[9],"simulation":[11,69],"and":[12,38,47,58,70,111,129,194],"ML":[13,39,84,107,117,192],"are":[14],"growing":[15],"closer":[16],"together.":[17],"In":[18,41],"particular,":[19],"evolving":[21],"field":[22],"ML-based":[24],"surrogate":[25,118],"modeling":[26],"within":[27],"turbulence":[28],"simulations":[29],"often":[30],"relies":[31],"on":[32,167,183],"explicit":[33],"interfacing":[34],"between":[35,123],"scientific":[36],"codes":[37],"frameworks.":[40],"face":[43],"hardware":[46],"software":[48],"complexity,":[49],"it":[50,174],"is":[51],"important":[52],"to":[53,59,82,160,163,181],"critically":[54],"assess":[55],"this":[56],"approach":[57,103],"explore":[60],"alternatives":[61],"that":[62,79,135],"allow":[63],"for":[64,190],"a":[65,74,141],"tighter":[66],"integration":[67],"ML.":[71],"We":[72,153],"develop":[73],"tensor":[75],"loading":[76],"library,":[77],"dalotia,":[78,98],"allows":[80],"researchers":[81],"embed":[83],"inference":[85,105],"directly":[86],"into":[87],"their":[88,195],"HPC":[89],"code":[90],"(\u201cin-situ\u201d)":[91],"using":[92,115,149],"C,":[93],"C++,":[94],"or":[95],"Fortran.":[96],"Using":[97],"we":[99],"evaluate":[100],"in-situ":[102,151,156,185],"against":[104],"with":[106],"frameworks":[108,193],"(PyTorch,":[109],"libTorch,":[110],"oneDNN).":[112],"Our":[113],"experiments":[114],"state-of-the-art":[116],"architectures":[119],"present":[120],"complex":[121],"tradeoffs":[122],"convenience,":[124],"performance,":[125],"memory":[126,146],"usage,":[127],"energy,":[128],"dependency":[130],"complexity.":[131],"The":[132],"data":[133],"shows":[134],"small-batch":[136],"neural":[137],"networks":[138],"can":[139,175],"save":[140],"factor":[142],"5x":[144],"in":[145,178],"overheads":[147],"when":[148],"approach.":[152],"further":[154],"observe":[155],"speedups":[157],"up":[159],"8x":[161],"compared":[162],"libTorch":[165],"implementation":[166],"node":[169],"scale":[170],"(48":[171],"cores).":[172],"Thus":[173],"be":[176],"beneficial,":[177],"many":[179],"regards,":[180],"rely":[182],"native":[184],"implementations,":[186],"without":[187],"need":[189],"bloated":[191],"dependencies.":[196]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-09T00:00:00"}