{"id":"https://openalex.org/W7214058484","doi":"https://doi.org/10.48550/arxiv.2609.24294","title":"Toward GPU-Resident Climate Models: A Feasibility Study on Lossy Compression for the Spherical Harmonic Transform's Communication Bottleneck","display_name":"Toward GPU-Resident Climate Models: A Feasibility Study on Lossy Compression for the Spherical Harmonic Transform's Communication Bottleneck","publication_year":2026,"publication_date":"2026-09-21","ids":{"openalex":"https://openalex.org/W7214058484","doi":"https://doi.org/10.48550/arxiv.2609.24294"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.24294","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24294","pdf_url":"https://arxiv.org/pdf/2609.24294","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.24294","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152452422","display_name":"Lorenzo Breschi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Breschi, Lorenzo","raw_affiliation_strings":["University of Trento Trento , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento Trento , Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011440366","display_name":"Flavio Vella","orcid":"https://orcid.org/0000-0002-5676-9228","observed_orcids":["https://orcid.org/0000-0002-5676-9228"]},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Vella, Flavio","raw_affiliation_strings":["University of Trento Trento , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento Trento , Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193223587"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9789999723434448,"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":0.9789999723434448,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.002099999925121665,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spherical-harmonic-transform","display_name":"spherical harmonic transform","score":0.984000027179718},{"id":"https://openalex.org/keywords/communication-bottleneck","display_name":"communication bottleneck","score":0.6570000052452087},{"id":"https://openalex.org/keywords/zinc-finger-proteins","display_name":"zinc finger proteins","score":0.8939999938011169},{"id":"https://openalex.org/keywords/ecmwf-integrated-forecasting-system","display_name":"ECMWF Integrated Forecasting System","score":0.8209999799728394}],"concepts":[{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.7537999749183655},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.616100013256073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5834000110626221},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5776000022888184},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4876999855041504},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.45570001006126404},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C203858083","wikidata":"https://www.wikidata.org/wiki/Q188347","display_name":"Harmonic mean","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C26955809","wikidata":"https://www.wikidata.org/wiki/Q10167591","display_name":"Initial value problem","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33629998564720154},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C12455157","wikidata":"https://www.wikidata.org/wiki/Q7835331","display_name":"Transposition (logic)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3095000088214874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3068999946117401},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2776303044","wikidata":"https://www.wikidata.org/wiki/Q5463579","display_name":"Flying height","level":3,"score":0.29179999232292175},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C118365302","wikidata":"https://www.wikidata.org/wiki/Q4817115","display_name":"Atmospheric model","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.28029999136924744}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.24294","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24294","pdf_url":"https://arxiv.org/pdf/2609.24294","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2609.24294","doi":"https://doi.org/10.48550/arxiv.2609.24294","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.24294","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.24294","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24294","pdf_url":"https://arxiv.org/pdf/2609.24294","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334679","display_name":"Research Executive Agency","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214058484.pdf","grobid_xml":"https://content.openalex.org/works/W7214058484.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W1900210448"],"related_works":["https://openalex.org/W2118906989","https://openalex.org/W4412605638","https://openalex.org/W6969486393","https://openalex.org/W4405756077","https://openalex.org/W7202246324","https://openalex.org/W7212359044","https://openalex.org/W7169807706","https://openalex.org/W2059920026","https://openalex.org/W3043494828","https://openalex.org/W4388105305"],"abstract_inverted_index":{"Operational":[0],"pseudospectral":[1],"atmospheric":[2],"models":[3,31],"such":[4],"as":[5,85,112],"the":[6,34,80,108,115,139],"ECMWF":[7],"Integrated":[8],"Forecasting":[9],"System":[10],"(IFS)":[11],"run":[12],"today":[13],"almost":[14],"exclusively":[15],"on":[16,33,50],"CPUs;":[17],"GPU":[18,90],"ports":[19],"are":[20],"under":[21],"active":[22],"development":[23],"but":[24],"not":[25],"yet":[26],"used":[27],"in":[28],"production.":[29],"These":[30],"rely":[32],"Spherical":[35],"Harmonic":[36],"Transform":[37],"(SHT).":[38],"Each":[39],"time-step":[40],"requires":[41],"forward":[42],"and":[43,46,87],"inverse":[44],"SHTs,":[45],"both":[47],"passes":[48],"depend":[49],"global":[51,66],"pencil":[52],"transposition":[53],"that":[54,99],"redistribute":[55],"multi-dimensional":[56],"arrays":[57],"across":[58],"compute":[59],"nodes.":[60],"At":[61],"large":[62],"node":[63],"counts":[64],"these":[65],"collectives":[67],"dominate":[68],"wall-clock":[69],"time.":[70],"We":[71],"investigate":[72],"GPU-resident":[73],"lossy":[74],"compression,":[75],"using":[76],"representative":[77],"fields":[78],"from":[79],"DYAMOND":[81],"high-resolution":[82],"operational":[83],"dataset":[84],"input,":[86],"combining":[88],"measured":[89],"compression":[91],"throughput":[92],"with":[93],"SimGrid":[94],"network":[95],"simulation,":[96],"we":[97],"show":[98],"ZFP":[100,129],"at":[101,130],"16":[102],"bits":[103,132],"per":[104,133],"value":[105,134],"(rate-16),":[106],"about":[107],"same":[109],"storage":[110],"budget":[111],"float16,":[113],"matches":[114],"communication-time":[116],"reduction":[117],"of":[118,141],"float16":[119,142],"truncation":[120],"while":[121,143],"delivering":[122],"approximately":[123,137],"$\\mathbf{1600\\times}$":[124],"lower":[125,146],"mean":[126,147],"relative":[127,148],"error.":[128,149],"8":[131],"(rate-8)":[135],"achieves":[136],"$\\mathbf{1.93\\times}$":[138],"speedup":[140],"retaining":[144],"$\\mathbf{4\\times}$":[145]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-23T00:00:00"}