{"id":"https://openalex.org/W7225040243","doi":"https://doi.org/10.5281/zenodo.23871044","title":"Subgrid-Scale Turbulence Closure and 44.01\u00d7 Speedup on Blackwell SM120: Matrix-Free Fused Triton Kernels for High-Resolution Global Climate Modeling","display_name":"Subgrid-Scale Turbulence Closure and 44.01\u00d7 Speedup on Blackwell SM120: Matrix-Free Fused Triton Kernels for High-Resolution Global Climate Modeling","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225040243","doi":"https://doi.org/10.5281/zenodo.23871044"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23871044","doi":"https://doi.org/10.5281/zenodo.23871044","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23871044","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23871044","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160290735","display_name":"Axel Domingo Padilla Arriaga","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Padilla Arriaga, Axel Domingo","raw_affiliation_strings":["RadhikaChain Sovereign Infrastructure & Autonomous Research Swarm"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RadhikaChain Sovereign Infrastructure & Autonomous Research Swarm","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160290735"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.9984999895095825,"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":0.9984999895095825,"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":0.00039999998989515007,"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":0.00019999999494757503,"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/triton","display_name":"Triton","score":0.7160000205039978},{"id":"https://openalex.org/keywords/atmospheric-modeling","display_name":"atmospheric modeling","score":0.7080000042915344},{"id":"https://openalex.org/keywords/gpu-kernel-optimization","display_name":"GPU kernel optimization","score":0.6079999804496765},{"id":"https://openalex.org/keywords/memory-throughput","display_name":"memory throughput","score":0.5600000023841858},{"id":"https://openalex.org/keywords/high-bandwidth-memory","display_name":"high-bandwidth memory","score":0.675000011920929},{"id":"https://openalex.org/keywords/coalesced-memory-access","display_name":"coalesced memory access","score":0.6639999747276306}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8532999753952026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5684000253677368},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5673999786376953},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.5127000212669373},{"id":"https://openalex.org/C196558001","wikidata":"https://www.wikidata.org/wiki/Q190132","display_name":"Turbulence","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C121448008","wikidata":"https://www.wikidata.org/wiki/Q1755722","display_name":"Large eddy simulation","level":3,"score":0.4537000060081482},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45239999890327454},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.41130000352859497},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.37450000643730164},{"id":"https://openalex.org/C146834321","wikidata":"https://www.wikidata.org/wiki/Q2979672","display_name":"Closure (psychology)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C118365302","wikidata":"https://www.wikidata.org/wiki/Q4817115","display_name":"Atmospheric model","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.328900009393692},{"id":"https://openalex.org/C23379533","wikidata":"https://www.wikidata.org/wiki/Q1099481","display_name":"Clear-air turbulence","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.3125},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C161067210","wikidata":"https://www.wikidata.org/wiki/Q1464943","display_name":"Wind speed","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C5072599","wikidata":"https://www.wikidata.org/wiki/Q379788","display_name":"Advection","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C168754636","wikidata":"https://www.wikidata.org/wiki/Q620920","display_name":"Climate model","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2734000086784363},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.272599995136261},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C41156917","wikidata":"https://www.wikidata.org/wiki/Q682831","display_name":"Downscaling","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C2780615140","wikidata":"https://www.wikidata.org/wiki/Q920419","display_name":"Upgrade","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23871044","doi":"https://doi.org/10.5281/zenodo.23871044","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23871044","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23871045","doi":"https://doi.org/10.5281/zenodo.23871045","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23871045","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23871044","doi":"https://doi.org/10.5281/zenodo.23871044","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23871044","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2763018387","https://openalex.org/W4414426751","https://openalex.org/W3184002667","https://openalex.org/W7225049151","https://openalex.org/W7146768688","https://openalex.org/W7162816398","https://openalex.org/W2102694295","https://openalex.org/W3087387446","https://openalex.org/W7225037637","https://openalex.org/W4402284386"],"abstract_inverted_index":{"High-resolution":[0],"atmospheric":[1],"modeling":[2],"frameworks":[3,28],"encounter":[4],"severe":[5],"memory":[6,102,125],"bottlenecks":[7],"when":[8],"evaluating":[9],"non-linear":[10],"subgrid":[11,48],"turbulence":[12,49],"closures":[13],"across":[14],"global":[15,124],"meshes":[16],"(such":[17],"as":[18],"ERA5":[19],"with":[20],"103.8":[21],"million":[22],"3D":[23],"points).":[24],"Standard":[25],"deep":[26],"learning":[27],"(PyTorch":[29],"Eager)":[30],"dispatch":[31],"multiple":[32],"disjoint":[33],"kernels,":[34],"causing":[35],"effective":[36],"throughput":[37],"to":[38,118],"drop":[39],"below":[40],"50":[41],"GB/s.":[42],"We":[43],"present":[44],"a":[45,91],"register-fused,":[46],"matrix-free":[47],"closure":[50],"operator":[51],"in":[52],"Triton":[53],"coupling":[54],"Smagorinsky":[55],"eddy":[56],"dissipation,":[57],"advective":[58],"shocks,":[59],"and":[60,96,121],"Coriolis":[61],"dispersion.":[62],"On":[63],"an":[64],"NVIDIA":[65],"RTX":[66],"PRO":[67],"6000":[68],"Blackwell":[69],"Server":[70],"Edition":[71],"GPU":[72],"(94.97":[73],"GB":[74],"VRAM,":[75],"188":[76],"SMs,":[77],"sm_120),":[78],"the":[79],"kernel":[80],"achieves":[81],"0.8597":[82],"ms":[83,87],"latency":[84],"versus":[85],"37.84":[86],"for":[88],"PyTorch":[89],"Eager\u2014delivering":[90],"measured":[92],"44.01x":[93],"end-to-end":[94],"speedup":[95],"sustaining":[97],"1,449.14":[98],"GB/s":[99],"of":[100],"high-bandwidth":[101],"(HBM)":[103],"throughput.":[104],"Low-level":[105],"compiler":[106],"SASS":[107],"telemetry":[108],"confirmed":[109],"optimal":[110],"occupancy:":[111],"40":[112],"registers":[113],"per":[114],"thread,":[115],"zero":[116],"spills":[117],"local":[119],"memory,":[120],"100%":[122],"coalesced":[123],"access.":[126]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2026-11-02T00:00:00"}