{"id":"https://openalex.org/W4414818955","doi":"https://doi.org/10.1109/ipdps65963.2026.00017","title":"cuHPX: GPU-Accelerated Differentiable Spherical Harmonic Transforms on HEALPix Grids","display_name":"cuHPX: GPU-Accelerated Differentiable Spherical Harmonic Transforms on HEALPix Grids","publication_year":2026,"publication_date":"2026-05-25","ids":{"openalex":"https://openalex.org/W4414818955","doi":"https://doi.org/10.1109/ipdps65963.2026.00017"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps65963.2026.00017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps65963.2026.00017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.01785","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024414867","display_name":"X. Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaopo Cheng","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103230483","display_name":"Akshay Subramaniam","orcid":"https://orcid.org/0000-0003-0297-0978"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akshay Subramaniam","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075806978","display_name":"Shixun Wu","orcid":"https://orcid.org/0000-0001-8637-3307"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shixun Wu","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090320439","display_name":"Noah Brenowitz","orcid":"https://orcid.org/0000-0001-8615-4921"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noah Brenowitz","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00493117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.920199990272522,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.920199990272522,"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/grid","display_name":"Grid","score":0.7014999985694885},{"id":"https://openalex.org/keywords/spherical-harmonics","display_name":"Spherical harmonics","score":0.6850000023841858},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5738999843597412},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.48750001192092896},{"id":"https://openalex.org/keywords/spherical-geometry","display_name":"Spherical geometry","score":0.4575999975204468},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45239999890327454},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4262999892234802},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4205999970436096},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.33379998803138733}],"concepts":[{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.7014999985694885},{"id":"https://openalex.org/C3768446","wikidata":"https://www.wikidata.org/wiki/Q877100","display_name":"Spherical harmonics","level":2,"score":0.6850000023841858},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5949000120162964},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5738999843597412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5360000133514404},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4603999853134155},{"id":"https://openalex.org/C77730005","wikidata":"https://www.wikidata.org/wiki/Q326905","display_name":"Spherical geometry","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34200000762939453},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.33239999413490295},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.33230000734329224},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C43173174","wikidata":"https://www.wikidata.org/wiki/Q2646942","display_name":"Regular grid","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.3068000078201294},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C64208722","wikidata":"https://www.wikidata.org/wiki/Q861606","display_name":"Lagrange polynomial","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C48753275","wikidata":"https://www.wikidata.org/wiki/Q11216","display_name":"Numerical analysis","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C2778664614","wikidata":"https://www.wikidata.org/wiki/Q575597","display_name":"Spherical cap","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ipdps65963.2026.00017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps65963.2026.00017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.01785","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.01785","pdf_url":"https://arxiv.org/pdf/2510.01785","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.01785","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.01785","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.01785","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.01785","pdf_url":"https://arxiv.org/pdf/2510.01785","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414818955.pdf","grobid_xml":"https://content.openalex.org/works/W4414818955.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"HEALPix":[0,42,82],"(Hierarchical":[1],"Equal":[2],"Area":[3],"isoLatitude":[4],"Pixelization)":[5],"is":[6],"a":[7,149],"widely":[8],"adopted":[9],"spherical":[10,37,75,114],"grid":[11,115],"system":[12],"in":[13,154],"astrophysics,":[14,157],"cosmology,":[15],"and":[16,53,78,105,111,127,145,158],"Earth":[17],"sciences.":[18],"Its":[19],"equal-area,":[20],"iso-latitude":[21],"structure":[22],"makes":[23],"it":[24],"particularly":[25],"well-suited":[26],"for":[27,56,74,96],"large-scale":[28],"data":[29],"analysis":[30,77],"on":[31,41,81],"the":[32,54],"sphere.":[33],"However,":[34],"implementing":[35],"high-performance":[36],"harmonic":[38,76],"transforms":[39,58],"(SHTs)":[40],"grids":[43],"remains":[44],"challenging":[45],"due":[46],"to":[47,134],"irregular":[48],"pixel":[49],"geometry,":[50],"latitude-dependent":[51],"alignments,":[52],"demands":[55],"high-resolution":[57],"at":[59],"scale.":[60],"In":[61],"this":[62],"work,":[63],"we":[64,119],"present":[65],"cuHPX,":[66],"an":[67],"optimized":[68,163],"CUDA":[69],"library":[70],"that":[71,121],"provides":[72],"functionality":[73],"related":[79],"utilities":[80],"grids.":[83],"Beyond":[84],"delivering":[85],"substantial":[86],"performance":[87],"improvements,":[88],"cuHPX":[89,122,147],"ensures":[90],"high":[91],"numerical":[92,139],"accuracy,":[93,143],"analytic":[94],"gradients":[95],"integration":[97],"with":[98,166],"deep":[99],"learning":[100],"frameworks,":[101],"out-of-core":[102],"memory-efficient":[103],"optimization,":[104],"flexible":[106],"regridding":[107],"between":[108],"HEALPix,":[109],"equiangular,":[110],"other":[112],"common":[113],"formats.":[116],"Through":[117],"evaluation,":[118],"show":[120],"achieves":[123],"rapid":[124],"spectral":[125],"convergence":[126],"delivers":[128],"over":[129],"20":[130],"times":[131],"speedup":[132],"compared":[133],"existing":[135],"libraries,":[136],"while":[137],"maintaining":[138],"consistency.":[140],"By":[141],"combining":[142],"scalability,":[144],"differentiability,":[146],"enables":[148],"broad":[150],"range":[151],"of":[152],"applications":[153],"climate":[155],"science,":[156],"machine":[159],"learning,":[160],"effectively":[161],"bridging":[162],"GPU":[164],"kernels":[165],"scientific":[167],"workflows.":[168]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}