{"id":"https://openalex.org/W4388581088","doi":"https://doi.org/10.1145/3624062.3624186","title":"High-level GPU code: a case study examining JAX and OpenMP.","display_name":"High-level GPU code: a case study examining JAX and OpenMP.","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581088","doi":"https://doi.org/10.1145/3624062.3624186"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624186","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624186","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624186","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 SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624186","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011805970","display_name":"Nestor Demeure","orcid":"https://orcid.org/0000-0002-0530-6530"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nestor Demeure","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, United States"],"raw_orcid":"https://orcid.org/0000-0002-0530-6530","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, United States","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080202253","display_name":"Theodore Kisner","orcid":"https://orcid.org/0000-0003-3510-7134"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Theodore Kisner","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0003-3510-7134","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037667446","display_name":"Reijo Keskitalo","orcid":"https://orcid.org/0000-0001-5748-5182"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reijo Keskitalo","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0001-5748-5182","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107343393","display_name":"R. C. Thomas","orcid":"https://orcid.org/0000-0002-2834-4257"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rollin Thomas","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-2834-4257","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010843883","display_name":"Julian Borrill","orcid":"https://orcid.org/0000-0001-5104-7122"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian Borrill","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0001-5104-7122","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102790041","display_name":"Wahid Bhimji","orcid":"https://orcid.org/0000-0002-6213-8617"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wahid Bhimji","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-6213-8617","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, United States of America","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011805970"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":1.345,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84958578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1105","last_page":"1113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9977999925613403,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9900000095367432,"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/porting","display_name":"Porting","score":0.9030052423477173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8431762456893921},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7577950954437256},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.7418842315673828},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6273412108421326},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6038182377815247},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4942796230316162},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4806448519229889},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4315224289894104},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.39700886607170105},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3909503221511841}],"concepts":[{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.9030052423477173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431762456893921},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7577950954437256},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.7418842315673828},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6273412108421326},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6038182377815247},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4942796230316162},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4806448519229889},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4315224289894104},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.39700886607170105},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3909503221511841}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3624062.3624186","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624186","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624186","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 SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3624062.3624186","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624186","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624186","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 SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1143651532","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G1286236842","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1677143136","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320317220","funder_display_name":"National Energy Research Scientific Computing Center"},{"id":"https://openalex.org/G1799333409","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G3083819904","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3944918260","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4501827968","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4565140552","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5076365615","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320317220","funder_display_name":"National Energy Research Scientific Computing Center"},{"id":"https://openalex.org/G5611014977","display_name":null,"funder_award_id":"HEP-ERCAP0023125","funder_id":"https://openalex.org/F4320317220","funder_display_name":"National Energy Research Scientific Computing Center"},{"id":"https://openalex.org/G6348972864","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7354628648","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G8306346728","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320317220","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320338292","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388581088.pdf","grobid_xml":"https://content.openalex.org/works/W4388581088.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1976579441","https://openalex.org/W1985462363","https://openalex.org/W1988888548","https://openalex.org/W2148897203","https://openalex.org/W2245493112","https://openalex.org/W2568054399","https://openalex.org/W2788749677","https://openalex.org/W2888259247","https://openalex.org/W2954698171","https://openalex.org/W2970909703","https://openalex.org/W2970971581","https://openalex.org/W2991101111","https://openalex.org/W3081656884","https://openalex.org/W3115858121","https://openalex.org/W3157590335","https://openalex.org/W3161200675","https://openalex.org/W3193023761","https://openalex.org/W3195293013","https://openalex.org/W3196582238","https://openalex.org/W4234180294","https://openalex.org/W6912644843","https://openalex.org/W6968978714"],"related_works":["https://openalex.org/W1820309981","https://openalex.org/W3124707092","https://openalex.org/W2375332572","https://openalex.org/W28826848","https://openalex.org/W3123383020","https://openalex.org/W4312942606","https://openalex.org/W2166776054","https://openalex.org/W2912579397","https://openalex.org/W2152694830","https://openalex.org/W2128640905"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"a":[3,12,58,68,111,144],"new":[4],"scientific":[5],"software":[6,60],"design":[7],"pattern":[8],"has":[9],"emerged,":[10],"pairing":[11],"Python":[13,87,168],"interface":[14],"with":[15,72,117],"high-performance":[16],"kernels":[17],"in":[18,36,103],"lower-level":[19],"languages.":[20],"The":[21],"rise":[22],"of":[23,29,55,67,143,152,159,162],"general-purpose":[24],"GPUs":[25],"necessitates":[26],"the":[27,53,85,141,150,157],"rewriting":[28],"many":[30],"such":[31],"kernels,":[32,146],"which":[33],"poses":[34],"challenges":[35],"GPU":[37,138],"programming":[38],"and":[39,43,50,89,156],"ensures":[40],"future":[41],"portability":[42],"flexibility.":[44],"This":[45,74],"paper":[46],"documents":[47],"our":[48,118],"experience":[49],"observations":[51],"during":[52],"process":[54],"porting":[56,82,142],"TOAST,":[57],"cosmology":[59],"framework":[61],"designed":[62],"to":[63,70,78,100],"take":[64],"full":[65],"advantage":[66],"supercomputer,":[69],"work":[71],"GPUs.":[73],"exploration":[75],"led":[76],"us":[77],"compare":[79],"two":[80],"different":[81],"strategies:":[83],"utilizing":[84],"JAX":[86,96],"library":[88],"employing":[90,160],"OpenMP":[91,107],"Target":[92,108],"Offload":[93,109],"compiler":[94],"directives.":[95],"allows":[97],"kernel":[98],"code":[99],"be":[101],"written":[102],"pure":[104],"Python,":[105],"whereas":[106],"is":[110],"directive-based":[112],"strategy":[113],"that":[114],"integrates":[115],"seamlessly":[116],"existing":[119],"OpenMP-accelerated":[120],"C++":[121],"kernels.":[122],"Both":[123],"frameworks":[124,164],"are":[125],"high-level,":[126],"abstracting":[127],"system":[128],"architecture":[129],"details":[130],"while":[131],"aiming":[132],"for":[133,165],"straightforward,":[134],"portable,":[135],"yet":[136],"performant":[137],"code.":[139],"Through":[140],"dozen":[145],"we":[147],"delve":[148],"into":[149],"analysis":[151],"development":[153],"cost,":[154],"performance,":[155],"viability":[158],"either":[161],"these":[163],"complex":[166],"numerical":[167],"applications.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
