{"id":"https://openalex.org/W4414790426","doi":"https://doi.org/10.1145/3731599.3767573","title":"Mojo: MLIR-based Performance-Portable HPC Science Kernels on GPUs for the Python Ecosystem","display_name":"Mojo: MLIR-based Performance-Portable HPC Science Kernels on GPUs for the Python Ecosystem","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4414790426","doi":"https://doi.org/10.1145/3731599.3767573"},"language":"en","primary_location":{"id":"doi:10.1145/3731599.3767573","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767573","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767573","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032103653","display_name":"William F. Godoy","orcid":"https://orcid.org/0000-0002-2590-5178"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Godoy","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0002-2590-5178","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119833462","display_name":"Tatiana Melnichenko","orcid":"https://orcid.org/0009-0001-0977-5481"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]},{"id":"https://openalex.org/I1309980932","display_name":"National Transportation Research Center","ror":"https://ror.org/011fc0n53","country_code":"US","type":"government","lineage":["https://openalex.org/I1309980932"]},{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tatiana Melnichenko","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, Knoxville, Tennessee, USA and Oak Ridge National Laboratory (ORNL), Knoxville, Tennessee, USA"],"raw_orcid":"https://orcid.org/0009-0001-0977-5481","affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, Knoxville, Tennessee, USA and Oak Ridge National Laboratory (ORNL), Knoxville, Tennessee, USA","institution_ids":["https://openalex.org/I75027704","https://openalex.org/I1309980932","https://openalex.org/I2802706902","https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083524237","display_name":"Pedro Valero\u2010Lara","orcid":"https://orcid.org/0000-0002-1479-4310"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]},{"id":"https://openalex.org/I1309980932","display_name":"National Transportation Research Center","ror":"https://ror.org/011fc0n53","country_code":"US","type":"government","lineage":["https://openalex.org/I1309980932"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro Valero-Lara","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Knoxville, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0002-1479-4310","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Knoxville, Tennessee, USA","institution_ids":["https://openalex.org/I1309980932","https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041347658","display_name":"Wael Elwasif","orcid":"https://orcid.org/0000-0003-0554-1036"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wael Elwasif","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0003-0554-1036","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035252865","display_name":"Philip W. Fackler","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip Fackler","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0003-4837-6181","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072339196","display_name":"Rafael Ferreira da Silva","orcid":"https://orcid.org/0000-0002-1720-0928"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafael Ferreira Da Silva","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0002-1720-0928","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019745966","display_name":"Keita Teranishi","orcid":"https://orcid.org/0000-0001-6647-2690"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keita Teranishi","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0001-6647-2690","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061838490","display_name":"Jeffrey S. Vetter","orcid":"https://orcid.org/0000-0002-2449-6720"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Vetter","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0002-2449-6720","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2114","last_page":"2128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.9664000272750854,"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":0.9664000272750854,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9659000039100647,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9401000142097473,"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/software-portability","display_name":"Software portability","score":0.6769000291824341},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.659500002861023},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5898000001907349},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.5764999985694885},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.49959999322891235},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.3626999855041504},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.35850000381469727},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.3546000123023987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8222000002861023},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6769000291824341},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.659500002861023},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5898000001907349},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.5764999985694885},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.49959999322891235},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4481000006198883},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43650001287460327},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.3490000069141388},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34209999442100525},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.3312000036239624},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.31450000405311584},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C19024347","wikidata":"https://www.wikidata.org/wiki/Q211496","display_name":"High-level programming language","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26919999718666077},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3731599.3767573","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767573","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.21039","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.21039","pdf_url":"https://arxiv.org/pdf/2509.21039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767573","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767573","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,51,84],"explore":[1],"the":[2,7,18,23,119,135,140],"performance":[3,35,73,88],"and":[4,36,43,64,70,80,93,107,115,122,145],"portability":[5],"of":[6,142],"novel":[8],"Mojo":[9,31,129],"language":[10,20],"for":[11,46,95,104,108],"scientific":[12,54,143],"computing":[13,144],"workloads":[14],"on":[15,22,77,101,112],"GPUs.":[16,83,117],"As":[17],"first":[19],"based":[21],"LLVM\u2019s":[24],"Multi-Level":[25],"Intermediate":[26],"Representation":[27],"(MLIR)":[28],"compiler":[29],"infrastructure,":[30],"aims":[32],"to":[33],"close":[34,131],"productivity":[37],"gaps":[38,99,133],"by":[39],"combining":[40],"Python\u2019s":[41],"interoperability":[42],"CUDA-like":[44],"syntax":[45],"compile-time":[47],"portable":[48],"GPU":[49],"programming.":[50],"target":[52],"four":[53],"workloads:":[55],"a":[56],"seven-point":[57],"stencil":[58],"(memory-bound),":[59,61],"BabelStream":[60],"miniBUDE":[62],"(compute-bound),":[63],"Hartree\u2013Fock":[65],"(compute-bound":[66],"with":[67,91],"atomic":[68,105],"operations);":[69],"compare":[71],"their":[72],"against":[74],"vendor":[75],"baselines":[76],"NVIDIA":[78,116],"H100":[79],"AMD":[81,102,114],"MI300A":[82],"show":[85],"that":[86],"Mojo\u2019s":[87],"is":[89],"competitive":[90],"CUDA":[92],"HIP":[94],"memory-bound":[96],"kernels,":[97],"whereas":[98],"exist":[100],"GPUs":[103],"operations":[106],"fast-math":[109],"compute-bound":[110],"kernels":[111],"both":[113],"Although":[118],"learning":[120],"curve":[121],"programming":[123],"requirements":[124],"are":[125],"still":[126],"fairly":[127],"low-level,":[128],"can":[130],"significant":[132],"in":[134,139],"fragmented":[136],"Python":[137],"ecosystem":[138],"convergence":[141],"AI.":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
