{"id":"https://openalex.org/W7170091325","doi":"https://doi.org/10.1145/3785462.3815862","title":"A Precision Emulation Approach to the GPU Acceleration of Ab Initio Electronic Structure Calculations","display_name":"A Precision Emulation Approach to the GPU Acceleration of Ab Initio Electronic Structure Calculations","publication_year":2026,"publication_date":"2026-07-22","ids":{"openalex":"https://openalex.org/W7170091325","doi":"https://doi.org/10.1145/3785462.3815862"},"language":null,"primary_location":{"id":"doi:10.1145/3785462.3815862","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785462.3815862","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 Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3785462.3815862","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104172348","display_name":"Hang Liu","orcid":"https://orcid.org/0000-0002-3486-7863"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Liu","raw_affiliation_strings":["Texas Advanced Computing Center, The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-3486-7863","affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367646","display_name":"Junjie Li","orcid":"https://orcid.org/0000-0002-1051-5927"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junjie Li","raw_affiliation_strings":["Texas Advanced Computing Center, The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-1051-5927","affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018692017","display_name":"Yinzhi Wang","orcid":"https://orcid.org/0000-0001-8505-0223"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinzhi Wang","raw_affiliation_strings":["Pittsburgh Computing Center, Carnegie Mellon University, Pittsburgh, PA, USA","Texas Advanced Computing Center, The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-8505-0223","affiliations":[{"raw_affiliation_string":"Pittsburgh Computing Center, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Texas Advanced Computing Center, The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050597860","display_name":"Niraj K. Nepal","orcid":"https://orcid.org/0000-0002-7281-3268"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niraj Nepal","raw_affiliation_strings":["Pittsburgh Computing Center, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7281-3268","affiliations":[{"raw_affiliation_string":"Pittsburgh Computing Center, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100322853","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0002-9837-5796"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["Pittsburgh Computing Center, Carnegie Mellon University, Pittsburgh, PA, USA","Texas Advanced Computing Center, The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-9837-5796","affiliations":[{"raw_affiliation_string":"Pittsburgh Computing Center, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Texas Advanced Computing Center, The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"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":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.8978000283241272},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.6830999851226807},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5133000016212463},{"id":"https://openalex.org/keywords/single-precision-floating-point-format","display_name":"Single-precision floating-point format","score":0.45210000872612},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.43230000138282776},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.3723999857902527},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.36880001425743103},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.367000013589859}],"concepts":[{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.8978000283241272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912999987602234},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6830999851226807},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.6819000244140625},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5133000016212463},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.45210000872612},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44369998574256897},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3986000120639801},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3912000060081482},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.367900013923645},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.3571999967098236},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.3310000002384186},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.3239000141620636},{"id":"https://openalex.org/C83581934","wikidata":"https://www.wikidata.org/wiki/Q527381","display_name":"Arbitrary-precision arithmetic","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C2781442258","wikidata":"https://www.wikidata.org/wiki/Q46310","display_name":"Ab initio","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C202799725","wikidata":"https://www.wikidata.org/wiki/Q272035","display_name":"Accuracy and precision","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3785462.3815862","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785462.3815862","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 Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3785462.3815862","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785462.3815862","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 Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2738246091","display_name":null,"funder_award_id":"OAC-2139536","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6117982661","display_name":null,"funder_award_id":"OAC-2402542","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2006326929","https://openalex.org/W2026499846","https://openalex.org/W2104380208","https://openalex.org/W2156597786","https://openalex.org/W3138530731","https://openalex.org/W4388581248","https://openalex.org/W4392884779","https://openalex.org/W4395064757","https://openalex.org/W4406214914"],"related_works":[],"abstract_inverted_index":{"This":[0,96],"study":[1],"explores":[2],"the":[3,35,40,56,59,85,93,99],"use":[4],"of":[5,58,87,101],"INT8-based":[6],"emulation":[7],"for":[8,24,108],"accelerating":[9],"traditional":[10,71],"FP64-based":[11],"HPC":[12],"workloads":[13],"on":[14,51],"modern":[15],"GPU":[16],"architectures.":[17],"Through":[18],"SCILIB-Accel":[19],"automatic":[20],"BLAS":[21],"offload":[22],"tool":[23],"cache-coherent":[25],"Unified":[26],"Memory":[27],"Architecture,":[28],"we":[29],"emulate":[30],"FP64":[31],"matrix":[32],"multiplications":[33],"in":[34,39,112],"LSMS":[36],"CPU":[37],"application":[38],"MuST":[41],"suite":[42],"without":[43],"code":[44],"changes.":[45],"We":[46,83],"find":[47],"that":[48],"accuracy":[49,89],"depends":[50],"both":[52],"arithmetic":[53],"precision":[54,68,110],"and":[55,90],"properties":[57],"operator,":[60],"which":[61],"can":[62],"be":[63],"dealt":[64],"with":[65],"through":[66],"tunable":[67],"emulation.":[69],"Unlike":[70],"mixed-precision":[72],"approaches,":[73],"this":[74],"method":[75],"preserves":[76],"original":[77],"algorithms":[78],"while":[79],"optimizing":[80],"hardware":[81,103],"utilization.":[82],"showcase":[84],"potential":[86,100],"improving":[88],"performance":[91],"at":[92],"same":[94],"time.":[95],"work":[97],"highlights":[98],"AI-driven":[102],"to":[104],"transform":[105],"HPC,":[106],"advocating":[107],"adaptive":[109],"strategies":[111],"future":[113],"scientific":[114],"computing.":[115]},"counts_by_year":[],"updated_date":"2026-07-23T06:02:39.697066","created_date":"2026-07-23T00:00:00"}
