{"id":"https://openalex.org/W4399851697","doi":"https://doi.org/10.1145/3652032.3657567","title":"MixPert: Optimizing Mixed-Precision Floating-Point Emulation on GPU Integer Tensor Cores","display_name":"MixPert: Optimizing Mixed-Precision Floating-Point Emulation on GPU Integer Tensor Cores","publication_year":2024,"publication_date":"2024-06-20","ids":{"openalex":"https://openalex.org/W4399851697","doi":"https://doi.org/10.1145/3652032.3657567"},"language":"en","primary_location":{"id":"doi:10.1145/3652032.3657567","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652032.3657567","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652032.3657567","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652032.3657567","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070842569","display_name":"Zejia Lin","orcid":"https://orcid.org/0000-0002-7205-4062"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zejia Lin","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7205-4062","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109735501","display_name":"Aoyuan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aoyuan Sun","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-4686-4493","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039843650","display_name":"Xianwei Zhang","orcid":"https://orcid.org/0000-0003-3507-4299"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianwei Zhang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3507-4299","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5315-3375","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9950000047683716,"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"}},{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.839707612991333},{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.8065369129180908},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.6650484204292297},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6096519231796265},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.598721444606781},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5946473479270935},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5941396951675415},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5612800717353821},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.5603983402252197},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.48243626952171326},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.476096510887146},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.451598584651947},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.44550764560699463},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.408214807510376},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35499143600463867},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.21640488505363464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.839707612991333},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.8065369129180908},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.6650484204292297},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6096519231796265},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.598721444606781},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5946473479270935},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5941396951675415},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5612800717353821},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5603983402252197},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.48243626952171326},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.476096510887146},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.451598584651947},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.44550764560699463},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.408214807510376},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35499143600463867},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.21640488505363464},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652032.3657567","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652032.3657567","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652032.3657567","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652032.3657567","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652032.3657567","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652032.3657567","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399851697.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1969213662","https://openalex.org/W2011756527","https://openalex.org/W2028960610","https://openalex.org/W2091085232","https://openalex.org/W2096504919","https://openalex.org/W2566629575","https://openalex.org/W2791673912","https://openalex.org/W2838756705","https://openalex.org/W2895305554","https://openalex.org/W2948348275","https://openalex.org/W2963407707","https://openalex.org/W3008102594","https://openalex.org/W3101543398","https://openalex.org/W3126212707","https://openalex.org/W3132532188","https://openalex.org/W3138530731","https://openalex.org/W3139307480","https://openalex.org/W3159717682","https://openalex.org/W3211043030","https://openalex.org/W4221106024","https://openalex.org/W4221160294","https://openalex.org/W4233996382","https://openalex.org/W4246166885","https://openalex.org/W4283025350","https://openalex.org/W4321636633","https://openalex.org/W4322008031","https://openalex.org/W4376454336","https://openalex.org/W4388556627","https://openalex.org/W4389734559","https://openalex.org/W4391579666","https://openalex.org/W4391952402","https://openalex.org/W4392884779"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2891987081","https://openalex.org/W2778498407"],"abstract_inverted_index":{"Featuring":[0],"mixed-precision":[1,117],"tensor":[2],"operations,":[3],"accelerators":[4],"significantly":[5],"enhance":[6],"performance":[7,49,63],"for":[8],"many":[9],"error-tolerant":[10],"computing":[11,123],"tasks,":[12],"but":[13],"their":[14],"applicability":[15],"is":[16],"limited":[17],"in":[18],"scenarios":[19],"demanding":[20],"high":[21],"precision.":[22],"While":[23],"emulating":[24],"higher-precision":[25],"data":[26,79],"types":[27],"from":[28],"lower-precision":[29],"ones":[30],"can":[31,106],"bridge":[32],"this":[33],"gap,":[34],"existing":[35],"techniques":[36],"either":[37],"struggle":[38],"to":[39,138],"achieve":[40],"sufficient":[41],"accuracy":[42,65,102],"or":[43],"incur":[44],"excessive":[45],"overhead,":[46],"inevitably":[47],"negating":[48],"gains.":[50],"To":[51],"mitigate":[52],"the":[53,83],"issue,":[54],"we":[55],"propose":[56],"MixPert,":[57],"a":[58],"novel":[59],"system":[60],"that":[61,129],"balances":[62],"and":[64,81,114,124,152,156],"via":[66],"optimizing":[67],"single-precision":[68],"emulation":[69],"on":[70,86,101,120,140],"GPU":[71],"Integer":[72],"Tensor":[73,87],"Cores.":[74,88],"MixPert":[75,94,105,130,147],"devises":[76],"an":[77,132],"efficient":[78],"layout":[80],"augments":[82],"computation":[84],"pipeline":[85],"By":[89],"deeply":[90],"analyzing":[91],"performance-precision":[92],"trade-offs,":[93],"provides":[95],"users":[96],"with":[97,109],"multiple":[98],"configurations":[99],"based":[100],"requirements.":[103],"Furthermore,":[104],"seamlessly":[107],"integrate":[108],"compilers,":[110],"facilitating":[111],"automatic":[112],"adaptation":[113],"tuning":[115],"of":[116,135],"parameters.":[118],"Evaluations":[119],"real-world":[121],"scientific":[122],"deep":[125],"learning":[126],"applications":[127],"demonstrate":[128],"achieves":[131],"average":[133],"speedup":[134],"1.72\u00d7":[136],"compared":[137],"cuBLAS":[139],"general-purpose":[141],"cores.":[142],"Beyond":[143],"maintaining":[144],"improved":[145],"accuracy,":[146],"outperforms":[148],"state-of-the-art":[149],"approaches":[150],"APE":[151],"CUTLASS":[153],"by":[154],"1.22\u00d7":[155],"1.21\u00d7,":[157],"respectively.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}