{"id":"https://openalex.org/W4407857403","doi":"https://doi.org/10.1145/3696443.3708967","title":"IntelliGen: Instruction-Level Auto-tuning for Tensor Program with Monotonic Memory Optimization","display_name":"IntelliGen: Instruction-Level Auto-tuning for Tensor Program with Monotonic Memory Optimization","publication_year":2025,"publication_date":"2025-02-22","ids":{"openalex":"https://openalex.org/W4407857403","doi":"https://doi.org/10.1145/3696443.3708967"},"language":"en","primary_location":{"id":"doi:10.1145/3696443.3708967","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696443.3708967","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 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3696443.3708967","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046669647","display_name":"Zixuan Ma","orcid":"https://orcid.org/0000-0001-9630-7645"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zixuan Ma","raw_affiliation_strings":["Qingcheng.AI, Beijing, China","Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9630-7645","affiliations":[{"raw_affiliation_string":"Qingcheng.AI, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735476","display_name":"Haojie Wang","orcid":"https://orcid.org/0000-0003-4605-148X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojie Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4605-148X","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111008124","display_name":"Jingze Xing","orcid":"https://orcid.org/0000-0002-4727-0150"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingze Xing","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4727-0150","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046794402","display_name":"Shuhong Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhong Huang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-9442-7375","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002743116","display_name":"Liyan Zheng","orcid":"https://orcid.org/0000-0001-7327-748X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyan Zheng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7327-748X","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101752464","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0001-9045-9269"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9045-9269","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039766485","display_name":"Huanqi Cao","orcid":"https://orcid.org/0000-0002-3092-1578"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanqi Cao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3092-1578","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023674199","display_name":"Kezhao Huang","orcid":"https://orcid.org/0009-0006-7273-0952"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kezhao Huang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-7273-0952","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032285247","display_name":"Mingshu Zhai","orcid":"https://orcid.org/0009-0009-7573-2250"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingshu Zhai","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-7573-2250","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023681514","display_name":"Shizhi Tang","orcid":"https://orcid.org/0000-0002-6543-0859"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shizhi Tang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6543-0859","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000912240","display_name":"P. X. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Penghan Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-9308-6273","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071200777","display_name":"Jidong Zhai","orcid":"https://orcid.org/0000-0002-7656-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jidong Zhai","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7656-6428","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5046669647"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.1546,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81984576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"107","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9757000207901001,"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":0.6526438593864441},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.6489812135696411},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5556784868240356},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5285550355911255},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19615212082862854},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.06490069627761841}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6526438593864441},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.6489812135696411},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5556784868240356},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5285550355911255},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19615212082862854},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.06490069627761841},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696443.3708967","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696443.3708967","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 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696443.3708967","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696443.3708967","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 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2034761517","https://openalex.org/W2954698171","https://openalex.org/W2981758446","https://openalex.org/W4212986322","https://openalex.org/W4245179399","https://openalex.org/W4281707342","https://openalex.org/W4281710230","https://openalex.org/W4327930469","https://openalex.org/W4394998532"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2077314575","https://openalex.org/W4315701745","https://openalex.org/W1990290471","https://openalex.org/W4380682190","https://openalex.org/W2005710836","https://openalex.org/W2102386043","https://openalex.org/W2945307361"],"abstract_inverted_index":{"Tensor":[0,54],"compilers":[1,28,55],"play":[2],"a":[3,17,57,99,109,126],"critical":[4],"role":[5],"in":[6,20],"optimizing":[7],"deep":[8],"neural":[9],"networks":[10],"(DNNs),":[11],"with":[12,47,112,138],"memory":[13,62,78,117],"performance":[14,63],"emerging":[15],"as":[16],"key":[18],"bottleneck":[19],"code":[21],"generation":[22],"for":[23,130],"DNN":[24],"models.":[25],"Existing":[26],"tensor":[27,110],"are":[29],"constrained":[30],"by":[31],"inefficient":[32],"auto-tuning":[33,52,93,97,114,136],"algorithms.":[34],"They":[35],"either":[36],"must":[37],"deploy":[38],"coarse-grained":[39],"descriptions,":[40],"thus":[41,95],"miss":[42],"potential":[43],"optimization,":[44],"or":[45],"struggle":[46],"vast":[48],"search":[49],"spaces,":[50],"rendering":[51],"inapplicable.":[53],"require":[56],"more":[58],"holistic":[59],"optimization":[60,75,86,128,131],"of":[61,92,145],"to":[64,83,147],"overcome":[65],"these":[66,104],"constraints.":[67],"To":[68],"address":[69],"this":[70],"issue,":[71],"we":[72,106],"focus":[73],"our":[74],"objective":[76],"on":[77,98,103,132,158],"performance,":[79],"which":[80],"allows":[81],"us":[82],"design":[84,120],"monotonic":[85,116,127],"methods,":[87],"significantly":[88],"enhancing":[89],"the":[90,167],"efficiency":[91],"and":[94,115,125,150,155,163],"enabling":[96],"fine-granularity":[100],"description.":[101],"Based":[102],"observations,":[105],"propose":[107],"IntelliGen,":[108],"compiler":[111],"instruction-level":[113,122],"optimization.":[118],"We":[119],"an":[121],"graph":[123],"description,":[124,140],"method":[129],".":[133],"Benefiting":[134],"from":[135],"techniques":[137],"fine-grained":[139],"IntelliGen":[141],"demonstrates":[142],"significant":[143],"speedup":[144],"up":[146],"3.13\u00d7,":[148],"3.55\u00d7,":[149],"16.9\u00d7":[151],"(averaging":[152],"1.46\u00d7,":[153],"1.85\u00d7,":[154],"2.30\u00d7,":[156],"respectively)":[157],"NVIDIA":[159],"GPUs,":[160,162],"AMD":[161],"Cambricon":[164],"MLUs":[165],"over":[166],"most":[168],"efficient":[169],"existing":[170],"frameworks.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}