{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:49:18Z","timestamp":1768031358118,"version":"3.49.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T00:00:00Z","timestamp":1648857600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T00:00:00Z","timestamp":1648857600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,2]]},"DOI":"10.1109\/cgo53902.2022.9741260","type":"proceedings-article","created":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T15:51:20Z","timestamp":1648569080000},"page":"313-324","source":"Crossref","is-referenced-by-count":6,"title":["Optimizing GPU Deep Learning Operators with Polyhedral Scheduling Constraint Injection"],"prefix":"10.1109","author":[{"given":"Cedric","family":"Bastoul","sequence":"first","affiliation":[{"name":"Huawei Technologies France,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Technologies France,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harenome","family":"Razanajato","sequence":"additional","affiliation":[{"name":"Huawei Technologies France,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nelson","family":"Lossing","sequence":"additional","affiliation":[{"name":"Huawei Technologies France,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adilla","family":"Susungi","sequence":"additional","affiliation":[{"name":"Huawei Technologies France,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"de Juan","sequence":"additional","affiliation":[{"name":"Huawei Technologies France,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Etienne","family":"Filhol","sequence":"additional","affiliation":[{"name":"Huawei Technologies France,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baptiste","family":"Jarry","sequence":"additional","affiliation":[{"name":"Huawei Technologies France,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gianpietro","family":"Consolaro","sequence":"additional","affiliation":[{"name":"Huawei Technologies France,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref33","first-page":"579","article-title":"Tvm: An automated end-to-end optimizing compiler for deep learning","author":"chen","year":"2018","journal-title":"Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation ser OSDI’18"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15582-6_49"},{"key":"ref31","author":"schrijver","year":"1986","journal-title":"Theory of Linear and Integer Programming"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF02577874"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","article-title":"Glove: Global vectors for word representation","author":"pennington","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref35","first-page":"142","article-title":"Learning word vectors for sentiment analysis","author":"maas","year":"2011","journal-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref34","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human LanguageTechnologies Volume 1 (Long and Short Papers)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/263699.263719"},{"key":"ref27","article-title":"Effective Automatic Parallelization and Locality Optimization using the Polyhedral Model","author":"bondhugula","year":"2008"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/581630.581650"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3355606"},{"key":"ref1","first-page":"1581","article-title":"Polyhedron model","author":"feautrier","year":"2011","journal-title":"Encyclopedia of Parallel Computing"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF01407835"},{"key":"ref22","article-title":"Improving parallelism and data locality with affine partitioning","author":"lim","year":"2001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF01379404"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2896389"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375595"},{"key":"ref26","article-title":"Computing dependence direction vectors and dependence cones with linear systems","author":"irigoin","year":"1987","journal-title":"Ecole des Mines de Paris Fontainebleau (France)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3178372.3179507"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2892208.2892217"},{"key":"ref51","first-page":"193","article-title":"Tiramisu: A polyhedral compiler for expressing fast and portable code","author":"baghdadi","year":"2019","journal-title":"International Symposium on Code Generation and Optimization CGO"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3033019.3033022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS48598.2019.9188233"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3229865"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661176"},{"key":"ref40","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400713"},{"key":"ref13","article-title":"Scheduling for ppcg","volume":"6","author":"verdoolaege","year":"2017","journal-title":"CW Reports"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICAPP.1995.472180"},{"key":"ref15","first-page":"8","article-title":"CHiLL: A framework for composing high-level loop transformations","author":"chen","year":"2008","journal-title":"USC Computer Science"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2854038.2854048"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007554627716"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2004.1342537"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2743016"},{"key":"ref4","article-title":"Stripe: Tensor compilation via the nested polyhedral model","volume":"abs 1903 6498","author":"zerrell","year":"2019","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3211346.3211354"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454106"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3433103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-2233-5"},{"key":"ref7","article-title":"Mindspore","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2009.18"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-015-1483-z"},{"key":"ref46","article-title":"Joint scheduling and layout optimization to enable multi-level vectorization","author":"vasilache","year":"2012","journal-title":"Second International Workshop on Polyhedral Compilation Techniques (IMPACT)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314653"},{"key":"ref48","article-title":"Extending pluto-style polyhedral scheduling with consecutivity","author":"verdoolaege","year":"2018","journal-title":"In 8th Int Workshop on Polyhedral Compilation Techniques (IMPACT 2018)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462187"},{"key":"ref42","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1926385.1926449"},{"key":"ref43","article-title":"Scalable optimization techniques in the polyhedral model","author":"vasilache","year":"2007"}],"event":{"name":"2022 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2022,4,2]]},"end":{"date-parts":[[2022,4,6]]}},"container-title":["2022 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9741235\/9741095\/09741260.pdf?arnumber=9741260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,4]],"date-time":"2022-08-04T20:43:56Z","timestamp":1659645836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9741260\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,2]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/cgo53902.2022.9741260","relation":{},"subject":[],"published":{"date-parts":[[2022,4,2]]}}}