{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:19:09Z","timestamp":1772695149050,"version":"3.50.1"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006826","name":"EU","doi-asserted-by":"publisher","award":["PID2022-136315OB-I00,MICIU\/AEI\/10.13039\/501100011033"],"award-info":[{"award-number":["PID2022-136315OB-I00,MICIU\/AEI\/10.13039\/501100011033"]}],"id":[{"id":"10.13039\/100006826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2246035,2402804"],"award-info":[{"award-number":["2246035,2402804"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/hpca68181.2026.11408440","type":"proceedings-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:47:22Z","timestamp":1772657242000},"page":"1-14","source":"Crossref","is-referenced-by-count":0,"title":["QuCo: Efficient and Flexible Hardware-Driven Automatic Configuration of Tile Transfers in GPUs"],"prefix":"10.1109","author":[{"given":"Nicol\u00e1s","family":"Meseguer","sequence":"first","affiliation":[{"name":"Universidad de Murcia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daoxuan","family":"Xu","sequence":"additional","affiliation":[{"name":"William & Mary"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Sun","sequence":"additional","affiliation":[{"name":"William & Mary"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Pellauer","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9 L.","family":"Abell\u00e1n","sequence":"additional","affiliation":[{"name":"Universidad de Murcia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel E.","family":"Acacio","sequence":"additional","affiliation":[{"name":"Universidad de Murcia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC62836.2024.10938479"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.31"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569666"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063400"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555258"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/mm.2023.3256796"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1145\/3350755.3400252","volume-title":"A computational model for tensor core units","author":"Chowdhury","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00086"},{"key":"ref9","volume-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","author":"Dao","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/77626.79170"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00040"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2022.11.003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2021.3096191"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.56021\/9781421407944"},{"key":"ref15","volume-title":"Deep residual learning for image recognition","author":"He","year":"2015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3570638"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3068281"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.06.041"},{"key":"ref19","volume-title":"Why Data Center GPUs Are Essential to Innovation","year":"2024"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1145\/3341301.3359630","article-title":"Taso: optimizing deep learning computation with automatic generation of graph substitutions","volume-title":"Proceedings of the 27th ACM Symposium on Operating Systems Principles","author":"Jia","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2980983.2908117"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00047"},{"key":"ref24","volume-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2872887.2750418"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628107"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3517020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1110.0940"},{"key":"ref29","volume-title":"Dissecting the nvidia hopper architecture through microbenchmarking and multiple level analysis","author":"Luo","year":"2025"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1109\/IPDPS57955.2024.00064","volume-title":"Benchmarking and dissecting the nvidia hopper gpu architecture","author":"Luo","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623782"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2018.2873679"},{"key":"ref33","volume-title":"cublas"},{"key":"ref34","volume-title":"Cuda c++ programming guide. version 12.4"},{"key":"ref35","volume-title":"Cutlass"},{"key":"ref36","year":"2025","journal-title":"The engine behind ai factories - nvidia blackwell architecture"},{"key":"ref37","year":"2025","journal-title":"Nvidia rtx pro blackwell gpu architecture"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3652892.3700768"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.30880\/ijie.2024.16.01.026"},{"key":"ref40","volume-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref41","volume-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942177"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774761"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322230"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01261-8_1","volume-title":"Group normalization","author":"Wu","year":"2018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3729262"}],"event":{"name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408404\/11408433\/11408440.pdf?arnumber=11408440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:47:03Z","timestamp":1772693223000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/hpca68181.2026.11408440","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}