{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T06:01:01Z","timestamp":1777874461549,"version":"3.51.4"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Academic Research Fund Tier 1","award":["FY2021"],"award-info":[{"award-number":["FY2021"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpds.2026.3675079","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:40:55Z","timestamp":1773862855000},"page":"1205-1218","source":"Crossref","is-referenced-by-count":0,"title":["Texplorer: Efficient Tensor Program Optimization for GPUs Using a Highly Constrained Search Space"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9763-3319","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"first","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5009-3514","authenticated-orcid":false,"given":"Bin","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4281-2053","authenticated-orcid":false,"given":"Weng-Fai","family":"Wong","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","first-page":"3393","article-title":"Learning to optimize tensor programs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chen","year":"2018"},{"key":"ref4","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. USENIX Symp. Operating Syst. Des. Implementation","author":"Zheng","year":"2020"},{"key":"ref5","first-page":"35783","article-title":"Tensor program optimization with probabilistic programs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Shao","year":"2022"},{"key":"ref6","first-page":"181","article-title":"A deep learning based cost model for automatic code optimization","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"Baghdadi","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716269"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656626"},{"key":"ref9","first-page":"2021","article-title":"TenSet: A large-scale program performance dataset for learned tensor compilers","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track (Round 1)","author":"Zheng"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651348"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656631"},{"key":"ref12","article-title":"Explore as a storm, exploit as a droplet: A unified search technique for the ansor optimizer","author":"Canesche","year":"2024"},{"key":"ref13","first-page":"233","article-title":"ROLLER: Fast and efficient tensor compilation for deep learning","volume-title":"Proc. USENIX Symp. Operating Syst. Des. Implementation","author":"Zhu","year":"2022"},{"key":"ref14","first-page":"289","article-title":"Enabling tensor language model to assist in generating High-Performancetensor programs for deep learning","volume-title":"Proc. USENIX Symp. Operating Syst. Des. Implementation","author":"Zhai","year":"2024"},{"key":"ref15","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. USENIX Symp. Operating Syst. Des. Implementation","author":"Chen","year":"2018"},{"key":"ref16","article-title":"CUDA C++ programming guide","year":"2025"},{"key":"ref17","article-title":"Naming convention for CUDA tags","author":"Apache","year":"2024"},{"key":"ref18","article-title":"TVM verify GPU code","author":"Apache","year":"2024"},{"key":"ref19","article-title":"Tvm target kind","author":"Apache","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2016604.2016608"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00041"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref24","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Radford","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.373"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref29","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"issue":"8","key":"ref30","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3650109"},{"key":"ref34","first-page":"680","article-title":"ALCOP: Automatic load-compute pipelining in deep learning compiler for AI-GPUs","volume-title":"Proc. Mach. Learn. Syst.","volume":"5","author":"Huang","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640390"},{"key":"ref36","article-title":"FTuner: A fast dynamic shape tensors program auto-tuner for deep learning compilers","volume":"abs\/2407.21418","author":"Mu","year":"2024","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00076"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/11434582\/11442641.pdf?arnumber=11442641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:49:27Z","timestamp":1777578567000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11442641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":37,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2026.3675079","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}