{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T16:52:28Z","timestamp":1743267148550,"version":"3.37.3"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T00:00:00Z","timestamp":1698451200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T00:00:00Z","timestamp":1698451200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0115304"],"award-info":[{"award-number":["2022ZD0115304"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072479"],"award-info":[{"award-number":["62072479"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Guangdong Natural Science Foundation","doi-asserted-by":"publisher","award":["2021A1515011836"],"award-info":[{"award-number":["2021A1515011836"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004000","name":"Guangzhou Science and Technology Projects","doi-asserted-by":"publisher","award":["202201011388"],"award-info":[{"award-number":["202201011388"]}],"id":[{"id":"10.13039\/501100004000","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,28]]},"DOI":"10.1109\/iccad57390.2023.10323944","type":"proceedings-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T18:58:45Z","timestamp":1701370725000},"page":"1-9","source":"Crossref","is-referenced-by-count":4,"title":["Automatic Kernel Generation for Large Language Models on Deep Learning Accelerators"],"prefix":"10.1109","author":[{"given":"Fuyu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-Sen University,Guangzhou,China"}]},{"given":"Minghua","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-Sen University,Guangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Improving language understanding by generative pretraining","author":"Radford","year":"2018","journal-title":"OpenAI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"ref3","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI"},{"article-title":"Lan-guage models are few-shot learners","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)","author":"Brown","key":"ref4"},{"volume-title":"Palm: Scaling language modeling with pathways","year":"2023","author":"Chowdhery","key":"ref5"},{"journal-title":"OpenAI blog","article-title":"Gpt-4 technical report","year":"2019","key":"ref6"},{"article-title":"Attention is all you need","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)","author":"Vaswani","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"volume-title":"NVDLA","key":"ref10","article-title":"Tensor core"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476138"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"article-title":"Ansor: Generating {High-Performance} tensor programs for deep learning","volume-title":"Proceedings of the 14th USENIX symposium on operating systems design and implementation (OSDI)","author":"Zheng","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00050"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454106"},{"volume-title":"Gurobi solver","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15582-6_49"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582061"},{"article-title":"{TVM}: An automated {End-to-End} optimizing compiler for deep learning","volume-title":"Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Chen","key":"ref20"},{"article-title":"Learning to optimize tensor programs","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)","author":"Chen","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575737"},{"article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)","author":"Sutton","key":"ref24"},{"article-title":"Off-policy reinforcement learning with delayed rewards","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Han","key":"ref25"},{"article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proceedings of the International conference on machine learning (ICML)","author":"Mnih","key":"ref26"},{"article-title":"Recurrent experience replay in distributed reinforcement learning","volume-title":"Proceedings of the International conference on learning representations (ICLR)","author":"Kapturowski","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)","author":"Chen","key":"ref30"},{"article-title":"Reinforcement learning with sparse rewards using guidance from offline demonstration","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Rengarajan","key":"ref31"},{"key":"ref32","first-page":"27 042","article-title":"Online decision transformer","volume-title":"International Conference on Machine Learning","author":"Zheng"},{"article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Haarnoja","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00058"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480114"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527442"}],"event":{"name":"2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD)","start":{"date-parts":[[2023,10,28]]},"location":"San Francisco, CA, USA","end":{"date-parts":[[2023,11,2]]}},"container-title":["2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10323590\/10323543\/10323944.pdf?arnumber=10323944","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T22:17:37Z","timestamp":1709417857000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10323944\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,28]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iccad57390.2023.10323944","relation":{},"subject":[],"published":{"date-parts":[[2023,10,28]]}}}