{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:45:48Z","timestamp":1783784748247,"version":"3.55.0"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Dutch Research Council (NWO) Perspectief Program ZERO-ARM P3"},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research, ComPort: Rigorous Testing Methods to Safeguard Software Porting","doi-asserted-by":"publisher","award":["78284"],"award-info":[{"award-number":["78284"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3411473","type":"journal-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T17:31:47Z","timestamp":1717781507000},"page":"126135-126144","source":"Crossref","is-referenced-by-count":4,"title":["How Much Can We Gain From Tensor Kernel Fusion on GPUs?"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2873-6418","authenticated-orcid":false,"given":"Wei","family":"Sun","sequence":"first","affiliation":[{"name":"Electronic System Group, Eindhoven University of Technology, Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3734-9137","authenticated-orcid":false,"given":"Ang","family":"Li","sequence":"additional","affiliation":[{"name":"Physical and Computational Sciences Directorate, Pacific Northwest National Laboratory, Richland, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2518-6847","authenticated-orcid":false,"given":"Sander","family":"Stuijk","sequence":"additional","affiliation":[{"name":"Electronic System Group, Eindhoven University of Technology, Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4506-5732","authenticated-orcid":false,"given":"Henk","family":"Corporaal","sequence":"additional","affiliation":[{"name":"Electronic System Group, Eindhoven University of Technology, Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"AMD CDNA2 Architecture White Paper","year":"2022"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref3","first-page":"578","article-title":"$TVM$: An automated $end-to-end$ optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Chen"},{"key":"ref4","first-page":"873","article-title":"Vs-quant: Per-vector scaled quantization for accurate low-precision neural network inference","volume":"3","author":"Dai","year":"2021","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref5","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Dao"},{"key":"ref6","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref7","article-title":"A survey of quantization methods for efficient neural network inference","author":"Gholami","year":"2021","journal-title":"arXiv:2103.13630"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00064"},{"key":"ref10","volume-title":"NVIDIA Ampere Architecture White Paper","year":"2020"},{"key":"ref11","volume-title":"Accelerating Convolution With Tensor Cores in Cutlass","year":"2021"},{"key":"ref12","volume-title":"Cublas","year":"2022"},{"key":"ref13","volume-title":"Cudnn","year":"2022"},{"key":"ref14","volume-title":"NVIDIA Hopper Architecture White Paper","year":"2022"},{"key":"ref15","volume-title":"NVIDIA Jetson Orin","year":"2022"},{"key":"ref16","volume-title":"NVIDIA Nsight","year":"2022"},{"key":"ref17","volume-title":"Occupancy","year":"2022"},{"key":"ref18","volume-title":"Tensorrt","year":"2022"},{"key":"ref19","volume-title":"Cutlass","year":"2023"},{"key":"ref20","volume-title":"Cutlass Tensor Fusion","year":"2023"},{"key":"ref21","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NIPS","author":"Paszke"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-39932-9_5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3406117"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3217824"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3134930"},{"key":"ref28","volume-title":"The Transformer Family Version 2.0","author":"Weng","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref30","volume-title":"AITemplate","author":"Xu","year":"2022"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/10380310\/10551817-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10551817.pdf?arnumber=10551817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T06:21:15Z","timestamp":1726640475000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10551817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3411473","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}