{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:32:06Z","timestamp":1777653126767,"version":"3.51.4"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["3G051318"],"award-info":[{"award-number":["3G051318"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,9,1]]},"DOI":"10.1109\/tpds.2021.3136457","type":"journal-article","created":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T20:27:17Z","timestamp":1639772837000},"page":"2230-2248","source":"Crossref","is-referenced-by-count":17,"title":["Flexible Performant GEMM Kernels on GPUs"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6420-6476","authenticated-orcid":false,"given":"Thomas","family":"Faingnaert","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Besard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0317-2089","authenticated-orcid":false,"given":"Bjorn","family":"De Sutter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Forward-mode automatic differentiation in Julia","author":"revels","year":"2016"},{"key":"ref38","article-title":"Design of a high-performance GEMM-like tensor-tensor multiplication","author":"springer","year":"2016"},{"key":"ref33","article-title":"Matrix capsules with EM routing","author":"hinton","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","article-title":"GPUifyLoops.jl: Support for writing loop-based code that executes both on CPU and GPU","author":"churavy","year":"2020"},{"key":"ref31","article-title":"The LLVM compiler infrastructure project","year":"2020","journal-title":"LLVM Contributors"},{"key":"ref30","article-title":"The Julia language official documentation","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1021\/ct1007247"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.60"},{"key":"ref35","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Int Conf Adv Neural Inf Process Syst 32"},{"key":"ref34","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Symp Operating Syst Des Implementation"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2872064"},{"key":"ref27","article-title":"Julia micro-benchmarks","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.advengsoft.2019.02.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ScalA49573.2019.00008"},{"key":"ref1","article-title":"BLAS (Basic Linear Algebra Subprograms)","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1186785.1186794"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/16M108968X"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661182"},{"key":"ref24","article-title":"CUDA C++ programming guide","year":"2020"},{"key":"ref23","article-title":"The landscape of software for tensor computations","author":"psarras","year":"2021"},{"key":"ref26","article-title":"The Julia language","year":"2020"},{"key":"ref25","article-title":"OpenCL: An open standard for parallel programming of heterogeneous systems","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3211346.3211354"},{"key":"ref51","article-title":"Automatic kernel generation for Volta Tensor Cores","author":"bhaskaracharya","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3378678.3391880"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3317550.3321441"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3183895.3183900"},{"key":"ref40","article-title":"KernelAbstractions.jl: Heterogeneous programming in Julia","author":"churavy","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2017.02.016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/00268970500275780"},{"key":"ref14","article-title":"The landscape of high-performance tensor contractions","author":"springer","year":"2017","journal-title":"Proc Workshop Batched Reproducible Reduced Precis Basic Linear Algebra Subprograms"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2015.106"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3157733"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2014.02.051"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807671"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21236\/ADA580199"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00052"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00050"},{"key":"ref6","article-title":"Getting started with tensor cores in HPC","author":"mehta","year":"2019","journal-title":"Proc NVIDIA GPU Technol Conf"},{"key":"ref5","first-page":"1","article-title":"Harnessing Tensor Cores FP16 arithmetic to accelerate linear solvers and HPC scientific applications","author":"haidar","year":"2018","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref8","article-title":"Deep learning performance guide","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00071"},{"key":"ref49","article-title":"High performance code generation in MLIR: An early case study with GEMM","author":"bondhugula","year":"2020"},{"key":"ref9","article-title":"NVIDIA V100","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2012.19"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400713"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1375527.1375562"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626412500107"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"ref41","article-title":"CUTLASS: CUDA templates for linear algebra subroutines","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375595"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/19M1282040"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9696253\/09655458.pdf?arnumber=9655458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T21:09:45Z","timestamp":1650920985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9655458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,1]]},"references-count":52,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3136457","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":[[2022,9,1]]}}}