{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T16:56:31Z","timestamp":1782924991657,"version":"3.54.5"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,25]]},"DOI":"10.1109\/ipdps65963.2026.00093","type":"proceedings-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T20:55:16Z","timestamp":1782852916000},"page":"1105-1119","source":"Crossref","is-referenced-by-count":0,"title":["Just-in-Time Convolution and GEMM Code Generation for SIMD Architectures"],"prefix":"10.1109","author":[{"given":"Alexandre de Limas","family":"Santana","sequence":"first","affiliation":[{"name":"Universitat Politècnica de Catalunya,Barcelona Supercomputing Center,Barcelona, Catalunya,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adri\u00e0","family":"Armejach","sequence":"additional","affiliation":[{"name":"Universitat Politècnica de Catalunya,Barcelona Supercomputing Center,Barcelona, Catalunya,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Casas","sequence":"additional","affiliation":[{"name":"Universitat Politècnica de Catalunya,Barcelona Supercomputing Center,Barcelona, Catalunya,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2019.2899330"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1109\/SC41405.2020.00051","article-title":"Co-Design for A64FX Manycore Processor and","volume-title":"Fugaku","author":"Sato","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503219"},{"key":"ref4","article-title":"Oneapi deep neural network library","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2017.35"},{"key":"ref7","article-title":"The risc-v vector extension","author":"International","year":"2023"},{"key":"ref8","article-title":"Xbyak, a c++ jit assembler for x86 (ia32), x64 (amd64, x86-64)","author":"Shigeo","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1587\/transele.2021LHP0001"},{"key":"ref10","article-title":"D1-h soc introduction","author":"Technology"},{"key":"ref11","article-title":"Banana pi bpi-f133 risc-v development board","author":"Pi","year":"2024"},{"key":"ref12","article-title":"Milk-v pioneer: Native risc-v development motherboard"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref14","article-title":"Hiera: A hierarchical vision transformer without the bells-and-whistles","author":"Ryali","year":"2023","journal-title":"ICML"},{"key":"ref15","article-title":"Next-vit: Next generation vision transformer for efficient deployment in realistic industrial scenarios","author":"Li","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref17","first-page":"15 909","article-title":"Repvit: Revisiting mobile cnn from vit perspective","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Wang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref20","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref23","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and\u00a1 0.5 mb model size","author":"Iandola","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/77626.79170"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref26","first-page":"5776","article-title":"High performance zero-memory overhead direct convolutions","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref27","article-title":"Distributed deep learning using synchronous stochastic gradient descent","author":"Das","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00069"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577435"},{"key":"ref30","volume-title":"Advanced Compiler Design and Implementation","author":"Muchnick","year":"1997"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00034"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3579990.3580024"},{"key":"ref34","article-title":"Openc906 processor datasheet","year":"2025"},{"key":"ref35","article-title":"The RISC-V Instruction Set Manual: Volume I: RISC-V Unprivileged ISA, Document Version 0.7","year":"2019"},{"key":"ref36","article-title":"Spacemit k1 8 core risc-v chip brief","author":"Pi","year":"2024"},{"key":"ref37","article-title":"Openc910 processor datasheet","year":"2025"},{"key":"ref38","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874254"},{"key":"ref40","article-title":"Benchdnn github repository","year":"2025"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3575861"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2017.7995254"},{"key":"ref43","article-title":"Low-memory gemm-based convolution algorithms for deep neural networks","author":"Anderson","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624229"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CGO57630.2024.10444883"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673121"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3362060"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0155"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD56317.2022.00061"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CGO57630.2024.10444827"},{"key":"ref52","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Abadi"}],"event":{"name":"2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","location":"New Orleans, LA, USA","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11575315\/11575316\/11575851.pdf?arnumber=11575851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T16:29:16Z","timestamp":1782923356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11575851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/ipdps65963.2026.00093","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]}}}