{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T23:14:40Z","timestamp":1776122080658,"version":"3.50.1"},"reference-count":13,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T00:00:00Z","timestamp":1708300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T00:00:00Z","timestamp":1708300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003359","name":"Generalitat Valenciana","doi-asserted-by":"publisher","award":["Santiago Grisol\u00eda"],"award-info":[{"award-number":["Santiago Grisol\u00eda"]}],"id":[{"id":"10.13039\/501100003359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003359","name":"Generalitat Valenciana","doi-asserted-by":"publisher","award":["PROMETEO 2023-CIPROM\/2022\/20"],"award-info":[{"award-number":["PROMETEO 2023-CIPROM\/2022\/20"]}],"id":[{"id":"10.13039\/501100003359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011033","name":"Agencia Estatal de Investigaci\u00f3n","doi-asserted-by":"publisher","award":["FJC2019-039222-I"],"award-info":[{"award-number":["FJC2019-039222-I"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011033","name":"Agencia Estatal de Investigaci\u00f3n","doi-asserted-by":"publisher","award":["PID2020-113656RB-C22"],"award-info":[{"award-number":["PID2020-113656RB-C22"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011011","name":"Junta de Andaluc\u00eda","doi-asserted-by":"publisher","award":["POSTDOC_21_00025"],"award-info":[{"award-number":["POSTDOC_21_00025"]}],"id":[{"id":"10.13039\/501100011011","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004233","name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004233","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2024,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    We address the efficient implementation of the convolution operator on the GAP8 parallel ultra-low power platform (PULP), a heterogeneous multi-core processor equipped with a fabric controller (FC); a cluster of eight compute cores; and a four-level memory hierarchy with scratchpads instead of conventional, hardware-assisted cache memories. Our solution for this platform transforms the convolution into a general matrix\u2013matrix multiplication (\n                    <jats:sc>gemm<\/jats:sc>\n                    ) via the lowering approach, demonstrating that it is possible to attain reasonable performance on the GAP8 by carefully adapting techniques such as tiling and loop parallelism, which are mainstream in the multi-threaded, cache-aware realization of\n                    <jats:sc>gemm<\/jats:sc>\n                    .\n                  <\/jats:p>","DOI":"10.1007\/s11227-024-05927-y","type":"journal-article","created":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T15:02:22Z","timestamp":1708354942000},"page":"12623-12643","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Parallel GEMM-based convolution for deep learning on multicore RISC-V processors"],"prefix":"10.1007","volume":"80","author":[{"given":"Cristian","family":"Ram\u00edrez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adri\u00e1n","family":"Castell\u00f3","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"H\u00e9ctor","family":"Mart\u00ednez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,19]]},"reference":[{"key":"5927_CR1","doi-asserted-by":"crossref","unstructured":"Hazelwood K, Bird S, Brooks D, Chintala S, Diril U, Dzhulgakov D, Fawzy M, Jia B, Jia Y, Kalro A, Law J, Lee K, Lu J, Noordhuis P, Smelyanskiy M, Xiong L, Wang X (2018) Applied machine learning at Facebook: A datacenter infrastructure perspective. In: IEEE Int. Symp. HPC Architecture, pp 620\u2013629","DOI":"10.1109\/HPCA.2018.00059"},{"key":"5927_CR2","unstructured":"Park J, Naumov M, Basu P, Deng S, Kalaiah A, Khudia D, Law J, Malani P, Malevich A, Nadathur S, Pino J, Schatz M, Sidorov A, Sivakumar V, Tulloch A, Wang X, Wu Y, Yuen H, Diril U, Dzhulgakov D, Hazelwood K, Jia B, Jia Y, Qiao L, Rao V, Rotem N, Yoo S, Smelyanskiy M (2018) Deep learning inference in Facebook data centers: characterization, performance optimizations and hardware implications. arXiv:1811.09886"},{"key":"5927_CR3","doi-asserted-by":"crossref","unstructured":"Wu C, Brooks D, Chen K, Chen D, Choudhury S, Dukhan M, Hazelwood K, Isaac E, Jia Y, Jia B, Leyvand T, Lu H, Lu Y, Qiao L, Reagen B, Spisak J, Sun F, Tulloch A, Vajda P, Wang X, Wang Y, Wasti B, Wu Y, Xian R, Yoo S, Zhang P (2019) Machine learning at Facebook: Understanding inference at the edge. In: IEEE international symposium HPC architecture, pp 331\u2013344","DOI":"10.1109\/HPCA.2019.00048"},{"key":"5927_CR4","doi-asserted-by":"crossref","unstructured":"Garofalo A, Rusci M, Conti F, Rossi D, Benini L (2019) PULP-NN: a computing library for quantized neural network inference at the edge on RISC-V based parallel ultra low power clusters. In: 2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS), pp 33\u201336","DOI":"10.1109\/ICECS46596.2019.8965067"},{"key":"5927_CR5","unstructured":"Chellapilla K, Puri S, Simard P (2006) High performance convolutional neural networks for document processing. In: 10th international workshop on frontiers in handwriting recognition, Universit\u00e9 de Rennes, France"},{"issue":"12","key":"5927_CR6","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","volume":"105","author":"V Sze","year":"2017","unstructured":"Sze V, Chen Y-H, Yang T-J, Emer JS (2017) Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12):2295\u20132329","journal-title":"Proc. IEEE"},{"issue":"3","key":"5927_CR7","doi-asserted-by":"publisher","first-page":"12:1","DOI":"10.1145\/1356052.1356053","volume":"34","author":"K Goto","year":"2008","unstructured":"Goto K, van de Geijn RA (2008) Anatomy of a high-performance matrix multiplication. ACM Trans. Math. Softw. 34(3):12:1-12:25","journal-title":"ACM Trans. Math. Softw."},{"key":"5927_CR8","unstructured":"Smith TM, van\u00a0de Geijn RA (2019) The MOMMS family of matrix multiplication algorithms. CoRR, Arxiv:abs\/1904.05717"},{"key":"5927_CR9","doi-asserted-by":"crossref","unstructured":"Gunnels JA, Gustavson FG, Henry GM, van\u00a0de Geijn RA (2004) A family of high-performance matrix multiplication algorithms. In: Proceedings of the 7th international Conference on Applied Parallel Computing, pp 256\u2013265","DOI":"10.1007\/11558958_30"},{"key":"5927_CR10","doi-asserted-by":"crossref","unstructured":"Castell\u00f3 A, Igual FD, Quintana-Ort\u00ed ES (2022) Anatomy of the BLIS family of algorithms for matrix multiplication. In: 2022 30th Euromicro international Conference on Parallel, Distributed and Network-based Processing (PDP), pp 92\u201399","DOI":"10.1109\/PDP55904.2022.00023"},{"issue":"7","key":"5927_CR11","doi-asserted-by":"publisher","first-page":"1970","DOI":"10.1109\/JSSC.2019.2912307","volume":"54","author":"A Pullini","year":"2019","unstructured":"Pullini A, Rossi D, Loi I, Tagliavini G, Benini L (2019) Mr. Wolf: an energy-precision scalable parallel ultra low power SoC for IoT edge processing. IEEE J. Solid-State Circuits 54(7):1970\u20131981","journal-title":"IEEE J. Solid-State Circuits"},{"issue":"16","key":"5927_CR12","doi-asserted-by":"publisher","first-page":"18051","DOI":"10.1007\/s11227-022-04581-6","volume":"78","author":"C Ram\u00edrez","year":"2022","unstructured":"Ram\u00edrez C, Castell\u00f3 A, Quintana-Ort\u00ed ES (2022) A BLIS-like matrix multiplication for machine learning in the RISC-V ISA-based GAP8 processor. J. Supercomput. 78(16):18051\u201318060. https:\/\/doi.org\/10.1007\/s11227-022-04581-6","journal-title":"J. Supercomput."},{"key":"5927_CR13","doi-asserted-by":"publisher","unstructured":"Ram\u00edrez C, Castell\u00f3 A, Mart\u00ednez H, Quintana-Ort\u00ed ES (2023) Performance analysis of matrix multiplication for deep learning on the edge. In: High Performance Computing. ISC High Performance 2022 International Workshops: Hamburg, Germany, May 29\u2013June 2, 2022, Revised Selected Papers. Springer-Verlag, Berlin, Heidelberg, pp 65\u201376. Available: https:\/\/doi.org\/10.1007\/978-3-031-23220-6_5","DOI":"10.1007\/978-3-031-23220-6_5"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-05927-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-05927-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-05927-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T06:44:17Z","timestamp":1717483457000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-05927-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,19]]},"references-count":13,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["5927"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-05927-y","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3394564\/v1","asserted-by":"object"}]},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,19]]},"assertion":[{"value":"21 January 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}